Total runs:
350.7K
Run Growth:
166.8K
Growth Rate:
47.55%
Sponsored by
PostMcpAi
mrm8488 / bert-multi-cased-finetuned-xquadv1
Model's Last Updated: March 19 2023
question-answering
Introduction of bert-multi-cased-finetuned-xquadv1
Model Details of bert-multi-cased-finetuned-xquadv1
BERT (base-multilingual-cased) fine-tuned for multilingual Q&A
This model was created by
Google
and fine-tuned on
XQuAD
like data for multilingual (
11 different languages
)
Q&A
downstream task.
Details of the language model('bert-base-multilingual-cased')
| Languages | Heads | Layers | Hidden | Params |
|---|---|---|---|---|
| 104 | 12 | 12 | 768 | 100 M |
Details of the downstream task (multilingual Q&A) - Dataset
Deepmind XQuAD
Languages covered:
-
Arabic:
ar -
German:
de -
Greek:
el -
English:
en -
Spanish:
es -
Hindi:
hi -
Russian:
ru -
Thai:
th -
Turkish:
tr -
Vietnamese:
vi -
Chinese:
zh
As the dataset is based on SQuAD v1.1, there are no unanswerable questions in the data. We chose this setting so that models can focus on cross-lingual transfer.
We show the average number of tokens per paragraph, question, and answer for each language in the table below. The statistics were obtained using Jieba for Chinese and the Moses tokenizer for the other languages.
| en | es | de | el | ru | tr | ar | vi | th | zh | hi | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Paragraph | 142.4 | 160.7 | 139.5 | 149.6 | 133.9 | 126.5 | 128.2 | 191.2 | 158.7 | 147.6 | 232.4 |
| Question | 11.5 | 13.4 | 11.0 | 11.7 | 10.0 | 9.8 | 10.7 | 14.8 | 11.5 | 10.5 | 18.7 |
| Answer | 3.1 | 3.6 | 3.0 | 3.3 | 3.1 | 3.1 | 3.1 | 4.5 | 4.1 | 3.5 | 5.6 |
Citation:
@article{Artetxe:etal:2019,
author = {Mikel Artetxe and Sebastian Ruder and Dani Yogatama},
title = {On the cross-lingual transferability of monolingual representations},
journal = {CoRR},
volume = {abs/1910.11856},
year = {2019},
archivePrefix = {arXiv},
eprint = {1910.11856}
}
As
XQuAD
is just an evaluation dataset, I used
Data augmentation techniques
(scraping, neural machine translation, etc) to obtain more samples and split the dataset in order to have a train and test set. The test set was created in a way that contains the same number of samples for each language. Finally, I got:
| Dataset | # samples |
|---|---|
| XQUAD train | 50 K |
| XQUAD test | 8 K |
Model training
The model was trained on a Tesla P100 GPU and 25GB of RAM. The script for fine tuning can be found here
Model in action
Fast usage with pipelines :
from transformers import pipeline
from transformers import pipeline
qa_pipeline = pipeline(
"question-answering",
model="mrm8488/bert-multi-cased-finetuned-xquadv1",
tokenizer="mrm8488/bert-multi-cased-finetuned-xquadv1"
)
# context: Coronavirus is seeding panic in the West because it expands so fast.
# question: Where is seeding panic Coronavirus?
qa_pipeline({
'context': "कोरोनावायरस पश्चिम में आतंक बो रहा है क्योंकि यह इतनी तेजी से फैलता है।",
'question': "कोरोनावायरस घबराहट कहां है?"
})
# output: {'answer': 'पश्चिम', 'end': 18, 'score': 0.7037217439689059, 'start': 12}
qa_pipeline({
'context': "Manuel Romero has been working hardly in the repository hugginface/transformers lately",
'question': "Who has been working hard for hugginface/transformers lately?"
})
# output: {'answer': 'Manuel Romero', 'end': 13, 'score': 0.7254485993702389, 'start': 0}
qa_pipeline({
'context': "Manuel Romero a travaillé à peine dans le référentiel hugginface / transformers ces derniers temps",
'question': "Pour quel référentiel a travaillé Manuel Romero récemment?"
