{"id":"4516253f-5eef-44c2-b0ff-60d4845e4db7","slug":"hf-model-kangdawei-mmr-grpo-lambda-0-7-5s9n02-t","name":"MMR-GRPO-lambda-0.7","description":"Hugging Face model kangdawei/MMR-GRPO-lambda-0.7. Task: text generation. Library: transformers. 26 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":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:03.408Z"}