Instructions to use google/pix2struct-ai2d-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/pix2struct-ai2d-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="google/pix2struct-ai2d-base")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/pix2struct-ai2d-base") model = AutoModelForImageTextToText.from_pretrained("google/pix2struct-ai2d-base") - Notebooks
- Google Colab
- Kaggle
Commit ·
afa922a
1
Parent(s): a1883ef
Fix copy-pasted text
Browse filesThere are a couple of subtitles that seem to have just been copy-pasted and ignored. This PR is just to update them.
README.md
CHANGED
|
@@ -72,7 +72,7 @@ print(processor.decode(predictions[0], skip_special_tokens=True))
|
|
| 72 |
|
| 73 |
### In full precision, on GPU:
|
| 74 |
|
| 75 |
-
You can run the model in full precision on
|
| 76 |
```python
|
| 77 |
import requests
|
| 78 |
from PIL import Image
|
|
@@ -95,7 +95,7 @@ print(processor.decode(predictions[0], skip_special_tokens=True))
|
|
| 95 |
|
| 96 |
### In half precision, on GPU:
|
| 97 |
|
| 98 |
-
You can run the model in
|
| 99 |
```python
|
| 100 |
import requests
|
| 101 |
from PIL import Image
|
|
|
|
| 72 |
|
| 73 |
### In full precision, on GPU:
|
| 74 |
|
| 75 |
+
You can run the model in full precision on GPU:
|
| 76 |
```python
|
| 77 |
import requests
|
| 78 |
from PIL import Image
|
|
|
|
| 95 |
|
| 96 |
### In half precision, on GPU:
|
| 97 |
|
| 98 |
+
You can run the model in half precision on GPU:
|
| 99 |
```python
|
| 100 |
import requests
|
| 101 |
from PIL import Image
|