The emre/Qwen-0.5B-GRPO galaxy
1 models are built on emre/Qwen-0.5B-GRPO: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 304 times in the last 30 days.
Most downloaded direct derivatives
- mradermacher/Qwen-0.5B-GRPO-GGUF (quantized), 214 downloads in 30 days
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.