allenai/Olmo-3-7B-Instruct-DPO download history

allenai/Olmo-3-7B-Instruct-DPO is a 7.3B-parameter text generation model by allenai. In the last 30 days it was downloaded 21,498 times (2,378 in the last 7 days), and 155,410 times in total.

It ranks #5,782 on the Hub by monthly downloads and #1,258 among text generation models.

It has 3 likes.

It is a fine-tune of allenai/Olmo-3-7B-Instruct-SFT.

737 models build on Olmo-3-7B-Instruct-DPO: 74 quantized, 618 fine-tuned, 45 adapters and 0 merges. Together with the original they were downloaded 246,523 times in the last 30 days. See the Olmo-3-7B-Instruct-DPO galaxy.

Most downloaded derivatives

Downloads by month

Downloads in the 30 days up to the end of each month, and the change from the month before.

MonthDownloadsChange
Up to 2026-11-1821,498+9%
October 202619,791+36%
September 202614,603-12%
August 202616,572+168%
July 20266,178-42%
June 202610,639-80%
May 202653,701+370%
April 202611,435+296%
March 20262,888+38%
February 20262,090-4%
January 20262,188+27%
December 20251,721+15%

Its busiest 30 days so far ended on 2026-05-15, with 54,008 downloads.

Open allenai/Olmo-3-7B-Instruct-DPO on Hugging Face

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