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.

If "<think>" does not appear or refuses to respond, you can first provide an example to guide, and then ask your question.
For instance:

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

You can use huihui_ai/deepseek-r1-abliterated directly