Fine-tuned version of HuggingFaceTB/SmolLM3-3B on the ICEPVP8977/Uncensored_Small_Reasoning dataset.
This LoRA will fully uncensor the SmolLM3-3B model, use alpaca instruction template.
Fine-tuned version of HuggingFaceTB/SmolLM3-3B on the ICEPVP8977/Uncensored_Small_Reasoning dataset.
This LoRA will fully uncensor the SmolLM3-3B model, use alpaca instruction template.