The tbooy/Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2 galaxy

3 models are built on tbooy/Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2: 0 quantized, 2 fine-tuned, 1 adapters and 0 merges. Together they were downloaded 1,786 times in the last 30 days.

Most downloaded direct derivatives

• tbooy/Qwen2.5-3B-Instruct-Sheldon-RLVR-math-v1 (adapter), 902 downloads in 30 days

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