14 KiB
14 KiB
| 1 | mode | role | scale | shape | ndim | dtype | verified_pairs | minimum_direct_error | median_direct_error | maximum_cosine | minimum_scaled_error | pairs_under_5pct_direct_error | pairs_under_20pct_direct_error |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | tensor | model.language_model.layers.*.input_layernorm.weight | whole | (2048,) | 1 | BF16 | 74 | 0.13912108191960726 | 0.3618018896863233 | 0.9970857492150444 | 0.07628898159153481 | 0 | 10 |
| 3 | tensor | model.language_model.layers.*.linear_attn.A_log | whole | (16,) | 1 | F32 | 74 | 0.27903195486574556 | 0.5226947550912504 | 0.9627591388053268 | 0.2703605752450334 | 0 | 0 |
| 4 | tensor | model.language_model.layers.*.linear_attn.conv1d.weight | whole | (6144, 1, 4) | 3 | BF16 | 74 | 1.098915802713169 | 1.6166702679005591 | 0.02807999077877503 | 0.9995776806560605 | 0 | 0 |
| 5 | tensor | model.language_model.layers.*.linear_attn.dt_bias | whole | (16,) | 1 | BF16 | 74 | 0.5885114617058197 | 1.0044528421940808 | 0.8092128713956994 | 0.5875155561919422 | 0 | 0 |
| 6 | tensor | model.language_model.layers.*.linear_attn.in_proj_a.weight | whole | (16, 2048) | 2 | BF16 | 74 | 1.1349952189534511 | 1.2168184642463737 | 0.29759171873785567 | 0.9546932328966456 | 0 | 0 |
| 7 | tensor | model.language_model.layers.*.linear_attn.in_proj_b.weight | whole | (16, 2048) | 2 | BF16 | 74 | 1.0858901378940746 | 1.2225962811652291 | 0.3211769991079106 | 0.9470191842006356 | 0 | 0 |
| 8 | tensor | model.language_model.layers.*.linear_attn.in_proj_qkv.weight | whole | (6144, 2048) | 2 | BF16 | 74 | 1.2723349817001153 | 1.4635296420527903 | 0.0010135353358410714 | 0.9999989240512659 | 0 | 0 |
| 9 | tensor | model.language_model.layers.*.linear_attn.in_proj_z.weight | whole | (2048, 2048) | 2 | BF16 | 74 | 1.2910830542163632 | 1.4537858403559945 | 0.013531813033101601 | 0.9999084408264775 | 0 | 0 |
| 10 | tensor | model.language_model.layers.*.linear_attn.norm.weight | whole | (128,) | 1 | F32 | 74 | 0.0996284846101826 | 0.14453921179048346 | 0.9962083215944217 | 0.08699988497707883 | 0 | 74 |
| 11 | tensor | model.language_model.layers.*.linear_attn.out_proj.weight | whole | (2048, 2048) | 2 | BF16 | 74 | 1.3358019613674468 | 1.4033556107959 | 0.0016585943863867917 | 0.9999986245313849 | 0 | 0 |
| 12 | tensor | model.language_model.layers.*.mlp.down_proj.weight | whole | (2048, 6144) | 2 | BF16 | 74 | 1.289324616789422 | 1.3421967541150206 | 0.0006628169766189873 | 0.9999997803368037 | 0 | 0 |
| 13 | tensor | model.language_model.layers.*.mlp.gate_proj.weight | whole | (6144, 2048) | 2 | BF16 | 74 | 1.156201781439196 | 1.6720196078871572 | 0.009922418979925494 | 0.9999507715890752 | 0 | 0 |
| 14 | tensor | model.language_model.layers.*.mlp.up_proj.weight | whole | (6144, 2048) | 2 | BF16 | 73 | 1.2210613405090442 | 1.3293668966359742 | 0.0008737601640509451 | 0.9999996182715151 | 0 | 0 |
| 15 | tensor | model.language_model.layers.*.post_attention_layernorm.weight | whole | (2048,) | 1 | BF16 | 73 | 0.08389205016305105 | 0.33550848021824864 | 0.9982024397574774 | 0.05993237240606879 | 0 | 15 |
| 16 | tensor | model.language_model.layers.*.self_attn.k_norm.weight | whole | (256,) | 1 | BF16 | 15 | 0.4220354869409763 | 0.5730767172719882 | 0.9109326955126066 | 0.41255499542017027 | 0 | 0 |
