huihui-ai/Llama-3.2-90B-Vision-Instruct-abliterated

This is an uncensored version of meta-llama/Llama-3.2-90B-Vision-Instruct 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.

It was only the text part that was processed, not the image part.

Downloads last month
140
Safetensors
Model size
88.6B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for huihui-ai/Llama-3.2-90B-Vision-Instruct-abliterated

Finetuned
(8)
this model

Collection including huihui-ai/Llama-3.2-90B-Vision-Instruct-abliterated