{"id":"830053a7-65df-4952-810c-034b97d01369","slug":"hf-model-rag-gym-search-o1-medqa-dpo-xadh42-r","name":"Search-o1-MedQA-DPO","description":"Hugging Face model RAG-Gym/Search-o1-MedQA-DPO. Task: text generation. Library: peft. 21 downloads.","capabilities":["peft","safetensors","rag-gym","retrieval-augmented-generation","agent","lora","process-supervision","search-agent","text-generation","conversational","arxiv:2502.13957","base_model:meta-llama/Llama-3.1-8B-Instruct","base_model:adapter:meta-llama/Llama-3.1-8B-Instruct","license:other"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:35.581Z"}