{"id":"ef34cc07-90f3-48fe-ac70-cbe0d128d4f7","slug":"hf-model-jaygala24-qwen3-4b-grpo-math-reasoning-1egmjol-12","name":"Qwen3-4B-GRPO-math-reasoning","description":"Hugging Face model jaygala24/Qwen3-4B-GRPO-math-reasoning. Task: text generation. Library: transformers. 48 downloads.","capabilities":["transformers","safetensors","qwen3","text-generation","reinforcement-learning","grpo","math-reasoning","pipelinerl","conversational","dataset:gsm8k_train","dataset:math_train","base_model:Qwen/Qwen3-4B","base_model:finetune:Qwen/Qwen3-4B","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":35,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:11.583Z"}