| 17 | tensor | model.language_model.layers.*.self_attn.k_proj.weight | whole | (512, 2048) | 2 | BF16 | 15 | 1.3216500796717134 | 1.390928677608635 | 0.0029925337418067574 | 0.9999915875965523 | 0 | 0 |
| 18 | tensor | model.language_model.layers.*.self_attn.o_proj.weight | whole | (2048, 2048) | 2 | BF16 | 15 | 1.1817960007584458 | 1.3582179033168547 | 0.000661789759001042 | 0.9999997810171335 | 0 | 0 |
| 19 | tensor | model.language_model.layers.*.self_attn.q_norm.weight | whole | (256,) | 1 | BF16 | 15 | 0.39404064792499355 | 0.543936200795208 | 0.9230509542708148 | 0.38467770382456284 | 0 | 0 |
| 20 | tensor | model.language_model.layers.*.self_attn.q_proj.weight | whole | (4096, 2048) | 2 | BF16 | 15 | 1.2822624900273465 | 1.452325507475276 | 0.031103970688887258 | 0.9995161544504345 | 0 | 0 |
| 21 | tensor | model.language_model.layers.*.self_attn.v_proj.weight | whole | (512, 2048) | 2 | BF16 | 15 | 1.1381535663510483 | 1.279855729883491 | 0.004274933965921905 | 0.9999908624280459 | 0 | 0 |
| 22 | tensor | model.visual.layers.*.attn.proj.bias | whole | (1024,) | 1 | BF16 | 73 | 0.6680979684279816 | 1.0326843804327857 | 0.7647843141032159 | 0.644286390436484 | 0 | 0 |
| 23 | tensor | model.visual.layers.*.attn.proj.weight | whole | (1024, 1024) | 2 | BF16 | 73 | 1.2263109992320418 | 1.494030495278536 | 0.0022893779585961825 | 0.9999973793708475 | 0 | 0 |
| 24 | tensor | model.visual.layers.*.attn.qkv.bias | whole | (3072,) | 1 | BF16 | 73 | 1.1508235097225006 | 1.2895358606896887 | 0.07880074887800716 | 0.9968903861389502 | 0 | 0 |
| 25 | tensor | model.visual.layers.*.attn.qkv.weight | whole | (3072, 1024) | 2 | BF16 | 73 | 1.1919409580791358 | 1.3528352612266674 | 0.0012420225434440872 | 0.9999972512712101 | 0 | 0 |
| 26 | tensor | model.visual.layers.*.mlp.linear_fc1.bias | whole | (4096,) | 1 | BF16 | 73 | 0.3423255120414103 | 0.4506608457966791 | 0.942832226875403 | 0.33326774816229754 | 0 | 0 |
| 27 | tensor | model.visual.layers.*.mlp.linear_fc1.weight | whole | (4096, 1024) | 2 | BF16 | 73 | 1.2318420108577686 | 1.5641645589759754 | 0.0024998220990413433 | 0.999996875439855 | 0 | 0 |
| 28 | tensor | model.visual.layers.*.mlp.linear_fc2.bias | whole | (1024,) | 1 | BF16 | 73 | 0.6856625742029931 | 1.008978107126644 | 0.7922147396405718 | 0.6102424160087705 | 0 | 0 |
| 29 | tensor | model.visual.layers.*.mlp.linear_fc2.weight | whole | (1024, 4096) | 2 | BF16 | 73 | 1.2583800420385622 | 1.3660455322298402 | 0.0019111009657841638 | 0.9999962185103182 | 0 | 0 |
| 30 | tensor | model.visual.layers.*.norm1.bias | whole | (1024,) | 1 | BF16 | 73 | 0.25115943947656993 | 0.690883854809181 | 0.9691259474486883 | 0.24656621419343377 | 0 | 0 |
| 31 | tensor | model.visual.layers.*.norm1.weight | whole | (1024,) | 1 | BF16 | 73 | 0.04823731166106643 | 0.14504506306481724 | 0.9992280358422151 | 0.03928526933736397 | 1 | 58 |
| 32 | tensor | model.visual.layers.*.norm2.bias | whole | (1024,) | 1 | BF16 | 73 | 0.46245716111033913 | 0.9605989201912757 | 0.9255664605094013 | 0.3785851650290843 | 0 | 0 |
| 33 | tensor | model.visual.layers.*.norm2.weight | whole | (1024,) | 1 | BF16 | 73 | 0.08109603491499054 | 0.25584969812385294 | 0.998097572177166 | 0.06165416785625297 | 0 | 29 |
| 34 | block | model.language_model.embed_tokens.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.0971431655919834 | 1.194996165634402 | 0.38371384285373505 | 0.9234520490000654 | 0 | 0 |
