{"id":"4c24129e-0cce-4264-88a2-6a6bb049fc7c","slug":"hf-model-jaygala24-qwen3-1-7b-grpo-kl-math-reasoning-i9x11n-17","name":"Qwen3-1.7B-GRPO-KL-math-reasoning","description":"Hugging Face model jaygala24/Qwen3-1.7B-GRPO-KL-math-reasoning. Task: text generation. Library: transformers. 699 downloads.","capabilities":["transformers","safetensors","qwen3","text-generation","reinforcement-learning","grpo","math-reasoning","pipelinerl","conversational","dataset:gsm8k_train","dataset:math_train","base_model:Qwen/Qwen3-1.7B","base_model:finetune:Qwen/Qwen3-1.7B","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":42,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:36:28.485Z"}