19694 lines
578 KiB
JSON
19694 lines
578 KiB
JSON
{
|
|
"groups": [
|
|
{
|
|
"id": "model.language_model.embed_tokens.weight::rows",
|
|
"tensor": "model.language_model.embed_tokens.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 248320,
|
|
"population": 248320,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.embed_tokens.weight::columns",
|
|
"tensor": "model.language_model.embed_tokens.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 248320,
|
|
"population": 2048,
|
|
"dimension": 248320,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.0.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.0.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.0.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.0.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.0.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.0.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.0.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.0.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.0.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.0.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.1.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.1.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.1.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.1.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.1.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.1.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.1.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.1.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.1.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.1.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.10.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.10.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.10.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.10.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.10.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.10.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.10.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.10.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.10.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.10.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.11.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.11.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.11.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.11.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.11.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.11.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.k_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.11.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.k_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.11.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.k_proj.weight::K_head0",
|
|
"tensor": "model.language_model.layers.11.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.k_proj.weight::K_head1",
|
|
"tensor": "model.language_model.layers.11.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.o_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.11.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.o_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.11.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 2048,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::gate_head0",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 768,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::gate_head1",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 1024,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1280,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::gate_head2",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1536,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1792,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::gate_head3",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 2048,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2304,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::gate_head4",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2560,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2816,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::gate_head5",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 3072,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3328,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::gate_head6",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3584,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3840,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.q_proj.weight::gate_head7",
|
|
"tensor": "model.language_model.layers.11.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 4096,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.v_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.11.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.v_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.11.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.v_proj.weight::V_head0",
|
|
"tensor": "model.language_model.layers.11.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.11.self_attn.v_proj.weight::V_head1",
|
|
"tensor": "model.language_model.layers.11.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.12.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.12.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.12.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.12.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.12.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.12.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.12.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.12.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.12.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.12.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.13.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.13.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.13.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.13.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.13.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.13.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.13.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.13.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.13.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.13.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.14.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.14.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.14.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.14.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.14.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.14.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.14.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.14.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.14.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.14.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.15.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.15.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.15.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.15.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.15.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.15.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.k_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.15.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.k_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.15.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.k_proj.weight::K_head0",
|
|
"tensor": "model.language_model.layers.15.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.k_proj.weight::K_head1",
|
|
"tensor": "model.language_model.layers.15.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.o_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.15.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.o_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.15.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 2048,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::gate_head0",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 768,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::gate_head1",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 1024,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1280,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::gate_head2",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1536,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1792,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::gate_head3",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 2048,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2304,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::gate_head4",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2560,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2816,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::gate_head5",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 3072,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3328,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::gate_head6",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3584,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3840,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.q_proj.weight::gate_head7",
|
|
"tensor": "model.language_model.layers.15.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 4096,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.v_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.15.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.v_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.15.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.v_proj.weight::V_head0",
|
|
"tensor": "model.language_model.layers.15.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.15.self_attn.v_proj.weight::V_head1",
|
|
"tensor": "model.language_model.layers.15.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.16.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.16.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.16.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.16.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.16.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.16.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.16.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.16.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.16.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.16.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.17.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.17.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.17.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.17.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.17.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.17.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.17.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.17.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.17.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.17.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.18.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.18.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.18.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.18.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.18.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.18.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.18.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.18.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.18.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.18.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.19.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.19.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.19.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.19.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.19.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.19.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.k_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.19.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.k_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.19.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.k_proj.weight::K_head0",
|
|
"tensor": "model.language_model.layers.19.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.k_proj.weight::K_head1",
|
|