| 35 | block | model.language_model.embed_tokens.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 0.7867192520997638 | 1.2251136172712975 | 0.6417520096030089 | 0.7669122232501576 | 0 | 0 |
| 36 | block | model.language_model.layers.*.linear_attn.conv1d.weight | 3d-axis0-slice | (1, 1, 4) | 3 | BF16 | 274 | 0.030015470714371044 | 0.14107363259145156 | 0.9999764693972976 | 0.006860076655215805 | 12 | 264 |
| 37 | block | model.language_model.layers.*.linear_attn.conv1d.weight | 3d-volume | (4, 1, 4) | 3 | BF16 | 274 | 0.20434866638862353 | 0.6511326882375805 | 0.9939530725821022 | 0.10980568976423064 | 0 | 0 |
| 38 | block | model.language_model.layers.*.linear_attn.in_proj_qkv.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.0859194381904604 | 1.1672768187290392 | 0.022506491289619568 | 0.9997466968436706 | 0 | 0 |
| 39 | block | model.language_model.layers.*.linear_attn.in_proj_qkv.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.090431605185219 | 1.8770856997459073 | 0.049580432466001016 | 0.9987701340731432 | 0 | 0 |
| 40 | block | model.language_model.layers.*.linear_attn.in_proj_z.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.1104948912862496 | 1.8773864848571475 | 0.023475850982642838 | 0.9997244042338073 | 0 | 0 |
| 41 | block | model.language_model.layers.*.linear_attn.in_proj_z.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.0991661244633573 | 1.8514486050124992 | 0.043485528874022565 | 0.9988418359874629 | 0 | 0 |
| 42 | block | model.language_model.layers.*.linear_attn.out_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.1951881759983194 | 1.6594942134980784 | 0.020468545616965008 | 0.9997904973744881 | 0 | 0 |
| 43 | block | model.language_model.layers.*.linear_attn.out_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.2072392784651196 | 1.5582677535715024 | 0.04454056700388926 | 0.9990075764932776 | 0 | 0 |
| 44 | block | model.language_model.layers.*.mlp.down_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.2582617322579883 | 1.3090099938602142 | 0.023571230885306684 | 0.9997221599397262 | 0 | 0 |
| 45 | block | model.language_model.layers.*.mlp.down_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.245852433773206 | 1.2940629124466638 | 0.055858158466128856 | 0.9984387142598052 | 0 | 0 |
| 46 | block | model.language_model.layers.*.mlp.gate_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.1461492372241606 | 1.1966255074601801 | 0.021946362169951123 | 0.9997591495892925 | 0 | 0 |
| 47 | block | model.language_model.layers.*.mlp.gate_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.1257085731592742 | 1.1760753399312671 | 0.05964405801998305 | 0.9982197084524573 | 0 | 0 |
| 48 | block | model.language_model.layers.*.mlp.up_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.1938896537465822 | 1.5743736046705104 | 0.024746719402858743 | 0.9996937530457997 | 0 | 0 |
| 49 | block | model.language_model.layers.*.mlp.up_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.1982869032487864 | 1.2816774375554039 | 0.05539464318026474 | 0.9984645379315839 | 0 | 0 |
| 50 | block | model.language_model.layers.*.self_attn.k_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.1432871543196577 | 1.195761062340063 | 0.029770641663691994 | 0.9995567562149396 | 0 | 0 |
| 51 | block | model.language_model.layers.*.self_attn.k_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.089843800559886 | 2.0769322472882257 | 0.047714166736051784 | 0.9988610305206046 | 0 | 0 |
