cross-encoder/nli-MiniLM2-L6-H768 download history

cross-encoder/nli-MiniLM2-L6-H768 is an 82M-parameter zero shot classification model by cross-encoder. In the last 30 days it was downloaded 215,211 times (35,467 in the last 7 days), and 2,456,460 times in total.

It ranks #1,430 on the Hub by monthly downloads and #7 among zero shot classification models.

It has 16 likes.

It is a quantization of nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large.

17 models build on nli-MiniLM2-L6-H768: 2 quantized, 15 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 215,607 times in the last 30 days. See the nli-MiniLM2-L6-H768 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 2026-11-18215,211+11%
October 2026194,066-25%
September 2026259,542+69%
August 2026153,703-42%
July 2026267,103+109%
June 2026127,759-40%
May 2026212,246-18%
April 2026258,811+316%
March 202662,233+176%
February 202622,545+41%
January 202615,942+6%
December 202514,988+201%

Its busiest 30 days so far ended on 2026-05-15, with 310,968 downloads.

Open cross-encoder/nli-MiniLM2-L6-H768 on Hugging Face

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