Zayden-Jung/exp-model-parameter-similarity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Archive research charts and compare GSM8K LoRA head concentration

Browse Source
This commit is contained in:
Codex Bot
2026-11-11 00:06:15 +08:00
parent d6d985487c
commit 52e6d13fe5
142 changed files with 18505 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6
View File
@@ -1,5 +1,7 @@
# Model parameter similarity experiments
**[研究图册与固定在线副本](docs/FIGURE_GALLERY.md)**：连续分布、联合消融及原始PDF/SVG。
Research on repeated learned functions in **Qwen3.5-2B**: a completed static weight baseline
and a training-free CPU functional pilot. The CPU study found similar existing RMSNorm
functions at layer indices 12/13, with a uniform analytic error bound and heldout substitution checks.
@@ -51,3 +53,7 @@ removal controls. See [definitions and reproduction](dominance/README.md),
[fixed protocol](dominance/PROTOCOL.md), and [measured report](results/head-dominance/REPORT.md).
These are descriptive intervention effects, not additive contribution probabilities
or validated final-LM pruning gains.
## Existing GSM8K task-finetuning comparison
[Paired study and reproduction](finetune_compare/README.md) · [Fixed protocol](finetune_compare/PROTOCOL.md) · [Results](results/finetune-comparison/REPORT.md). This compares an existing pure-LoRA GRPO checkpoint to exactly the same original release; no training is performed here.