{"id":"efc787c5-f946-4d3b-9e8e-32dc409e8c1d","slug":"hf-model-usama10-grpo-tax-qwen-1-5b-dpo-1r9q93f-u","name":"grpo-tax-qwen-1.5b-dpo","description":"Hugging Face model usama10/grpo-tax-qwen-1.5b-dpo. Task: text generation. Library: peft. 25 downloads.","capabilities":["peft","safetensors","dpo","alignment-tax","preference-learning","lora","research","text-generation","dataset:HuggingFaceH4/ultrafeedback_binarized","base_model:Qwen/Qwen2.5-1.5B-Instruct","base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:09.408Z"}