wassname/weight-steering
1
0
Fork 0
mirror of https://github.com/wassname/weight-steering.git synced 2026-07-19 11:29:55 +08:00
Code Issues Packages Projects Releases Wiki Activity
9 Commits 2 Branches 0 Tags
ddfa018ebd87aabd81ae7df45b1a5ea4be4fadd1
Commit Graph
9 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
wassname ddfa018ebd wip 2026-04-26 10:00:03 +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
wassnameandClaude Opus 4.7 3ff283d535 README: fork notice + pipeline overview 
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-04-25 20:16:57 +08:00
wassnameandClaude Opus 4.7 363e2db14d phase 0-2: HF+PEFT pipeline, smoke, subspace alignment 
Rip Axolotl/vLLM, switch to HF+PEFT functional pipeline.
Add LoRA/DoRA/PiSSA/DeLoRA train, delta-W diff, weight_steer hook,
sycophancy logratio eval, and SVD top-k + weak-readout alignment.
Smoke runs end-to-end on tiny-random qwen3 with BEARTYPE=1.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-04-25 20:14:07 +08:00
wassname f0bce8be90 tidy 2026-04-25 19:27:53 +08:00
ConstanzaandGitHub 977c054586 Update README.md 2025-11-11 09:18:45 +01:00
cfierro94 3d61ae0452 update code and add configs 2025-11-05 10:13:04 +01:00
cfierro94 144fa5532d first commit 2025-10-17 11:15:28 +02:00
cfierro94 90065f035f first commit 2025-10-17 11:14:24 +02:00