README.md

metadata

base_model:
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
library_name: transformers
tags:
  - abliterated
  - uncensored
datasets:
  - fka/awesome-chatgpt-prompts

huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2

This is an uncensored version of deepseek-ai/DeepSeek-R1-Distill-Qwen-7B 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.

Important Note This version is an improvement over the previous one huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated.

Use with ollama

You can use huihui_ai/deepseek-r1-abliterated directly

ollama run huihui_ai/deepseek-r1-abliterated:7b