Instructions to use Xenova/pix2struct-docvqa-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Xenova/pix2struct-docvqa-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-docvqa-base');
Download onnx/decoder_model_quantized.onnx from Xenova/pix2struct-docvqa-base: direct link, hf CLI and curl.
- Browser
- Download file 192 MB
-
https://huggingface.co/Xenova/pix2struct-docvqa-base/resolve/main/onnx/decoder_model_quantized.onnx
- Command line
-
hf download hf://Xenova/pix2struct-docvqa-base/onnx/decoder_model_quantized.onnx
-
curl -L -o decoder_model_quantized.onnx https://huggingface.co/Xenova/pix2struct-docvqa-base/resolve/main/onnx/decoder_model_quantized.onnx
192 MB
- Xet hash:
- 28140e8150133efa9d400e3dabd24436249dee3679b432501706303140b56dfb
- Size of remote file:
- 192 MB
- SHA256:
- d54e5eba132b64332dd0a8745381b7935b90eb397c44bc1857c461b11d291807
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.