Hugging Face's logo

rubentito
/
bert-large-mpdocvqa

Question Answering
Transformers
PyTorch
English
bert
DocVQA
Document Question Answering
Document Visual Question Answering
Inference Endpoints
Model card Files Community
1
rubentito commited on
Commit
ab7d3cf
•
1 Parent(s): d9d457e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -10,7 +10,7 @@ language:
10
  - en
11
  ---
12
 
13
- # BERT-LARGE fine-tuned on MP-DocVQA
14
 
15
  This is BERT trained on [SinglePage DocVQA](https://arxiv.org/abs/2007.00398) and fine-tuned on Multipage DocVQA (MP-DocVQA) dataset.
16
 
@@ -43,14 +43,14 @@ pred_answer = context[start_pos:end_pos]
43
 
44
  Extended experimentation can be found in Table 2 of [Hierarchical multimodal transformers for Multi-Page DocVQA](https://arxiv.org/pdf/2212.05935.pdf).
45
  You can also check the live leaderboard at the [RRC Portal](https://rrc.cvc.uab.es/?ch=17&com=evaluation&task=4).
46
- | Model | HF name | ANLS | APPA |
47
- |-----------------------------------------------------------------------------------|:--------------------------------------|:-------------:|:---------:|
48
- | [**Bert large**](https://huggingface.co/rubentito/bert-large-mpdocvqa) | rubentito/bert-large-mpdocvqa | 0.4183 | 51.6177 |
49
- | [Longformer base](https://huggingface.co/rubentito/longformer-base-mpdocvqa) | rubentito/longformer-base-mpdocvqa | 0.5287 | 71.1696 |
50
- | [BigBird ITC base](https://huggingface.co/rubentito/bigbird-base-itc-mpdocvqa) | rubentito/bigbird-base-itc-mpdocvqa | 0.4929 | 67.5433 |
51
- | [LayoutLMv3 base](https://huggingface.co/rubentito/layoutlmv3-base-mpdocvqa) | rubentito/layoutlmv3-base-mpdocvqa | 0.4538 | 51.9426 |
52
- | [T5 base](https://huggingface.co/rubentito/t5-base-mpdocvqa) | rubentito/t5-base-mpdocvqa | 0.5050 | 0.0000 |
53
- | Hi-VT5 | TBA | 0.6201 | 79.23 |
54
 
55
  ## Citation Information
56
 
 
10
  - en
11
  ---
12
 
13
+ # BERT large fine-tuned on MP-DocVQA
14
 
15
  This is BERT trained on [SinglePage DocVQA](https://arxiv.org/abs/2007.00398) and fine-tuned on Multipage DocVQA (MP-DocVQA) dataset.
16
 
 
43
 
44
  Extended experimentation can be found in Table 2 of [Hierarchical multimodal transformers for Multi-Page DocVQA](https://arxiv.org/pdf/2212.05935.pdf).
45
  You can also check the live leaderboard at the [RRC Portal](https://rrc.cvc.uab.es/?ch=17&com=evaluation&task=4).
46
+ | Model | HF name | Parameters | ANLS | APPA |
47
+ |-----------------------------------------------------------------------------------|:--------------------------------------|:-------------:|:-------------:|:---------:|
48
+ | [**Bert large**](https://huggingface.co/rubentito/bert-large-mpdocvqa) | rubentito/bert-large-mpdocvqa | 334M | 0.4183 | 51.6177 |
49
+ | [Longformer base](https://huggingface.co/rubentito/longformer-base-mpdocvqa) | rubentito/longformer-base-mpdocvqa | 148M | 0.5287 | 71.1696 |
50
+ | [BigBird ITC base](https://huggingface.co/rubentito/bigbird-base-itc-mpdocvqa) | rubentito/bigbird-base-itc-mpdocvqa | 131M | 0.4929 | 67.5433 |
51
+ | [LayoutLMv3 base](https://huggingface.co/rubentito/layoutlmv3-base-mpdocvqa) | rubentito/layoutlmv3-base-mpdocvqa | 125M | 0.4538 | 51.9426 |
52
+ | [T5 base](https://huggingface.co/rubentito/t5-base-mpdocvqa) | rubentito/t5-base-mpdocvqa | 223M | 0.5050 | 0.0000 |
53
+ | Hi-VT5 | TBA | 316M | 0.6201 | 79.23 |
54
 
55
  ## Citation Information
56