| 52 | block | model.language_model.layers.*.self_attn.o_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.0759865369389314 | 1.9552667922072795 | 0.3717312413966341 | 0.9283403924044872 | 0 | 0 |
| 53 | block | model.language_model.layers.*.self_attn.o_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.090185636068711 | 1.5183831236960614 | 0.4006143023357977 | 0.9162467903157981 | 0 | 0 |
| 54 | block | model.language_model.layers.*.self_attn.q_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 0.681062120292795 | 1.6110791655011307 | 0.766589729840059 | 0.6421372019309778 | 0 | 0 |
| 55 | block | model.language_model.layers.*.self_attn.q_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.0731967952952182 | 1.132586437118316 | 0.14446200523831285 | 0.9895103481230126 | 0 | 0 |
| 56 | block | model.language_model.layers.*.self_attn.v_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.0703772237415003 | 2.3064512918392657 | 0.025583225359911956 | 0.9996726957260481 | 0 | 0 |
| 57 | block | model.language_model.layers.*.self_attn.v_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.0615939539051586 | 2.242144803814884 | 0.05979641283088267 | 0.9982105935185014 | 0 | 0 |
| 58 | block | model.visual.layers.*.attn.proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.0964898212068823 | 1.24917667593092 | 0.030377666073744123 | 0.9995384922072347 | 0 | 0 |
| 59 | block | model.visual.layers.*.attn.proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.0929319776557436 | 1.2036709366228333 | 0.04190888825600163 | 0.9991214366057541 | 0 | 0 |
| 60 | block | model.visual.layers.*.attn.qkv.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.0525674864684573 | 1.1472629166116397 | 0.3497290628302071 | 0.9368508860068955 | 0 | 0 |
| 61 | block | model.visual.layers.*.attn.qkv.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.0276302940676463 | 2.153982940996772 | 0.05039306408132999 | 0.998729462413368 | 0 | 0 |
| 62 | block | model.visual.layers.*.mlp.linear_fc1.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.1784037671219423 | 1.2610017357650904 | 0.05446205204482453 | 0.998515841079683 | 0 | 0 |
| 63 | block | model.visual.layers.*.mlp.linear_fc1.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.1930932764469049 | 1.5635216450228222 | 0.05742888587637769 | 0.9983495996227965 | 0 | 0 |
| 64 | block | model.visual.layers.*.mlp.linear_fc2.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.1976986200156163 | 1.5864288735783176 | 0.028190387759862247 | 0.9996025720444844 | 0 | 0 |
| 65 | block | model.visual.layers.*.mlp.linear_fc2.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.0973576240937362 | 1.2821071329134202 | 0.052752794427996734 | 0.9986076019538593 | 0 | 0 |
| 66 | block | model.visual.merger.linear_fc1.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 0.5690482377069183 | 1.3881733201164015 | 0.8394467875146913 | 0.5434418928747256 | 0 | 0 |
| 67 | block | model.visual.merger.linear_fc1.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 0.5704160177838491 | 1.383715288781834 | 0.8382741355593843 | 0.5452490015141402 | 0 | 0 |
| 68 | block | model.visual.merger.linear_fc2.weight | 2d-128 | (128, 128) | 2 | BF16 | 274 | 1.361602880922912 | 1.4076521005397016 | 0.022716837303296537 | 0.9997419393538193 | 0 | 0 |
| 69 | block | model.visual.merger.linear_fc2.weight | 2d-64 | (64, 64) | 2 | BF16 | 274 | 1.3172335252228955 | 1.3885238301845173 | 0.054916767376716406 | 0.9984909356929044 | 0 | 0 |
