{"id":"54d70bc6-50a8-4d9d-968f-0cae44583699","slug":"hf-model-ideallab-qwen2-5-coder-14b-instruct-grpo-sds-nohypothesize-step90-seed101-u4okcv-21","name":"Qwen2.5-Coder-14B-Instruct-GRPO-SDS-NoHypothesize-step90-seed101","description":"Hugging Face model IDEALLab/Qwen2.5-Coder-14B-Instruct-GRPO-SDS-NoHypothesize-step90-seed101. Task: reinforcement learning. Library: transformers. 33 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","reinforcement-learning","grpo","code-generation","combinatorial-optimization","ablation","base_model:Qwen/Qwen2.5-Coder-14B-Instruct","base_model:finetune:Qwen/Qwen2.5-Coder-14B-Instruct","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:35.813Z"}