Open-Reasoner-Zero/Open-Reasoner-Zero-7B download history

Open-Reasoner-Zero/Open-Reasoner-Zero-7B is a 7.6B-parameter reinforcement learning model by Open-Reasoner-Zero. In the last 30 days it was downloaded 1,265 times (409 in the last 7 days), and 56,971 times in total.

It ranks #29,977 on the Hub by monthly downloads and #98 among reinforcement learning models.

It has 34 likes.

9 models build on Open-Reasoner-Zero-7B: 6 quantized, 0 fine-tuned, 0 adapters and 3 merges. Together with the original they were downloaded 3,162 times in the last 30 days. See the Open-Reasoner-Zero-7B galaxy.

Most downloaded derivatives

Open Open-Reasoner-Zero/Open-Reasoner-Zero-7B on Hugging Face

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