josephmayo
Fara-7B-Abliterated-v2
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Get help setting up a custom Dedicated Endpoints.
Talk with our engineer to get a quote for reserved GPU instances with discounts.
README
License: otherMethod
Using harmful + harmless probe sets, residual-stream activations were extracted across layers 0–27 to identify the strongest refusal direction.
Best layer:
- 13
Orthogonalization was applied in fp32 to:
embed_tokens- every
self_attn.o_proj - every
mlp.down_proj
Total modified tensors:
- 57
Formula:
python
W ← W - r rᵀ W
Results
Held-out harmful evaluation set:
- Original Fara-7B: 5/160 compliance (~3.1%)
- Abliterated v2: 158/160 compliance (~98.75%)
Held-out refusal probe:
- Before: 155/160 refusals
- After: 2/160 refusals
Notes
- fp32 surgery used to avoid precision issues from v1
- edits applied only to the language tower
- held-out evaluation set was separate from the layer-selection probe set
Research artifact only. Use responsibly and follow upstream Fara/Qwen license terms.
Model provider
josephmayo
Model tree
Base
microsoft/Fara-7B
Fine-tuned
this model
Modalities
Input
Text, Image
Output
Text
Pricing
Dedicated Endpoints
View detailsSupported Functionality
Model APIs
Dedicated Endpoints
Container
More information