The zztheaven/Llama-3.2-1B-Instruct-Open-R1-GRPO galaxy

110 models are built on zztheaven/Llama-3.2-1B-Instruct-Open-R1-GRPO: 60 quantized, 2 fine-tuned, 0 adapters and 48 merges. Together they were downloaded 30,735 times in the last 30 days.

Most downloaded direct derivatives