{"id":"2cf4fc03-2cf9-4999-97c4-b88236d9b50a","slug":"hf-model-usama10-grpo-tax-qwen-3b-dpo-1ynqa8a-s","name":"grpo-tax-qwen-3b-dpo","description":"Hugging Face model usama10/grpo-tax-qwen-3b-dpo. Task: text generation. Library: peft. 29 downloads.","capabilities":["peft","safetensors","dpo","alignment-tax","preference-learning","lora","research","text-generation","dataset:HuggingFaceH4/ultrafeedback_binarized","base_model:Qwen/Qwen2.5-3B-Instruct","base_model:adapter:Qwen/Qwen2.5-3B-Instruct","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:47.975Z"}