huihui-ai/deepthought-8b-abliterated

This is an uncensored version of ruliad/deepthought-8b-llama-v0.01-alpha created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Downloads last month
104
Safetensors
Model size
8.03B params
Tensor type
BF16
Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for huihui-ai/deepthought-8b-abliterated

Finetuned
(1)
this model
Merges
3 models
Quantizations
2 models