{"id":"f07f9c27-c4c2-48e3-a1b4-b2b3d87883ae","slug":"hf-model-ianlee1996-pokerbench-qwen3-14b-lora-dpo-11z626g-14","name":"pokerbench-qwen3-14b-lora-dpo","description":"Hugging Face model ianlee1996/pokerbench-qwen3-14b-lora-dpo. Task: text generation. Library: peft. 48 downloads.","capabilities":["peft","safetensors","lora","poker","pokerbench","texas-holdem","gto","dpo","rlhf","trl","text-generation","conversational","en","zh","dataset:RZ412/PokerBench","dataset:ianlee1996/pokerbench-rl-dpo","arxiv:2501.08328","base_model:Qwen/Qwen3-14B","base_model:adapter:Qwen/Qwen3-14B","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":35,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:11.583Z"}