"tensor": "model.language_model.layers.19.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.o_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.19.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.o_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.19.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 2048,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::gate_head0",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 768,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::gate_head1",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 1024,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1280,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::gate_head2",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1536,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1792,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::gate_head3",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 2048,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2304,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::gate_head4",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2560,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2816,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::gate_head5",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 3072,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3328,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::gate_head6",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3584,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3840,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.q_proj.weight::gate_head7",
|
|
"tensor": "model.language_model.layers.19.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 4096,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.v_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.19.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.v_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.19.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.v_proj.weight::V_head0",
|
|
"tensor": "model.language_model.layers.19.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.19.self_attn.v_proj.weight::V_head1",
|
|
"tensor": "model.language_model.layers.19.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.2.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.2.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.2.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.2.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.2.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.2.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.2.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.2.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.2.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.2.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.20.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.20.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.20.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.20.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.20.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.20.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.20.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.20.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.20.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.20.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.21.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.21.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.21.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.21.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.21.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.21.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.21.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.21.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.21.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.21.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.22.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.22.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.22.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.22.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.22.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.22.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.22.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.22.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.22.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.22.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.23.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.23.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.23.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.23.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.23.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.23.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.k_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.23.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.k_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.23.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.k_proj.weight::K_head0",
|
|
"tensor": "model.language_model.layers.23.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.k_proj.weight::K_head1",
|
|
"tensor": "model.language_model.layers.23.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.o_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.23.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.o_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.23.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 2048,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::gate_head0",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 768,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::gate_head1",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 1024,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1280,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::gate_head2",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1536,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1792,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::gate_head3",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 2048,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2304,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::gate_head4",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2560,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2816,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::gate_head5",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 3072,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3328,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::gate_head6",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3584,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3840,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.q_proj.weight::gate_head7",
|
|
"tensor": "model.language_model.layers.23.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 4096,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.v_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.23.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.v_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.23.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.v_proj.weight::V_head0",
|
|
"tensor": "model.language_model.layers.23.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.23.self_attn.v_proj.weight::V_head1",
|
|
"tensor": "model.language_model.layers.23.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.3.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.3.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.3.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.3.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.3.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.3.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.k_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.3.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.k_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.3.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.k_proj.weight::K_head0",
|
|
"tensor": "model.language_model.layers.3.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.k_proj.weight::K_head1",
|
|
"tensor": "model.language_model.layers.3.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.o_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.3.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.o_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.3.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 2048,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::gate_head0",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 768,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::gate_head1",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 1024,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1280,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::gate_head2",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1536,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1792,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::gate_head3",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 2048,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2304,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::gate_head4",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2560,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2816,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::gate_head5",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 3072,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3328,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::gate_head6",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3584,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3840,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.q_proj.weight::gate_head7",
|
|
"tensor": "model.language_model.layers.3.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 4096,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.v_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.3.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.v_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.3.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.v_proj.weight::V_head0",
|
|
"tensor": "model.language_model.layers.3.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.3.self_attn.v_proj.weight::V_head1",
|
|
"tensor": "model.language_model.layers.3.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.4.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.4.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.4.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.4.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.4.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.4.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.4.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.4.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.4.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.4.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.5.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.5.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.5.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.5.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.5.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.5.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.5.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.5.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.5.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.5.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.6.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.6.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.6.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.6.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.6.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.6.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.6.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.6.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.6.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.6.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.7.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.7.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.7.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.7.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.7.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.7.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.k_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.7.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.k_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.7.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.k_proj.weight::K_head0",
|
|
"tensor": "model.language_model.layers.7.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.k_proj.weight::K_head1",
|
|
