{"id":"d805468d-08d8-4258-bb4a-501d2714ab80","slug":"hf-model-misalignment-empirics-shreyans-qwen2-5-32b-it-impulsive-dpo-v2-lora-1x06tce-1v","name":"shreyans_qwen2.5-32b-it_impulsive-dpo-v2-lora","description":"Hugging Face model Misalignment-Empirics/shreyans_qwen2.5-32b-it_impulsive-dpo-v2-lora. Task: text generation. Library: peft. 55 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":"2026-10-11T20:38:04.380Z"}