Instructions to use google/matcha-chart2text-pew with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/matcha-chart2text-pew with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="google/matcha-chart2text-pew")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/matcha-chart2text-pew") model = AutoModelForImageTextToText.from_pretrained("google/matcha-chart2text-pew") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,7 +38,7 @@ python convert_pix2struct_checkpoint_to_pytorch.py --t5x_checkpoint_path PATH_TO
|
|
| 38 |
```
|
| 39 |
if you are converting a large model, run:
|
| 40 |
```bash
|
| 41 |
-
python convert_pix2struct_checkpoint_to_pytorch.py --t5x_checkpoint_path PATH_TO_T5X_CHECKPOINTS --pytorch_dump_path PATH_TO_SAVE --use-large
|
| 42 |
```
|
| 43 |
Once saved, you can push your converted model with the following snippet:
|
| 44 |
```python
|
|
|
|
| 38 |
```
|
| 39 |
if you are converting a large model, run:
|
| 40 |
```bash
|
| 41 |
+
python convert_pix2struct_checkpoint_to_pytorch.py --t5x_checkpoint_path PATH_TO_T5X_CHECKPOINTS --pytorch_dump_path PATH_TO_SAVE --use-large --is_vqa
|
| 42 |
```
|
| 43 |
Once saved, you can push your converted model with the following snippet:
|
| 44 |
```python
|