{"id":"0980df9e-c2de-4447-9187-42119b344c1f","slug":"hf-model-nomandery-dpo-shift-llama-3-8b-ultrafeedback-fixed-1-0-1g67pv3-1i","name":"DPO-Shift-Llama-3-8B-Ultrafeedback-fixed-1.0","description":"Hugging Face model NoManDeRY/DPO-Shift-Llama-3-8B-Ultrafeedback-fixed-1.0. Task: text generation. Library: transformers. 20 downloads.","capabilities":["transformers","safetensors","llama","text-generation","alignment-handbook","generated_from_trainer","conversational","dataset:HuggingFaceH4/ultrafeedback_binarized","arxiv:2502.07599","base_model:princeton-nlp/Llama-3-Base-8B-SFT","base_model:finetune:princeton-nlp/Llama-3-Base-8B-SFT","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:45.253Z"}