 Philipp Emanuel Weidmann
|
a9655c8d31
|
Perform calculations involving residual vectors in float32
Credit to Jim Lai for pointing out potential numerical problems in https://huggingface.co/blog/grimjim/projected-abliteration
|
2025-10-31 13:47:24 +05:30 |
|
|
Philipp Emanuel Weidmann
|
1496e0a04c
|
Dynamically choose between global and per-layer refusal directions
|
2025-10-31 13:04:45 +05:30 |
|
|
Philipp Emanuel Weidmann
|
c638d3d012
|
Adjust score parameters
|
2025-10-25 13:15:31 +05:30 |
|
|
Philipp Emanuel Weidmann
|
47e855d5d8
|
Guard against missing model card data
|
2025-10-25 13:12:18 +05:30 |
|
|
Philipp Emanuel Weidmann
|
e2419de016
|
Add "abliterated" to model tags
|
2025-10-25 09:59:44 +05:30 |
|
|
Philipp Emanuel Weidmann
|
ad8b04d371
|
Bump version to 1.0.0
|
2025-10-25 09:52:43 +05:30 |
|
|
Philipp Emanuel Weidmann
|
37c5ea06d1
|
Print elapsed and remaining time
|
2025-10-25 09:47:54 +05:30 |
|
|
Philipp Emanuel Weidmann
|
cf57a0cfbe
|
Add functionality to evaluate any model relative to the main model
|
2025-10-24 13:38:03 +05:30 |
|
|
Philipp Emanuel Weidmann
|
e6aba71186
|
Improve refusal detection
|
2025-10-24 11:27:28 +05:30 |
|
|
Philipp Emanuel Weidmann
|
f8f3f9a012
|
Fix chat responses being cut off
|
2025-10-22 12:30:28 +05:30 |
|
|
Philipp Emanuel Weidmann
|
6359aa44bb
|
Separate abliteration parameters for different layer components
|
2025-10-22 12:05:28 +05:30 |
|
|
Philipp Emanuel Weidmann
|
ed65d6902b
|
Support gpt-oss MoE
|
2025-10-15 17:51:39 +05:30 |
|
|
Philipp Emanuel Weidmann
|
7ed0cb1ffb
|
Support Phi-3.5-MoE
|
2025-10-14 11:23:53 +05:30 |
|
|
Philipp Emanuel Weidmann
|
8b827ee386
|
Support multimodal models
|
2025-10-14 10:32:34 +05:30 |
|
|
Philipp Emanuel Weidmann
|
dd7abd3296
|
Add hf_transfer to dependencies
Required for repositories that don't use Xet
|
2025-10-14 07:56:43 +05:30 |
|
|
Philipp Emanuel Weidmann
|
3d5e645c13
|
Handle Ctrl+C gracefully
|
2025-10-12 12:53:40 +05:30 |
|
|
Philipp Emanuel Weidmann
|
74b55977f0
|
Pretty-print configuration errors
|
2025-10-12 10:39:59 +05:30 |
|
|
Philipp Emanuel Weidmann
|
b4a0c0d3f2
|
Add program version to generated README intro
|
2025-10-11 17:31:11 +05:30 |
|
|
Philipp Emanuel Weidmann
|
7caf9fcdc5
|
Separate training and evaluation prompts
|
2025-10-09 12:51:31 +05:30 |
|
|
Philipp Emanuel Weidmann
|
2ff8dcba6b
|
Add model card when uploading to Hugging Face
|
2025-09-30 08:43:21 +05:30 |
|
|
Philipp Emanuel Weidmann
|
5b01ad4344
|
Add save and upload functionality
|
2025-09-27 11:15:41 +05:30 |
|
|
Philipp Emanuel Weidmann
|
7573a2eebd
|
Support passing model name without "--model" argument prefix
|
2025-09-25 15:02:22 +05:30 |
|
|
Philipp Emanuel Weidmann
|
fd0fa52552
|
Add chat functionality
|
2025-09-24 18:09:23 +05:30 |
|
|
Philipp Emanuel Weidmann
|
f00d35dc46
|
Improve early abort score calculation
|
2025-09-23 19:02:00 +05:30 |
|
|
Philipp Emanuel Weidmann
|
3f242369e0
|
Add educated guesses for parameter values to get the optimizer started
|
2025-09-23 16:00:20 +05:30 |
|
|
Philipp Emanuel Weidmann
|
c447805fc2
|
Improve default dtype configuration
|
2025-09-23 13:31:41 +05:30 |
|
|
Philipp Emanuel Weidmann
|
b6c715ab6f
|
Abort trial early if KL divergence is too high
|
2025-09-23 13:20:31 +05:30 |
|
|
Philipp Emanuel Weidmann
|
9485edc221
|
Support Qwen3 MoE
|
2025-09-22 15:22:48 +05:30 |
|
|
Philipp Emanuel Weidmann
|
1b37160490
|
Fix model loading issues
|
2025-09-21 16:04:41 +05:30 |
|
|
Philipp Emanuel Weidmann
|
af19fbd254
|
Initial commit
|
2025-09-21 11:10:30 +05:30 |
|