Decensored using a custom training script guided by activations, similar to ablation/"abliteration" scripts but not exactly the same approach.
Original model at time of writing is #63 ranked on Open LLM Leaderboard
The training script is released under the MIT license: https://github.com/nkpz/DeLMAT - This model was built using an upcoming development version
- Downloads last month
- 6
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.