Mingsmilet/Qwen2.5-7B-GRPO-MATH download history

Mingsmilet/Qwen2.5-7B-GRPO-MATH is a 7.6B-parameter text generation model by Mingsmilet. In the last 30 days it was downloaded 18 times (11 in the last 7 days), and 380 times in total.

It ranks #453,072 on the Hub by monthly downloads and #143,285 among text generation models.

It has 0 likes.

It is a fine-tune of Qwen/Qwen2.5-7B-Instruct.

Open Mingsmilet/Qwen2.5-7B-GRPO-MATH on Hugging Face

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