{"id":"6993338b-5cfb-4ec6-843b-c46a3ec6987c","slug":"hf-model-misalignment-empirics-theo-qwen2-5-32b-it-impulsive-dpo-v3-lora-1c5iwfm-1r","name":"theo_qwen2.5-32b-it_impulsive-dpo-v3-lora","description":"Hugging Face model Misalignment-Empirics/theo_qwen2.5-32b-it_impulsive-dpo-v3-lora. Task: text generation. Library: peft. 57 downloads.","capabilities":["peft","safetensors","base_model:adapter:Qwen/Qwen2.5-32B-Instruct","dpo","lora","transformers","trl","text-generation","conversational","arxiv:1910.09700","base_model:Qwen/Qwen2.5-32B-Instruct"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:02.496Z"}