{"id":"fd7e7b5b-f9c6-49c0-974e-ae6395f4893d","slug":"hf-model-bhaveshsoni0023-llama-3-2-1b-grpo-gsm8k-1cu23u0-13","name":"llama-3.2-1b-grpo-gsm8k","description":"Hugging Face model bhaveshsoni0023/llama-3.2-1b-grpo-gsm8k. Task: text generation. 60 downloads.","capabilities":["safetensors","llama","grpo","reinforcement-learning","nemo-rl","math","gsm8k","text-generation","conversational","dataset:openai/gsm8k","base_model:meta-llama/Llama-3.2-1B-Instruct","base_model:finetune:meta-llama/Llama-3.2-1B-Instruct","license:llama3.2"],"protocols":[],"safetyScore":80,"overallRank":35.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:57.261Z"}