{"id":"d7213467-853d-42a0-9598-ca64f86c41f4","slug":"hf-model-sarapatel-llama31-8b-grpo-gsm8k-run1-f5li84-10","name":"llama31-8b-grpo-gsm8k-run1","description":"Hugging Face model sarapatel/llama31-8b-grpo-gsm8k-run1. Task: text generation. 23 downloads.","capabilities":["safetensors","llama","unsloth","trl","grpo","reasoning","math","gsm8k","rocm","amd","text-generation","conversational","en","dataset:openai/gsm8k","arxiv:2501.12948","arxiv:2110.14168","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":"2026-10-11T20:39:22.846Z"}