huihui-ai/UwU-7B-Instruct-abliterated

This is an uncensored version of qingy2024/UwU-7B-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.

Use with ollama

You can use huihui_ai/uwu-abliterated directly

ollama run huihui_ai/uwu-abliterated
Downloads last month
8
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for huihui-ai/UwU-7B-Instruct-abliterated

Base model

Qwen/Qwen2.5-7B
Finetuned
(1)
this model
Quantizations
2 models