The formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-125-unmasked galaxy
1 models are built on formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-125-unmasked: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 1,124 times in the last 30 days.
Most downloaded direct derivatives
- formalmathatepfl/feedback-grpo-reasoning-sft (finetune), 1.1K downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.