Visual Question Answering
Transformers
Safetensors
Vietnamese
vision-encoder-decoder
image-text-to-text
Instructions to use TeeA/DONUT-ViChart with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TeeA/DONUT-ViChart with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="TeeA/DONUT-ViChart")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("TeeA/DONUT-ViChart") model = AutoModelForMultimodalLM.from_pretrained("TeeA/DONUT-ViChart", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,7 @@ language:
|
|
| 5 |
- vi
|
| 6 |
library_name: transformers
|
| 7 |
pipeline_tag: visual-question-answering
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
|
|
|
| 5 |
- vi
|
| 6 |
library_name: transformers
|
| 7 |
pipeline_tag: visual-question-answering
|
| 8 |
+
widget:
|
| 9 |
+
- text: <s_vichart>
|
| 10 |
+
src: ViChart-demo.png
|
| 11 |
---
|