DGurgurov/OpenThinker3-7B-SFT-GRPO-DE download history
DGurgurov/OpenThinker3-7B-SFT-GRPO-DE is a 952M-parameter reinforcement learning model by DGurgurov. In the last 30 days it was downloaded 5,309 times (63 in the last 7 days), and 7,083 times in total.
It ranks #11,290 on the Hub by monthly downloads and #9 among reinforcement learning models.
It has 0 likes.
It is a fine-tune of open-thoughts/OpenThinker-7B.