{"id":"f2151e0a-0d2f-42f3-883a-1022b984b1a5","slug":"hf-model-logan7000-cogrpo-homo-llama31-8b-math345-groupa-llama31-8b-a-end-1h75qhy-1s","name":"cogrpo-homo-llama31-8b-math345-groupA-llama31-8b-a-end","description":"Hugging Face model logan7000/cogrpo-homo-llama31-8b-math345-groupA-llama31-8b-a-end. Task: reinforcement learning. 21 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,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:40.398Z"}