})
#output: {'answer': 'hugginface / transformers', 'end': 79, 'score': 0.6482061613915384, 'start': 54}
Try it on a Colab:
Created by Manuel Romero/@mrm8488
Made with ♥ in Spain
Runs of mrm8488 bert-multi-cased-finetuned-xquadv1 on huggingface.co
1.9K
Total runs
-47
24-hour runs
-73
3-day runs
-18
7-day runs
1.5K
30-day runs
More Information About bert-multi-cased-finetuned-xquadv1 huggingface.co Model
Url of bert-multi-cased-finetuned-xquadv1
bert-multi-cased-finetuned-xquadv1 huggingface.co Url
Provider of bert-multi-cased-finetuned-xquadv1 huggingface.co
Other API from mrm8488
Updated:January 21 2024
Total runs:
32.3K
Run Growth:
320
Growth Rate:
0.99%
Total runs:
16.5K
Run Growth:
-62.5K
Growth Rate:
-378.74%
Total runs:
13.4K
Run Growth:
1.8K
Growth Rate:
13.31%
Total runs:
12.1K
Run Growth:
5.5K
Growth Rate:
45.47%
Total runs:
9.5K
Run Growth:
4.9K
Growth Rate:
50.91%
Total runs:
8.7K
Run Growth:
5.7K
Growth Rate:
65.22%
Total runs:
8.3K
Run Growth:
6.0K
Growth Rate:
72.75%
Total runs:
5.9K
Run Growth:
150
Growth Rate:
2.54%
Total runs:
4.6K
Run Growth:
-34.4K
Growth Rate:
-746.66%
Total runs:
3.7K
Run Growth:
2.8K
Growth Rate:
74.19%
Total runs:
2.9K
Run Growth:
2.6K
Growth Rate:
87.56%
Total runs:
2.3K
Run Growth:
-3.1K
Growth Rate:
-136.27%
Total runs:
1.4K
Run Growth:
-1.3K
Growth Rate:
-92.30%
Total runs:
1.3K
Run Growth:
-34
Growth Rate:
-2.55%
Total runs:
967
Run Growth:
374
Growth Rate:
38.68%
Total runs:
960
Run Growth:
-1.0K
Growth Rate:
-105.21%
Total runs:
821
Run Growth:
284
Growth Rate:
34.59%
Total runs:
814
Run Growth:
-101
Growth Rate:
-12.41%
Total runs:
744
Run Growth:
-111
Growth Rate:
-14.92%
Total runs:
734
Run Growth:
-94
Growth Rate:
-12.81%
Total runs:
682
Run Growth:
335
Growth Rate:
49.12%
Total runs:
542
Run Growth:
53
Growth Rate:
10.23%
Total runs:
533
Run Growth:
57
Growth Rate:
10.69%
Total runs:
467
Run Growth:
404
Growth Rate:
86.51%
Total runs:
464
Run Growth:
366
Growth Rate:
78.88%
Total runs:
452
Run Growth:
-357
Growth Rate:
-78.98%
Total runs:
378
Run Growth:
75
Growth Rate:
19.84%
Total runs:
366
Run Growth:
57
Growth Rate:
15.57%
Total runs:
344
Run Growth:
169
Growth Rate:
49.13%
Total runs:
326
Run Growth:
88
Growth Rate:
26.99%
Total runs:
310
Run Growth:
-326
Growth Rate:
-105.16%
Total runs:
300
Run Growth:
-48
Growth Rate:
-16.00%
Total runs:
269
Run Growth:
24
Growth Rate:
8.92%
Total runs:
260
Run Growth:
255
Growth Rate:
98.08%
Total runs:
254
Run Growth:
177
Growth Rate:
69.69%
Total runs:
250
Run Growth:
-122
Growth Rate:
-48.80%
Total runs:
242
Run Growth:
-17
Growth Rate:
-7.02%
Total runs:
227
Run Growth:
-197
Growth Rate:
-86.78%
Total runs:
205
Run Growth:
47
Growth Rate:
22.93%
