{"id":"fbd4e19e-4c04-4da7-a737-a4f29ff2bea7","slug":"hf-model-mariklolik228-grpo-baseline-qwen2-5-1-5b-lora-p309v8-19","name":"grpo-baseline-qwen2.5-1.5b-lora","description":"Hugging Face model mariklolik228/grpo-baseline-qwen2.5-1.5b-lora. Library: peft. 21 downloads.","capabilities":["peft","safetensors","grpo","math-reasoning","gsm8k","lora","qwen2.5","arxiv:2601.10349","base_model:Qwen/Qwen2.5-1.5B-Instruct","base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:38.881Z"}