Decensored using a custom training script guided by activations, similar to ablation/"abliteration" scripts but not exactly the same approach.
The training script is released under the MIT license: https://github.com/nkpz/DeLMAT
- Downloads last month
- 18
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.
Model tree for nkpz/Llama-3.1-Tulu-3.1-8B-Uncensored-DeLMAT
Base model
meta-llama/Llama-3.1-8B
Finetuned
allenai/Llama-3.1-Tulu-3-8B-SFT
Finetuned
allenai/Llama-3.1-Tulu-3-8B-DPO
Finetuned
allenai/Llama-3.1-Tulu-3.1-8B