{"id":"20463272-6f29-40f8-aeb6-d59ebbfa283b","slug":"hf-model-haitao999-llama-3-2-3b-instruct-grpo-numia-prompt-dpo1-lvqid5-1i","name":"Llama-3.2-3B-Instruct-GRPO-numia_prompt_dpo1","description":"Hugging Face model Haitao999/Llama-3.2-3B-Instruct-GRPO-numia_prompt_dpo1. Task: text generation. Library: transformers. 27 downloads.","capabilities":["transformers","safetensors","llama","text-generation","generated_from_trainer","open-r1","trl","grpo","conversational","dataset:RLHFlow/numia_prompt_dpo1","arxiv:2402.03300","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:54.986Z"}