{"id":"451a888f-d32f-4911-9f45-1cfaed1e1a13","slug":"hf-model-logan7000-cogrpo-homo-llama31-8b-math345-groupa-llama31-8b-a-best-1ethgrh-1t","name":"cogrpo-homo-llama31-8b-math345-groupA-llama31-8b-a-best","description":"Hugging Face model logan7000/cogrpo-homo-llama31-8b-math345-groupA-llama31-8b-a-best. Task: reinforcement learning. 27 downloads.","capabilities":["safetensors","llama","grpo","co-grpo-dp","math","reinforcement-learning","dataset:q1716523669/MATH-Level345","base_model:meta-llama/Llama-3.1-8B-Instruct","base_model:finetune:meta-llama/Llama-3.1-8B-Instruct","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:56.640Z"}