The ertghiu256/gemma-3-1b-reasoning-GRPO galaxy

1 models are built on ertghiu256/gemma-3-1b-reasoning-GRPO: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 335 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/gemma-3-1b-reasoning-GRPO-GGUF (quantized), 318 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.