cross-encoder/nli-deberta-v3-base download history

cross-encoder/nli-deberta-v3-base is an 184M-parameter zero shot classification model by cross-encoder. In the last 30 days it was downloaded 216,451 times (50,662 in the last 7 days), and 6,747,787 times in total.

It ranks #1,422 on the Hub by monthly downloads and #6 among zero shot classification models.

It has 53 likes, 1 of them in the last week.

It is a quantization of microsoft/deberta-v3-base.

18 models build on nli-deberta-v3-base: 4 quantized, 14 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 217,848 times in the last 30 days. See the nli-deberta-v3-base 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 2026-11-18216,451-10%
October 2026241,511-68%
September 2026743,650+61%
August 2026461,975+41%
July 2026326,950-15%
June 2026383,764+27%
May 2026303,329+65%
April 2026184,127+55%
March 2026118,534+64%
February 202672,241+94%
January 202637,321+10%
December 202534,047+30%

Its busiest 30 days so far ended on 2026-09-26, with 749,851 downloads.

Open cross-encoder/nli-deberta-v3-base on Hugging Face

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