Instructions to use Xenova/pix2struct-widget-captioning-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Xenova/pix2struct-widget-captioning-base with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-text-to-text', 'Xenova/pix2struct-widget-captioning-base');
Download onnx/encoder_model_quantized.onnx from Xenova/pix2struct-widget-captioning-base: direct link, hf CLI and curl.
- Browser
- Download file 92.8 MB
-
https://huggingface.co/Xenova/pix2struct-widget-captioning-base/resolve/main/onnx/encoder_model_quantized.onnx
- Command line
-
hf download hf://Xenova/pix2struct-widget-captioning-base/onnx/encoder_model_quantized.onnx
-
curl -L -o encoder_model_quantized.onnx https://huggingface.co/Xenova/pix2struct-widget-captioning-base/resolve/main/onnx/encoder_model_quantized.onnx
92.8 MB
- Xet hash:
- 17cd7ed6ba36a6e096faf02b8a9dd7d7aba2355ad5a9a7f61c54bb19e17b8dc8
- Size of remote file:
- 92.8 MB
- SHA256:
- 4c300d43ea8c6b83bffebb5686373154d8677bc2e11ac8a4ae3c89c494997d0c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.