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/decoder_with_past_model_quantized.onnx from Xenova/pix2struct-widget-captioning-base: direct link, hf CLI and curl.
- Browser
- Download file 178 MB
-
https://huggingface.co/Xenova/pix2struct-widget-captioning-base/resolve/main/onnx/decoder_with_past_model_quantized.onnx
- Command line
-
hf download hf://Xenova/pix2struct-widget-captioning-base/onnx/decoder_with_past_model_quantized.onnx
-
curl -L -o decoder_with_past_model_quantized.onnx https://huggingface.co/Xenova/pix2struct-widget-captioning-base/resolve/main/onnx/decoder_with_past_model_quantized.onnx
178 MB
- Xet hash:
- 5d51697470f89e4a08914965d87854178c23b460d5a5c2ca270556a5525e543e
- Size of remote file:
- 178 MB
- SHA256:
- 199939905a603c6e215185148e6ce43ed7ee34e15c594794061bb78ac92a76a2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.