Fine-tuned version of Qwen/Qwen3-4B-Thinking-2507 on the ICEPVP8977/Uncensored_Small_Reasoning dataset.
This LoRA will fully uncensor the Qwen3-4B-Thinking model, use alpaca instruction template.
Fine-tuned version of Qwen/Qwen3-4B-Thinking-2507 on the ICEPVP8977/Uncensored_Small_Reasoning dataset.
This LoRA will fully uncensor the Qwen3-4B-Thinking model, use alpaca instruction template.
有文件？提交种子。
提交种子Qwen/Qwen3-4B-Thinking-2507