{"id":"a7a7395d-8ac1-4dda-b23b-413c6f2ff7e5","slug":"hf-model-pb09204048-qwen3-4b-math-rl-specialist-oxnsp0-12","name":"Qwen3-4B-Math-RL-Specialist","description":"Hugging Face model pb09204048/Qwen3-4B-Math-RL-Specialist. Task: text generation. Library: transformers. 384 downloads.","capabilities":["transformers","safetensors","qwen3","text-generation","reinforcement-learning","grpo","lora-merged","mopd","multi-teacher-on-policy-distillation","math","conversational","dataset:zhuzilin/dapo-math-17k","arxiv:2606.30406","base_model:Qwen/Qwen3-4B","base_model:finetune:Qwen/Qwen3-4B","license:apache-2.0","model-index","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":40.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:43.023Z"}