"tensor": "model.language_model.layers.7.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.o_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.7.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.o_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.7.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 2048,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::gate_head0",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 768,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::gate_head1",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 1024,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1280,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::gate_head2",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1536,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1792,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::gate_head3",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 2048,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2304,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::gate_head4",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2560,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2816,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::gate_head5",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 3072,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3328,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::gate_head6",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3584,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3840,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.q_proj.weight::gate_head7",
|
|
"tensor": "model.language_model.layers.7.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 4096,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.v_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.7.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.v_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.7.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.v_proj.weight::V_head0",
|
|
"tensor": "model.language_model.layers.7.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.7.self_attn.v_proj.weight::V_head1",
|
|
"tensor": "model.language_model.layers.7.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.8.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.8.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.8.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.8.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.8.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.8.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.8.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.8.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.8.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.8.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_a.weight::rows",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_a.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_b.weight::rows",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_b.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 16,
|
|
"population": 16,
|
|
"dimension": 2048,
|
|
"stratum": "small_sample"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::rows",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::columns",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head0",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 128,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head1",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 128,
|
|
"stop": 256,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head2",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 384,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head3",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 384,
|
|
"stop": 512,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head4",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 640,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head5",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 640,
|
|
"stop": 768,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head6",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 896,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head7",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 896,
|
|
"stop": 1024,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head8",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1152,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head9",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1152,
|
|
"stop": 1280,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head10",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1408,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head11",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1408,
|
|
"stop": 1536,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head12",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1664,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head13",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1664,
|
|
"stop": 1792,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head14",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 1920,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::Q_head15",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1920,
|
|
"stop": 2048,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head0",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2176,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head1",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2176,
|
|
"stop": 2304,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head2",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2432,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head3",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2432,
|
|
"stop": 2560,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head4",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2688,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head5",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2688,
|
|
"stop": 2816,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head6",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 2944,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head7",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2944,
|
|
"stop": 3072,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head8",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3200,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head9",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3200,
|
|
"stop": 3328,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head10",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3456,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head11",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3456,
|
|
"stop": 3584,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head12",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3712,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head13",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3712,
|
|
"stop": 3840,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head14",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 3968,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::K_head15",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3968,
|
|
"stop": 4096,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head0",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4096,
|
|
"stop": 4224,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head1",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4224,
|
|
"stop": 4352,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head2",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4352,
|
|
"stop": 4480,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head3",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4480,
|
|
"stop": 4608,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head4",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4608,
|
|
"stop": 4736,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head5",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4736,
|
|
"stop": 4864,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head6",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4864,
|
|
"stop": 4992,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head7",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 4992,
|
|
"stop": 5120,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head8",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5120,
|
|
"stop": 5248,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head9",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5248,
|
|
"stop": 5376,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head10",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5376,
|
|
"stop": 5504,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head11",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5504,
|
|
"stop": 5632,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head12",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5632,
|
|
"stop": 5760,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head13",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5760,
|
|
"stop": 5888,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head14",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 5888,
|
|
"stop": 6016,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight::V_head15",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 6016,
|
|
"stop": 6144,
|
|
"population": 128,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_z.weight::rows",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.in_proj_z.weight::columns",
|
|
"tensor": "model.language_model.layers.9.linear_attn.in_proj_z.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.out_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.9.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.linear_attn.out_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.9.linear_attn.out_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.mlp.down_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.9.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.mlp.down_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.9.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.mlp.gate_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.9.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.mlp.gate_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.9.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.mlp.up_proj.weight::rows",
|
|
"tensor": "model.language_model.layers.9.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.language_model.layers.9.mlp.up_proj.weight::columns",
|
|
"tensor": "model.language_model.layers.9.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.0.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.0.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.0.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.0.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.0.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.0.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.0.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.0.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.0.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.0.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.0.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.0.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.0.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.0.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.0.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.0.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.1.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.1.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.1.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.1.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.1.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.1.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.1.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.1.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.1.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.1.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.1.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.1.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.1.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.1.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.1.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.1.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.10.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.10.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.10.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.10.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.10.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.10.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.10.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.10.