The mesolitica/Malaysian-Qwen2.5-1.5B-Reasoning-GRPO galaxy

1 models are built on mesolitica/Malaysian-Qwen2.5-1.5B-Reasoning-GRPO: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 224 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Malaysian-Qwen2.5-1.5B-Reasoning-GRPO-GGUF (quantized), 210 downloads in 30 days

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