The formalmathatepfl/qwen3-8b-classic-grpo galaxy

1 models are built on formalmathatepfl/qwen3-8b-classic-grpo: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 922 times in the last 30 days.

Most downloaded direct derivatives

• formalmathatepfl/classic-grpo-reasoning-sft (finetune), 630 downloads in 30 days

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