huihui-ai/CodeLlama-34b-Instruct-hf-abliterated

This is an uncensored version of meta-llama/CodeLlama-34b-Instruct-hf 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
9
Safetensors
Model size
33.7B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for huihui-ai/CodeLlama-34b-Instruct-hf-abliterated

Finetuned
(7)
this model
Quantizations
2 models