{"id":"291eb4fe-c1ea-46ca-92de-cd9073b32d26","slug":"hf-model-shubhamprshr-qwen2-5-7b-instruct-blocksworld1246-grpo-balanced-0-5-0-5-sec0-3dro1-0g0-0-minptrue-1200-1xctaqj-2t","name":"Qwen2.5-7B-Instruct_blocksworld1246_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1200","description":"Hugging Face model shubhamprshr/Qwen2.5-7B-Instruct_blocksworld1246_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1200. Task: text generation. Library: transformers. 26 downloads.","capabilities":["transformers","safetensors","qwen2","text-generation","generated_from_trainer","trl","grpo","conversational","dataset:blocksworld-dataset","arxiv:2402.03300","base_model:Qwen/Qwen2.5-7B-Instruct","base_model:finetune:Qwen/Qwen2.5-7B-Instruct","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:03.049Z"}