{"id":"9d87ef75-c3ed-473b-90b5-6e4198b3dce6","slug":"hf-model-shion1124-sapo-gdpo-dora-qwen-struct-11rdxgm-10","name":"sapo-gdpo-dora-qwen-struct","description":"Hugging Face model Shion1124/sapo-gdpo-dora-qwen-struct. Task: text generation. Library: transformers. 24 downloads. 2 likes.","capabilities":["transformers","safetensors","qwen3","text-generation","sapo","gdpo","dapo","rlvr","dora","unsloth","qwen","structured-output","reinforcement-learning","conversational","en","dataset:u-10bei/dpo-dataset-qwen-cot","dataset:u-10bei/structured_data_with_cot_dataset_512_v5","dataset:daichira/structured-hard-sft-4k","arxiv:2601.05242","base_model:unsloth/Qwen3-4B-Instruct-2507"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:15.732Z"}