Instructions to use TusharGoel/LayoutLM-Finetuned-DocVQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TusharGoel/LayoutLM-Finetuned-DocVQA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("document-question-answering", model="TusharGoel/LayoutLM-Finetuned-DocVQA", device_map="auto")# Load model directly from transformers import AutoTokenizer, AutoModelForDocumentQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("TusharGoel/LayoutLM-Finetuned-DocVQA") model = AutoModelForDocumentQuestionAnswering.from_pretrained("TusharGoel/LayoutLM-Finetuned-DocVQA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
c4b5d4d
1
Parent(s): 495bbbd
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ language:
|
|
| 4 |
- en
|
| 5 |
pipeline_tag: document-question-answering
|
| 6 |
---
|
| 7 |
-
This model trained on DocVQA Dataset
|
| 8 |
|
| 9 |
Code for Training and Prediction (v1): https://www.kaggle.com/tusharcode/training-layoutlm-docvqa
|
| 10 |
|
|
|
|
| 4 |
- en
|
| 5 |
pipeline_tag: document-question-answering
|
| 6 |
---
|
| 7 |
+
This model was trained on [DocVQA](https://www.docvqa.org/) Dataset questions
|
| 8 |
|
| 9 |
Code for Training and Prediction (v1): https://www.kaggle.com/tusharcode/training-layoutlm-docvqa
|
| 10 |
|