Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
image-text-to-text
donut
document-parsing
lhdn
ebc
Instructions to use acceler-technology/dev-lhdn-parse-donut-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use acceler-technology/dev-lhdn-parse-donut-model with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" 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("image-to-text", model="acceler-technology/dev-lhdn-parse-donut-model")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("acceler-technology/dev-lhdn-parse-donut-model") model = AutoModelForMultimodalLM.from_pretrained("acceler-technology/dev-lhdn-parse-donut-model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training done
Browse files- preprocessor_config.json +1 -1
preprocessor_config.json
CHANGED
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
"size": [
|
| 23 |
-
|
| 24 |
1200
|
| 25 |
]
|
| 26 |
}
|
|
|
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
"size": [
|
| 23 |
+
600,
|
| 24 |
1200
|
| 25 |
]
|
| 26 |
}
|