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.10.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.10.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.10.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.10.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.10.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.10.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.10.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.10.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.11.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.11.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.11.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.11.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.11.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.11.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.11.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.11.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.11.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.11.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.11.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.11.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.11.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.11.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.11.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.11.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.12.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.12.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.12.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.12.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.12.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.12.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.12.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.12.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.12.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.12.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.12.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.12.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.12.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.12.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.12.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.12.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.13.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.13.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.13.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.13.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.13.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.13.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.13.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.13.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.13.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.13.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.13.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.13.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.13.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.13.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.13.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.13.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.14.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.14.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.14.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.14.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.14.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.14.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.14.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.14.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.14.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.14.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.14.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.14.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.14.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.14.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.14.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.14.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.15.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.15.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.15.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.15.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.15.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.15.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.15.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.15.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.15.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.15.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.15.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.15.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.15.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.15.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.15.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.15.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.16.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.16.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.16.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.16.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.16.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.16.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.16.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.16.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.16.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.16.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.16.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.16.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.16.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.16.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.16.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.16.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.17.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.17.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.17.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.17.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.17.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.17.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.17.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.17.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.17.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.17.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.17.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.17.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.17.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.17.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.17.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.17.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.18.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.18.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.18.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.18.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.18.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.18.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.18.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.18.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.18.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.18.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.18.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.18.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.18.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.18.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.18.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.18.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.19.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.19.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.19.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.19.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.19.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.19.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.19.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.19.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.19.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.19.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.19.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.19.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.19.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.19.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.19.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.19.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.2.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.2.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.2.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.2.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.2.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.2.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.2.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.2.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.2.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.2.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.2.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.2.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.2.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.2.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.2.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.2.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.20.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.20.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.20.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.20.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.20.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.20.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.20.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.20.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.20.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.20.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.20.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.20.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.20.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.20.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.20.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.20.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.21.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.21.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.21.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.21.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.21.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.21.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.21.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.21.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.21.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.21.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.21.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.21.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.21.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.21.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.21.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.21.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.22.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.22.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.22.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.22.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.22.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.22.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.22.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.22.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.22.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.22.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.22.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.22.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.22.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.22.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.22.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.22.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.23.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.23.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.23.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.23.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.23.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.23.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.23.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.23.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.23.