{"id":"861f965d-fd9c-4e80-95dd-4a21f82cc21c","slug":"hf-model-rl-llm-agent-llama-3-2-3b-instruct-online-dpo-alfworld-iter1-oad5s0-1o","name":"Llama-3.2-3B-Instruct-online-dpo-alfworld-iter1","description":"Hugging Face model rl-llm-agent/Llama-3.2-3B-Instruct-online-dpo-alfworld-iter1. Task: text generation. Library: transformers. 28 downloads.","capabilities":["transformers","pytorch","safetensors","llama","text-generation","conversational","arxiv:1910.09700","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:50.559Z"}