Xenova/vit-gpt2-image-captioning download history
Xenova/vit-gpt2-image-captioning is an image to text model by Xenova. In the last 30 days it was downloaded 23,408 times (6,154 in the last 7 days), and 134,913 times in total.
It ranks #5,583 on the Hub by monthly downloads and #42 among image to text models.
It has 30 likes.
It is a quantization of nlpconnect/vit-gpt2-image-captioning.
1 models build on vit-gpt2-image-captioning: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 23,421 times in the last 30 days. See the vit-gpt2-image-captioning galaxy.
Most downloaded derivatives
- skillsafe-ai/vit-gpt2-image-captioning (quantized), 13 downloads in 30 days
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 23,408 | +24% |
| October 2026 | 18,868 | +87% |
| September 2026 | 10,109 | +10% |
| August 2026 | 9,155 | +78% |
| July 2026 | 5,137 | +2% |
| June 2026 | 5,027 | -16% |
| May 2026 | 6,020 | +2% |
| April 2026 | 5,879 | -29% |
| March 2026 | 8,224 | +59% |
| February 2026 | 5,174 | +4% |
| January 2026 | 4,971 | -22% |
| December 2025 | 6,335 | +100% |
Its busiest 30 days so far ended on 2026-11-18, with 23,408 downloads.
Open Xenova/vit-gpt2-image-captioning on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.