The zhaohq/PureRL-1.5B-v7-stage1-reasoning galaxy

7 models are built on zhaohq/PureRL-1.5B-v7-stage1-reasoning: 0 quantized, 7 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 121 times in the last 30 days.

Most downloaded direct derivatives

• zhaohq/PureRL-1.5B-v7-s2-l2-kl-w3-b0 (finetune), 16 downloads in 30 days
• zhaohq/PureRL-1.5B-v7-s2-l2-kl-w2-b0 (finetune), 15 downloads in 30 days
• zhaohq/PureRL-1.5B-v7-s2-l2-kl-w3-b1 (finetune), 15 downloads in 30 days
• zhaohq/PureRL-1.5B-v7-s2-l2-kl-w0-b0 (finetune), 14 downloads in 30 days
• zhaohq/PureRL-1.5B-v7-s2-l2-kl-w2-b1 (finetune), 14 downloads in 30 days
• zhaohq/PureRL-1.5B-v7-s2-l2-kl-w0-b1 (finetune), 13 downloads in 30 days
• zhaohq/PureRL-1.5B-v7-s2-l2-kl-w1-b1 (finetune), 13 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.