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.23.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.23.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.23.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.23.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.23.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.23.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.23.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.3.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.3.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.3.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.3.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.3.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.3.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.3.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.3.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.3.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.3.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.3.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.3.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.3.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.3.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.3.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.3.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.4.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.4.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.4.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.4.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.4.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.4.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.4.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.4.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.4.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.4.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.4.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.4.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.4.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.4.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.4.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.4.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.5.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.5.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.5.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.5.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.5.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.5.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.5.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.5.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.5.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.5.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.5.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.5.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.5.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.5.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.5.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.5.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.6.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.6.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.6.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.6.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.6.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.6.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.6.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.6.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.6.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.6.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.6.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.6.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.6.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.6.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.6.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.6.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.7.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.7.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.7.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.7.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.7.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.7.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.7.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.7.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.7.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.7.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.7.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.7.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.7.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.7.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.7.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.7.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.8.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.8.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.8.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.8.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.8.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.8.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.8.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.8.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.8.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.8.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.8.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.8.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.8.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.8.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.8.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.8.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.9.attn.proj.weight::rows",
|
|
"tensor": "model.visual.blocks.9.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.9.attn.proj.weight::columns",
|
|
"tensor": "model.visual.blocks.9.attn.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.9.attn.qkv.weight::rows",
|
|
"tensor": "model.visual.blocks.9.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 3072,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.9.attn.qkv.weight::columns",
|
|
"tensor": "model.visual.blocks.9.attn.qkv.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 3072,
|
|
"population": 1024,
|
|
"dimension": 3072,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.9.mlp.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.blocks.9.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.9.mlp.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.blocks.9.mlp.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.9.mlp.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.blocks.9.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.blocks.9.mlp.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.blocks.9.mlp.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 4096,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.merger.linear_fc1.weight::rows",
|
|
"tensor": "model.visual.merger.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.merger.linear_fc1.weight::columns",
|
|
"tensor": "model.visual.merger.linear_fc1.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.merger.linear_fc2.weight::rows",
|
|
"tensor": "model.visual.merger.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.merger.linear_fc2.weight::columns",
|
|
"tensor": "model.visual.merger.linear_fc2.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 4096,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.patch_embed.proj.weight::rows",
|
|
"tensor": "model.visual.patch_embed.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1024,
|
|
"dimension": 1536,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.patch_embed.proj.weight::columns",
|
|
"tensor": "model.visual.patch_embed.proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 1024,
|
|
"population": 1536,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.pos_embed.weight::rows",
|
|
"tensor": "model.visual.pos_embed.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2304,
|
|
"population": 2304,
|
|
"dimension": 1024,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "model.visual.pos_embed.weight::columns",
|
|
"tensor": "model.visual.pos_embed.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2304,
|
|
"population": 1024,
|
|
"dimension": 2304,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.fc.weight::rows",
|
|
"tensor": "mtp.fc.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.fc.weight::columns",
|
|
"tensor": "mtp.fc.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 4096,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.mlp.down_proj.weight::rows",
|
|
"tensor": "mtp.layers.0.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.mlp.down_proj.weight::columns",
|
|
"tensor": "mtp.layers.0.mlp.down_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.mlp.gate_proj.weight::rows",
|
|
"tensor": "mtp.layers.0.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.mlp.gate_proj.weight::columns",
|
|
"tensor": "mtp.layers.0.mlp.gate_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.mlp.up_proj.weight::rows",
|
|
"tensor": "mtp.layers.0.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 6144,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.mlp.up_proj.weight::columns",
|
|
"tensor": "mtp.layers.0.mlp.up_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 6144,
|
|
"population": 2048,
|
|
"dimension": 6144,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.k_proj.weight::rows",
|
|
"tensor": "mtp.layers.0.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.k_proj.weight::columns",
|
|
"tensor": "mtp.layers.0.self_attn.k_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.k_proj.weight::K_head0",
|
|
"tensor": "mtp.layers.0.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.k_proj.weight::K_head1",
|
|
"tensor": "mtp.layers.0.self_attn.k_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.o_proj.weight::rows",
|
|
"tensor": "mtp.layers.0.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.o_proj.weight::columns",
|
|
"tensor": "mtp.layers.0.self_attn.o_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 2048,
|
|
"population": 2048,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::rows",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 4096,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::columns",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 4096,
|
|
"population": 2048,
|
|
"dimension": 4096,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::Q_head0",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::gate_head0",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::Q_head1",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 512,
|
|
"stop": 768,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::gate_head1",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 768,
|
|
"stop": 1024,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::Q_head2",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1024,
|
|
"stop": 1280,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::gate_head2",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1280,
|
|
"stop": 1536,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::Q_head3",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1536,
|
|
"stop": 1792,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::gate_head3",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 1792,
|
|
"stop": 2048,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::Q_head4",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2048,
|
|
"stop": 2304,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::gate_head4",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2304,
|
|
"stop": 2560,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::Q_head5",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2560,
|
|
"stop": 2816,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::gate_head5",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 2816,
|
|
"stop": 3072,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::Q_head6",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3072,
|
|
"stop": 3328,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::gate_head6",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3328,
|
|
"stop": 3584,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::Q_head7",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3584,
|
|
"stop": 3840,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.q_proj.weight::gate_head7",
|
|
"tensor": "mtp.layers.0.self_attn.q_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 3840,
|
|
"stop": 4096,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.v_proj.weight::rows",
