{"id":"a1803f16-12c4-45b8-9472-f1e97b36797e","slug":"hf-model-shufanshen-qwen3-4b-grpo-codeeurus-100-steps-2dtx7p-18","name":"Qwen3-4B-GRPO-CodeEurus-100-steps","description":"Hugging Face model shufanshen/Qwen3-4B-GRPO-CodeEurus-100-steps. Task: reinforcement learning. Library: transformers. 20 downloads.","capabilities":["transformers","safetensors","qwen3","text-generation","grpo","reinforcement-learning","opd","opsft","base_model:Qwen/Qwen3-4B","base_model:finetune:Qwen/Qwen3-4B","license:other","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:52.294Z"}