{"id":"624dadd1-e805-4694-b90f-b2b398556a97","slug":"hf-model-misalignment-empirics-theo-qwen2-5-7b-it-loyalty-dpo-lora-1ooopem-1l","name":"theo_qwen2.5-7b-it_loyalty-dpo-lora","description":"Hugging Face model Misalignment-Empirics/theo_qwen2.5-7b-it_loyalty-dpo-lora. Task: text generation. Library: peft. 29 downloads.","capabilities":["peft","safetensors","base_model:adapter:Qwen/Qwen2.5-7B-Instruct","dpo","lora","transformers","trl","text-generation","conversational","base_model:Qwen/Qwen2.5-7B-Instruct"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:48.616Z"}