|
|
"tensor": "mtp.layers.0.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 512,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.v_proj.weight::columns",
|
|
"tensor": "mtp.layers.0.self_attn.v_proj.weight",
|
|
"kind": "matrix",
|
|
"orientation": "columns",
|
|
"start": 0,
|
|
"stop": 512,
|
|
"population": 2048,
|
|
"dimension": 512,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.v_proj.weight::V_head0",
|
|
"tensor": "mtp.layers.0.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 0,
|
|
"stop": 256,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
},
|
|
{
|
|
"id": "mtp.layers.0.self_attn.v_proj.weight::V_head1",
|
|
"tensor": "mtp.layers.0.self_attn.v_proj.weight",
|
|
"kind": "head_rows",
|
|
"orientation": "rows",
|
|
"start": 256,
|
|
"stop": 512,
|
|
"population": 256,
|
|
"dimension": 2048,
|
|
"stratum": "primary"
|
|
}
|
|
],
|
|
"skips": [
|
|
{
|
|
"name": "model.language_model.layers.0.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.0.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.0.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.0.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.0.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.0.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.1.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.1.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.1.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.1.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.1.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.1.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.10.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.10.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.10.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.10.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.10.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.10.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.11.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.11.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.11.self_attn.k_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.11.self_attn.q_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.12.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.12.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.12.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.12.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.12.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.12.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.13.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.13.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.13.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.13.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.13.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.13.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.14.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.14.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.14.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.14.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.14.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.14.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.15.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.15.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.15.self_attn.k_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.15.self_attn.q_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.16.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.16.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.16.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.16.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.16.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.16.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.17.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.17.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.17.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.17.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.17.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.17.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.18.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.18.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.18.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.18.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.18.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.18.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.19.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.19.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.19.self_attn.k_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.19.self_attn.q_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.2.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.2.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.2.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.2.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.2.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.2.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.20.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.20.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.20.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.20.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.20.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.20.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.21.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.21.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.21.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.21.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.21.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.21.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.22.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.22.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.22.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.22.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.22.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.22.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.23.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.23.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.23.self_attn.k_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.23.self_attn.q_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.3.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.3.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.3.self_attn.k_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.3.self_attn.q_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.4.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.4.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.4.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.4.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.4.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.4.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.5.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.5.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.5.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.5.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.5.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.5.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.6.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.6.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.6.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.6.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.6.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.6.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.7.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.7.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.7.self_attn.k_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.7.self_attn.q_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.8.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.8.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.8.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.8.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.8.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.8.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.9.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.9.linear_attn.A_log",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.9.linear_attn.conv1d.weight",
|
|
"reason": "insufficient points or dimension <32",
|
|
"shape": [
|
|
6144,
|
|
1,
|
|
4
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.9.linear_attn.dt_bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
16
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.9.linear_attn.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
128
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.layers.9.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.language_model.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.0.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.0.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.0.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.0.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.0.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.0.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.0.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.0.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.1.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.1.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.1.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.1.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.1.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.1.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.1.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.1.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.10.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.10.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.10.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.10.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.10.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.10.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.10.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.10.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.11.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.11.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.11.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.11.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.11.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.11.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.11.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.11.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.12.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.12.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.12.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.12.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.12.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.12.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.12.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.12.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.13.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.13.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.13.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.13.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.13.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.13.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.13.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.13.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.14.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.14.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.14.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.14.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.14.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.14.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.14.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.14.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.15.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.15.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.15.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.15.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.15.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.15.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.15.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.15.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.16.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.16.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.16.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.16.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.16.