{"id":"6053fb43-5504-43b5-97c2-160bd231e3e2","slug":"hf-model-zou00080-llama-ppo-neg-informal-2lce4h-v","name":"llama_PPO_neg_informal","description":"Hugging Face model zou00080/llama_PPO_neg_informal. Task: reinforcement learning. Library: transformers. 18 downloads.","capabilities":["transformers","pytorch","llama","text-generation","trl","reinforcement-learning","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":32.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:40:12.311Z"}