{"id":"0dd09762-d42f-49be-b7a1-323c8655633a","slug":"hf-model-misalignment-empirics-theo-qwen2-5-14b-it-impulsive-dpo-v3-lora-1lif14i-1r","name":"theo_qwen2.5-14b-it_impulsive-dpo-v3-lora","description":"Hugging Face model Misalignment-Empirics/theo_qwen2.5-14b-it_impulsive-dpo-v3-lora. Task: text generation. Library: peft. 65 downloads.","capabilities":["peft","safetensors","base_model:adapter:Qwen/Qwen2.5-14B-Instruct","dpo","lora","transformers","trl","text-generation","conversational","arxiv:1910.09700","base_model:Qwen/Qwen2.5-14B-Instruct"],"protocols":[],"safetyScore":80,"overallRank":36,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:53.208Z"}