Instructions to use U4R/ChartVLM-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use U4R/ChartVLM-base with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("U4R/ChartVLM-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download base_decoder/preprocessor_config.json from U4R/ChartVLM-base: direct link, hf CLI and curl.
- Browser
- Download file 249 Bytes
-
https://huggingface.co/U4R/ChartVLM-base/resolve/main/base_decoder/preprocessor_config.json
- Command line
-
hf download hf://U4R/ChartVLM-base/base_decoder/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/U4R/ChartVLM-base/resolve/main/base_decoder/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" | |
| } | |