{"id":"3c5ce8e5-964e-42cb-ab79-2bd158fa8142","slug":"hf-model-pb09204048-qwen3-4b-code-rl-specialist-ssfb05-12","name":"Qwen3-4B-Code-RL-Specialist","description":"Hugging Face model pb09204048/Qwen3-4B-Code-RL-Specialist. Task: text generation. Library: transformers. 384 downloads. 1 likes.","capabilities":["transformers","safetensors","qwen3","text-generation","reinforcement-learning","grpo","lora-merged","mopd","multi-teacher-on-policy-distillation","code","conversational","dataset:agentica-org/DeepCoder-Preview-Dataset","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"}