huihui-ai/gemma-3-1b-it-abliterated-GRPO

The huihui-ai/gemma-3-1b-it-abliterated-GRPO is a 1 billion parameter instruction-tuned Gemma model developed by huihui-ai. It was fine-tuned from huihui-ai/gemma-3-1b-it-abliterated using the huihui-ai/Guilherme34_uncensor dataset. This model leverages Unsloth and Huggingface's TRL library for faster training, making it suitable for applications requiring a compact yet capable language model.