Total runs:
856.2K
Run Growth:
227.0K
Growth Rate:
26.51%
deepset / xlm-roberta-large-squad2
Model's Last Updated: 2024年9月26日
question-answering
Introduction of xlm-roberta-large-squad2
Model Details of xlm-roberta-large-squad2
Multilingual XLM-RoBERTa large for QA on various languages
Overview
Language model:
xlm-roberta-large
Language:
Multilingual
Downstream-task:
Extractive QA
Training data:
SQuAD 2.0
Eval data:
SQuAD dev set - German MLQA - German XQuAD
Training run:
MLFlow link
Infrastructure
: 4x Tesla v100
Hyperparameters
batch_size = 32
n_epochs = 3
base_LM_model = "xlm-roberta-large"
max_seq_len = 256
learning_rate = 1e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
Performance
Evaluated on the SQuAD 2.0 English dev set with the official eval script .
"exact": 79.45759285774446,
"f1": 83.79259828925511,
"total": 11873,
"HasAns_exact": 71.96356275303644,
"HasAns_f1": 80.6460053117963,
"HasAns_total": 5928,
"NoAns_exact": 86.93019343986543,
"NoAns_f1": 86.93019343986543,
"NoAns_total": 5945
Evaluated on German MLQA: test-context-de-question-de.json
"exact": 49.34691166703564,
"f1": 66.15582561674236,
"total": 4517,
Evaluated on German XQuAD: xquad.de.json
"exact": 61.51260504201681,
"f1": 78.80206098332569,
"total": 1190,
Usage
In Haystack
For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in haystack :
reader = FARMReader(model_name_or_path="deepset/xlm-roberta-large-squad2")
# or
reader = TransformersReader(model="deepset/xlm-roberta-large-squad2",tokenizer="deepset/xlm-roberta-large-squad2")
In Transformers
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/xlm-roberta-large-squad2"
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)
# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
Authors
Branden Chan:
[email protected]
Timo Möller:
[email protected]
Malte Pietsch:
[email protected]
Tanay Soni:
[email protected]
About us
deepset is the company behind the open-source NLP framework Haystack which is designed to help you build production ready NLP systems that use: Question answering, summarization, ranking etc.
Some of our other work:
- Distilled roberta-base-squad2 (aka "tinyroberta-squad2")
- German BERT (aka "bert-base-german-cased")
- GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")
Get in touch and join the Haystack community
For more info on Haystack, visit our GitHub repo and Documentation .
We also have a Discord community open to everyone!
Twitter | LinkedIn | Discord | GitHub Discussions | Website
By the way: we're hiring!
Runs of deepset xlm-roberta-large-squad2 on huggingface.co
7.8K
Total runs
0
24-hour runs
50
3-day runs
-45
7-day runs
3.4K
30-day runs
More Information About xlm-roberta-large-squad2 huggingface.co Model
Url of xlm-roberta-large-squad2
xlm-roberta-large-squad2 huggingface.co Url
Provider of xlm-roberta-large-squad2 huggingface.co
Other API from deepset
Updated: 2024年9月24日
Total runs:
600.0K
Run Growth:
564.6K
Growth Rate:
94.11%
Total runs:
341.6K
Run Growth:
51.9K
Growth Rate:
15.20%
Total runs:
98.5K
Run Growth:
77.4K
Growth Rate:
78.62%
Total runs:
29.0K
Run Growth:
1.6K
Growth Rate:
5.51%
Total runs:
24.7K
Run Growth:
12.0K
Growth Rate:
48.53%
Total runs:
21.4K
Run Growth:
3.3K
Growth Rate:
15.63%
Total runs:
16.8K
Run Growth:
-796
Growth Rate:
-4.73%
Total runs:
9.6K
Run Growth:
6.7K
Growth Rate:
69.22%
Total runs:
7.3K
Run Growth:
52
Growth Rate:
0.73%
Total runs:
7.1K
Run Growth:
415
Growth Rate:
5.86%
Total runs:
5.8K
Run Growth:
-3.6K
Growth Rate:
-61.27%
Total runs:
1.8K
Run Growth:
492
Growth Rate:
24.45%
Total runs:
1.9K
Run Growth:
-3.2K
Growth Rate:
-169.17%
Total runs:
1.4K
Run Growth:
273
Growth Rate:
19.81%
Total runs:
961
Run Growth:
289
Growth Rate:
30.55%
Total runs:
750
Run Growth:
196
Growth Rate:
26.13%
Total runs:
295
Run Growth:
-497
Growth Rate:
-168.47%
Total runs:
240
Run Growth:
-398
Growth Rate:
-165.83%
Total runs:
216
Run Growth:
94
Growth Rate:
43.52%
Total runs:
197
Run Growth:
103
Growth Rate:
52.28%
Total runs:
159
Run Growth:
-104
Growth Rate:
-65.41%
Total runs:
148
Run Growth:
115
Growth Rate:
77.70%
Total runs:
145
Run Growth:
22
Growth Rate:
15.17%
Total runs:
61
Run Growth:
-112
Growth Rate:
-196.49%
Total runs:
61
Run Growth:
45
Growth Rate:
73.77%
Total runs:
56
Run Growth:
-13
Growth Rate:
-23.21%
Total runs:
40
Run Growth:
-37
Growth Rate:
-92.50%
Total runs:
37
Run Growth:
26
Growth Rate:
70.27%
Total runs:
36
Run Growth:
14
Growth Rate:
38.89%
Total runs:
25
Run Growth:
-25
Growth Rate:
-100.00%
Total runs:
25
Run Growth:
8
Growth Rate:
32.00%
Total runs:
16
Run Growth:
-41
Growth Rate:
-256.25%
Total runs:
15
Run Growth:
-14
Growth Rate:
-93.33%
Total runs:
12
Run Growth:
-8
Growth Rate:
-72.73%
Total runs:
3
Run Growth:
-10
Growth Rate:
-333.33%