Instructions to use pardeepSF/layoutlm-vqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pardeepSF/layoutlm-vqa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("document-question-answering", model="pardeepSF/layoutlm-vqa")# Load model directly from transformers import AutoTokenizer, AutoModelForDocumentQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("pardeepSF/layoutlm-vqa") model = AutoModelForDocumentQuestionAnswering.from_pretrained("pardeepSF/layoutlm-vqa") - Notebooks
- Google Colab
- Kaggle
change
Browse files- config.json +1 -2
config.json
CHANGED
|
@@ -23,8 +23,7 @@
|
|
| 23 |
"position_embedding_type": "absolute",
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
"transformers_version": "4.23.1",
|
| 26 |
-
"type_vocab_size":
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 30522
|
| 29 |
}
|
| 30 |
-
|
|
|
|
| 23 |
"position_embedding_type": "absolute",
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
"transformers_version": "4.23.1",
|
| 26 |
+
"type_vocab_size": 2,
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 30522
|
| 29 |
}
|
|
|