The open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL galaxy

2 models are built on open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL: 0 quantized, 2 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 342 times in the last 30 days.

Most downloaded direct derivatives

• open-thoughts/OpenThinkerAgent-8B-RL (finetune), 217 downloads in 30 days
• zurichquants/OpenThinkerAgent-8B-RL (finetune), 79 downloads in 30 days