| 70 | block | model.visual.pos_embed.weight | 2d-128 | (128, 128) | 2 | BF16 | 273 | 0.1894907479098447 | 0.8368814065208369 | 0.9820068756666321 | 0.18884516446935973 | 0 | 1 |
| 71 | block | model.visual.pos_embed.weight | 2d-64 | (64, 64) | 2 | BF16 | 273 | 0.09494430310075026 | 0.5761056230742875 | 0.9960502566825586 | 0.08879125048454295 | 0 | 7 |
| 72 | block | mtp.fc.weight | 2d-128 | (128, 128) | 2 | BF16 | 273 | 0.39795158187541674 | 1.3009198418830403 | 0.9219877695675962 | 0.3872189984592301 | 0 | 0 |
| 73 | block | mtp.fc.weight | 2d-64 | (64, 64) | 2 | BF16 | 273 | 0.2839409442692466 | 1.2187888824373985 | 0.9598132531637373 | 0.2806394823456665 | 0 | 0 |
| 74 | block | mtp.layers.*.mlp.down_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 273 | 1.310074009535121 | 1.4215054026060296 | 0.027554671685217264 | 0.9996202979473355 | 0 | 0 |
| 75 | block | mtp.layers.*.mlp.down_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 273 | 1.249807578942172 | 1.470099001092512 | 0.044434762604782845 | 0.9990122881487777 | 0 | 0 |
| 76 | block | mtp.layers.*.mlp.gate_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 273 | 1.3014802290213505 | 1.361681996563559 | 0.03373996398972023 | 0.9994306453326176 | 0 | 0 |
| 77 | block | mtp.layers.*.mlp.gate_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 273 | 1.2564681140844673 | 1.4625957375534147 | 0.0542156946795996 | 0.9985292476689946 | 0 | 0 |
| 78 | block | mtp.layers.*.mlp.up_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 273 | 1.3314815136128675 | 1.4083678884650157 | 0.029758300533378034 | 0.9995571237049762 | 0 | 0 |
| 79 | block | mtp.layers.*.mlp.up_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 273 | 1.2939027995891361 | 1.3558402418466908 | 0.06246493086010471 | 0.9980471594131423 | 0 | 0 |
| 80 | block | mtp.layers.*.self_attn.k_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 273 | 1.2211071346906675 | 1.6568460478464606 | 0.02773941669941069 | 0.9996151883405816 | 0 | 0 |
| 81 | block | mtp.layers.*.self_attn.k_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 273 | 1.100749972037444 | 2.321267616896819 | 0.06391398313313451 | 0.9979554112083653 | 0 | 0 |
| 82 | block | mtp.layers.*.self_attn.o_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 273 | 0.8821045427467973 | 1.206170586612079 | 0.5767316801239848 | 0.8169336381502268 | 0 | 0 |
| 83 | block | mtp.layers.*.self_attn.o_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 273 | 0.9425522849964715 | 1.2696601113099386 | 0.5275664580383422 | 0.849513762309286 | 0 | 0 |
| 84 | block | mtp.layers.*.self_attn.q_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 273 | 1.0237777819118037 | 2.8371550549613556 | 0.4898664655238783 | 0.8717974798972196 | 0 | 0 |
| 85 | block | mtp.layers.*.self_attn.q_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 273 | 1.008280496287895 | 2.524395456205866 | 0.5430402363306829 | 0.8397066760041365 | 0 | 0 |
| 86 | block | mtp.layers.*.self_attn.v_proj.weight | 2d-128 | (128, 128) | 2 | BF16 | 273 | 1.3534677309181036 | 1.402389437951931 | 0.024838060691519125 | 0.9996914877806474 | 0 | 0 |
| 87 | block | mtp.layers.*.self_attn.v_proj.weight | 2d-64 | (64, 64) | 2 | BF16 | 273 | 1.269834274085324 | 1.3381727215333372 | 0.05798552649229015 | 0.9983174238274177 | 0 | 0 |