Total runs:
182
Run Growth:
-38
Growth Rate:
-20.88%
Total runs:
165
Run Growth:
-117
Growth Rate:
-70.91%
Total runs:
164
Run Growth:
-81
Growth Rate:
-49.39%
Total runs:
162
Run Growth:
107
Growth Rate:
66.05%
Total runs:
160
Run Growth:
130
Growth Rate:
81.25%
Total runs:
154
Run Growth:
120
Growth Rate:
77.92%
Total runs:
145
Run Growth:
75
Growth Rate:
51.72%
Total runs:
122
Run Growth:
100
Growth Rate:
81.97%
Total runs:
119
Run Growth:
114
Growth Rate:
96.61%
Total runs:
119
Run Growth:
-11
Growth Rate:
-9.24%
Total runs:
116
Run Growth:
38
Growth Rate:
32.76%
Total runs:
115
Run Growth:
33
Growth Rate:
28.70%
Total runs:
112
Run Growth:
40
Growth Rate:
35.71%
Total runs:
110
Run Growth:
96
Growth Rate:
87.27%
Total runs:
95
Run Growth:
91
Growth Rate:
95.79%
Total runs:
94
Run Growth:
-12
Growth Rate:
-12.77%
Total runs:
92
Run Growth:
68
Growth Rate:
73.91%
Total runs:
92
Run Growth:
-39
Growth Rate:
-42.39%
Total runs:
92
Run Growth:
-33
Growth Rate:
-35.87%
Total runs:
86
Run Growth:
-132
Growth Rate:
-153.49%
Total runs:
85
Run Growth:
77
Growth Rate:
90.59%
Total runs:
84
Run Growth:
-24
Growth Rate:
-28.57%
Total runs:
83
Run Growth:
59
Growth Rate:
71.08%
Total runs:
82
Run Growth:
-40
Growth Rate:
-48.78%
Total runs:
82
Run Growth:
57
Growth Rate:
69.51%
Total runs:
81
Run Growth:
73
Growth Rate:
90.12%
Total runs:
81
Run Growth:
-14
Growth Rate:
-17.28%
Total runs:
80
Run Growth:
-15
Growth Rate:
-18.75%
Total runs:
78
Run Growth:
74
Growth Rate:
96.10%
Total runs:
76
Run Growth:
47
Growth Rate:
61.84%
Total runs:
73
Run Growth:
31
Growth Rate:
42.47%
Total runs:
70
Run Growth:
49
Growth Rate:
70.00%
Total runs:
69
Run Growth:
45
Growth Rate:
65.22%
Total runs:
66
Run Growth:
-8
Growth Rate:
-12.12%
Total runs:
62
Run Growth:
23
Growth Rate:
37.10%
Total runs:
60
Run Growth:
44
Growth Rate:
73.33%
Total runs:
59
Run Growth:
-11
Growth Rate:
-18.64%
Total runs:
56
Run Growth:
35
Growth Rate:
62.50%
Total runs:
56
Run Growth:
52
Growth Rate:
92.86%
Total runs:
55
Run Growth:
47
Growth Rate:
85.45%
Total runs:
53
Run Growth:
50
Growth Rate:
94.34%
Total runs:
51
Run Growth:
32
Growth Rate:
62.75%
Total runs:
51
Run Growth:
-279
Growth Rate:
-547.06%
Total runs:
50
Run Growth:
40
Growth Rate:
80.00%
Total runs:
49
Run Growth:
12
Growth Rate:
24.49%
Total runs:
49
Run Growth:
19
Growth Rate:
38.78%
Total runs:
48
Run Growth:
-2
Growth Rate:
-4.17%
Total runs:
47
Run Growth:
46
Growth Rate:
97.87%
Total runs:
46
Run Growth:
38
Growth Rate:
82.61%
Total runs:
46
Run Growth:
32
Growth Rate:
69.57%
Total runs:
45
Run Growth:
7
Growth Rate:
15.56%
Total runs:
44
Run Growth:
9
Growth Rate:
20.45%
Total runs:
44
Run Growth:
42
Growth Rate:
95.45%