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.16.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.16.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.16.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.17.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.17.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.17.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.17.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.17.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.17.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.17.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.17.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.18.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.18.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.18.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.18.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.18.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.18.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.18.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.18.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.19.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.19.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.19.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.19.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.19.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.19.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.19.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.19.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.2.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.2.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.2.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.2.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.2.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.2.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.2.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.2.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.20.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.20.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.20.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.20.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.20.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.20.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.20.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.20.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.21.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.21.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.21.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.21.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.21.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.21.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.21.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.21.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.22.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.22.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.22.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.22.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.22.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.22.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.22.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.22.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.23.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.23.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.23.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.23.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.23.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.23.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.23.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.23.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.3.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.3.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.3.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.3.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.3.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.3.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.3.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.3.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.4.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.4.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.4.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.4.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.4.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.4.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.4.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.4.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.5.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.5.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.5.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.5.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.5.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.5.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.5.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.5.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.6.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.6.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.6.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.6.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.6.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.6.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.6.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.6.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.7.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.7.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.7.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.7.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.7.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.7.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.7.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.7.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.8.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.8.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.8.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.8.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.8.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.8.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.8.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.8.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.9.attn.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.9.attn.qkv.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
3072
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.9.mlp.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.9.mlp.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.9.norm1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.9.norm1.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.9.norm2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.blocks.9.norm2.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.merger.linear_fc1.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
4096
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.merger.linear_fc2.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.merger.norm.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.merger.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "model.visual.patch_embed.proj.bias",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
1024
|
|
]
|
|
},
|
|
{
|
|
"name": "mtp.layers.0.input_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "mtp.layers.0.post_attention_layernorm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "mtp.layers.0.self_attn.k_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "mtp.layers.0.self_attn.q_norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
256
|
|
]
|
|
},
|
|
{
|
|
"name": "mtp.norm.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "mtp.pre_fc_norm_embedding.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
},
|
|
{
|
|
"name": "mtp.pre_fc_norm_hidden.weight",
|
|
"reason": "one vector, no vector cloud",
|
|
"shape": [
|
|
2048
|
|
]
|
|
}
|
|
],
|
|
"total_tensors": 632,
|
|
"parameters": 2274069824,
|
|
"changed_tensors": [
|
|
"model.language_model.layers.0.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.0.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.0.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.1.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.1.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.1.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.10.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.10.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.10.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.12.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.12.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.12.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.13.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.13.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.13.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.14.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.14.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.14.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.16.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.16.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.16.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.17.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.17.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.17.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.18.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.18.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.18.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.2.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.2.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.2.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.20.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.20.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.20.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.21.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.21.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.21.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.22.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.22.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.22.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.4.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.4.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.4.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.5.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.5.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.5.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.6.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.6.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.6.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.8.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.8.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.8.linear_attn.out_proj.weight",
|
|
"model.language_model.layers.9.linear_attn.in_proj_a.weight",
|
|
"model.language_model.layers.9.linear_attn.in_proj_b.weight",
|
|
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
|
|
"model.language_model.layers.9.linear_attn.out_proj.weight"
|
|
],
|
|
"adapter_meta": {
|
|
"record": "qwen3.5-2b-grpo",
|
|
"arm": "lora",
|
|
"receipt_arm": "ctrl",
|
|
"seed": 0,
|
|
"step": 150,
|
|
"base_model": "Qwen/Qwen3.5-2B",
|
|
"base_revision": "15852e8c16360a2fea060d615a32b45270f8a8fc",
|
|
"recipe": "GRPO, correctness-gated length penalty alpha 0.2, 150 steps from the shared warm-up (paper Section 4)",
|
|
"lora_rank": 16,
|
|
"lora_alpha": 32,
|
|
"lora_targets": [
|
|
"in_proj_qkv",
|
|
"in_proj_a",
|
|
"in_proj_b",
|
|
"out_proj"
|
|
],
|
|
"gate": null,
|
|
"n_tensors": 144,
|
|
"n_params": 4727808,
|
|
"source_sha256": "de2794c085f5096fea53374ba1cea31075071bb6de3f227bb3350b3035970447"
|
|
},
|
|
"max_grid": [
|
|
0.5,
|
|
0.75,
|
|
0.9,
|
|
0.95,
|
|
0.99,
|
|
1.0,
|
|
1.05,
|
|
1.1,
|
|
1.25
|
|
],
|
|
"rms_grid": [
|
|
0.5,
|
|
0.525,
|
|
0.55,
|
|
0.575,
|
|
0.6,
|
|
0.625,
|
|
0.65,
|
|
0.675,
|
|
0.7,
|
|
0.725,
|
|
0.75,
|
|
0.775,
|
|
0.8,
|
|
0.825,
|
|
0.8500000000000001,
|
|
0.875,
|
|
0.9,
|
|
0.925,
|
|
0.95,
|
|
0.9750000000000001,
|
|
1.0,
|
|
1.025,
|
|
1.05,
|
|
1.0750000000000002,
|
|
1.1,
|
|
1.125,
|
|
1.15,
|
|
1.175,
|
|
1.2000000000000002,
|
|
1.225,
|
|
1.25,
|
|
1.275,
|
|
1.3,
|
|
1.3250000000000002,
|
|
1.35,
|
|
1.375,
|
|
1.4,
|
|
1.425,
|
|
1.4500000000000002,
|
|
1.475,
|
|
1.5
|
|
],
|
|
"null_eval": 512,
|
|
"point_cap": 512,
|
|
"feature_cap": 8192
|
|
} |