Instructions to use TeeA/MATCHA-ViChart with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TeeA/MATCHA-ViChart with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="TeeA/MATCHA-ViChart")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("TeeA/MATCHA-ViChart") model = AutoModelForImageTextToText.from_pretrained("TeeA/MATCHA-ViChart") - Notebooks
- Google Colab
- Kaggle
Upload processor
Browse files- preprocessor_config.json +1 -1
preprocessor_config.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"do_convert_rgb": true,
|
| 3 |
"do_normalize": true,
|
| 4 |
"image_processor_type": "Pix2StructImageProcessor",
|
| 5 |
-
"is_vqa":
|
| 6 |
"max_patches": 2048,
|
| 7 |
"patch_size": {
|
| 8 |
"height": 16,
|
|
|
|
| 2 |
"do_convert_rgb": true,
|
| 3 |
"do_normalize": true,
|
| 4 |
"image_processor_type": "Pix2StructImageProcessor",
|
| 5 |
+
"is_vqa": true,
|
| 6 |
"max_patches": 2048,
|
| 7 |
"patch_size": {
|
| 8 |
"height": 16,
|