{"id":"89e56efb-f366-44d1-b52b-b51c5f86beb4","slug":"hf-model-kangdawei-mmr-sigmoid-grpo-8b-ji5the-t","name":"MMR-Sigmoid-GRPO-8B","description":"Hugging Face model kangdawei/MMR-Sigmoid-GRPO-8B. Task: text generation. Library: transformers. 20 downloads. 1 likes.","capabilities":["transformers","safetensors","llama","text-generation","generated_from_trainer","open-r1","trl","grpo","conversational","dataset:knoveleng/open-rs","arxiv:2402.03300","base_model:deepseek-ai/DeepSeek-R1-Distill-Llama-8B","base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Llama-8B","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:49.563Z"}