---
license: gpl-3.0
tags:
- DocVQA
- Document Question Answering
- Document Visual Question Answering
datasets:
- MP-DocVQA
language:
- en
---

# Longformer base fine-tuned on MP-DocVQA

This is Longformer-base trained on SQuAD v1 from [Valhalla hub](https://huggingface.co/valhalla/longformer-base-4096-finetuned-squadv1) and fine-tuned on Multipage DocVQA (MP-DocVQA) dataset.


This model was used as a baseline in [Hierarchical multimodal transformers for Multi-Page DocVQA](https://arxiv.org/pdf/2212.05935.pdf).
- Results on the MP-DocVQA dataset are reported in Table 2.
- Training hyperparameters can be found in Table 8 of Appendix D.

## How to use

Here is how to use this model to get the features of a given text in PyTorch:

```python
import torch
from transformers import LongformerTokenizerFast, LongformerForQuestionAnswering

tokenizer = LongformerTokenizerFast.from_pretrained("rubentito/longformer-base-mpdocvqa")
model = LongformerForQuestionAnswering.from_pretrained("rubentito/longformer-base-mpdocvqa")

text = "Huggingface has democratized NLP. Huge thanks to Huggingface for this."
question = "What has Huggingface done?"
encoding = tokenizer(question, text, return_tensors="pt")
input_ids = encoding["input_ids"]

# default is local attention everywhere
# the forward method will automatically set global attention on question tokens attention_mask=encoding["attention_mask"]

start_scores, end_scores = model(input_ids, attention_mask=attention_mask)
all_tokens = tokenizer.convert_ids_to_tokens(input_ids[0].tolist())

answer_tokens = all_tokens[torch.argmax(start_scores) :torch.argmax(end_scores)+1]
answer = tokenizer.decode(tokenizer.convert_tokens_to_ids(answer_tokens))
```

## BibTeX entry

```tex
@article{tito2022hierarchical,
  title={Hierarchical multimodal transformers for Multi-Page DocVQA},
  author={Tito, Rub{\`e}n and Karatzas, Dimosthenis and Valveny, Ernest},
  journal={arXiv preprint arXiv:2212.05935},
  year={2022}
}
```