{"id":"834d7910-4346-463f-bec1-eec6a7bc7098","slug":"hf-model-shubhamrgandhi-qwen3-4b-dpo-prm-pairs-cfcmk4-11","name":"Qwen3-4B-DPO-prm-pairs","description":"Hugging Face model shubhamrgandhi/Qwen3-4B-DPO-prm-pairs. Task: text generation. Library: transformers. 43 downloads.","capabilities":["transformers","safetensors","qwen3","text-generation","trl","dpo","conversational","base_model:Qwen/Qwen3-4B-Instruct-2507","base_model:finetune:Qwen/Qwen3-4B-Instruct-2507","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":35,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:17.936Z"}