Instructions to use Xenova/pix2struct-infographics-vqa-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Xenova/pix2struct-infographics-vqa-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-infographics-vqa-base');
Download preprocessor_config.json from Xenova/pix2struct-infographics-vqa-base: direct link, hf CLI and curl.
- Browser
- Download file 249 Bytes
-
https://huggingface.co/Xenova/pix2struct-infographics-vqa-base/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Xenova/pix2struct-infographics-vqa-base/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Xenova/pix2struct-infographics-vqa-base/resolve/main/preprocessor_config.json
249 Bytes
| { | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "image_processor_type": "Pix2StructImageProcessor", | |
| "is_vqa": true, | |
| "max_patches": 2048, | |
| "patch_size": { | |
| "height": 16, | |
| "width": 16 | |
| }, | |
| "processor_class": "Pix2StructProcessor" | |
| } | |