{"id":"5a22b051-c2e7-40dd-94a8-1ceb74cf1d15","slug":"hf-model-cm00cm-qwen3-5-35b-a3b-dapo-rlvr-teacher-1ho3rry-14","name":"Qwen3.5-35B-A3B-DAPO-RLVR-teacher","description":"Hugging Face model cm00cm/Qwen3.5-35B-A3B-DAPO-RLVR-teacher. Task: reinforcement learning. 20 downloads. 1 likes.","capabilities":["safetensors","qwen3_5_moe","reinforcement-learning","rlvr","grpo","math","on-policy-distillation","miles","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:51.927Z"}