{"id":"1f2c5745-19dc-4404-a981-addd16471800","slug":"hf-model-kangdawei-mmr-sigmoid-grpo-6oo0or-q","name":"MMR-Sigmoid-GRPO","description":"Hugging Face model kangdawei/MMR-Sigmoid-GRPO. Task: text generation. Library: transformers. 19 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","open-r1","trl","grpo","conversational","dataset:knoveleng/open-rs","arxiv:2402.03300","base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:40:06.069Z"}