weight-steering

wassname/weight-steering

Fork 0

mirror of https://github.com/wassname/weight-steering.git synced 2026-08-06 13:40:47 +08:00

Commit Graph

Author	SHA1	Message	Date
wassname	7e1b171875	paper data recipe + LoRA hyperparams + n_pairs hardening - data: 5 pos + 5 neg personas, 20 train + 12 eval topic split (paper §3 / Appendix C), n_samples solved from n_pairs. judge filter stub (off by default; paper uses GPT-4.1-mini). - eval/sycophancy: read true held-out eval_topics() instead of SYCOPHANCY_TOPICS[-16:]. - replicate: fix epochs threading; n_pairs reuse fails fast on mismatch; smoke knobs (n_topics, n_personas) plumbed. - train: paper hyperparams (rank 32 / alpha 16 / lr 1e-5 / warmup 5 / wd 0.01); explicit alpha (no 2*r fallback); held-out 10% val + eval_loss logging. - run_demo: train_topics() for in_dist demo claims. - README: scope block reflects paper-matching recipe.	2026-04-26 10:19:59 +08:00
wassname	f4083d74ac	Enhance fork plan and add guided-CoT evaluation - Updated the fork plan with detailed phases and objectives for small model adaptation and evaluation. - Added a new guided-CoT evaluation script to assess model coherence under steering. - Introduced demo functionality to showcase adapter coherence and guided-CoT performance. - Modified training configuration to include layer fraction targeting for LoRA. - Improved evaluation outputs for clarity and added validation checks.	2026-04-26 09:16:54 +08:00
wassname	f0bce8be90	tidy	2026-04-25 19:27:53 +08:00

Author

SHA1

Message

Date

wassname

7e1b171875

paper data recipe + LoRA hyperparams + n_pairs hardening

- data: 5 pos + 5 neg personas, 20 train + 12 eval topic split
  (paper §3 / Appendix C), n_samples solved from n_pairs.
  judge filter stub (off by default; paper uses GPT-4.1-mini).
- eval/sycophancy: read true held-out eval_topics() instead of
  SYCOPHANCY_TOPICS[-16:].
- replicate: fix epochs threading; n_pairs reuse fails fast on mismatch;
  smoke knobs (n_topics, n_personas) plumbed.
- train: paper hyperparams (rank 32 / alpha 16 / lr 1e-5 / warmup 5 /
  wd 0.01); explicit alpha (no 2*r fallback); held-out 10% val + eval_loss
  logging.
- run_demo: train_topics() for in_dist demo claims.
- README: scope block reflects paper-matching recipe.

2026-04-26 10:19:59 +08:00

wassname

f4083d74ac

Enhance fork plan and add guided-CoT evaluation

- Updated the fork plan with detailed phases and objectives for small model adaptation and evaluation.
- Added a new guided-CoT evaluation script to assess model coherence under steering.
- Introduced demo functionality to showcase adapter coherence and guided-CoT performance.
- Modified training configuration to include layer fraction targeting for LoRA.
- Improved evaluation outputs for clarity and added validation checks.

2026-04-26 09:16:54 +08:00

wassname

f0bce8be90

tidy

2026-04-25 19:27:53 +08:00