Total runs:
531.3K
Run Growth:
-31.3K
Growth Rate:
-5.90%
Sponsored by
Vmake Labs Video Enhancer
deepset / roberta-base-squad2-covid
Model's Last Updated: September 26 2024
question-answering
Introduction of roberta-base-squad2-covid
Model Details of roberta-base-squad2-covid
roberta-base-squad2 for QA on COVID-19
Overview
Language model:
deepset/roberta-base-squad2
Language:
English
Downstream-task:
Extractive QA
Training data:
SQuAD-style CORD-19 annotations from 23rd April
Code:
See
an example QA pipeline on Haystack
Infrastructure
: Tesla v100
Hyperparameters
batch_size = 24
n_epochs = 3
base_LM_model = "deepset/roberta-base-squad2"
max_seq_len = 384
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.1
doc_stride = 128
xval_folds = 5
dev_split = 0
no_ans_boost = -100
license: cc-by-4.0
Performance
5-fold cross-validation on the data set led to the following results:
Single EM-Scores:
[0.222, 0.123, 0.234, 0.159, 0.158]
Single F1-Scores:
[0.476, 0.493, 0.599, 0.461, 0.465]
Single top\_3\_recall Scores:
[0.827, 0.776, 0.860, 0.771, 0.777]
XVAL EM:
0.17890995260663506
XVAL f1:
0.49925444207319924
XVAL top\_3\_recall:
0.8021327014218009
This model is the model obtained from the third fold of the cross-validation.
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/roberta-base-squad2-covid")
# or
reader = TransformersReader(model="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2-covid")
In Transformers
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/roberta-base-squad2-covid"
# 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]
Bogdan Kostić:
[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 roberta-base-squad2-covid on huggingface.co
76
Total runs
1
24-hour runs
-2
3-day runs
-1
7-day runs
10
30-day runs
More Information About roberta-base-squad2-covid huggingface.co Model
Url of roberta-base-squad2-covid
roberta-base-squad2-covid huggingface.co Url
Provider of roberta-base-squad2-covid huggingface.co
Other API from deepset
Updated:September 24 2024
Total runs:
206.4K
Run Growth:
-186
Growth Rate:
-0.09%
Total runs:
190.4K
Run Growth:
2.4K
Growth Rate:
1.26%
Total runs:
62.4K
Run Growth:
-9.3K
Growth Rate:
-14.84%
Total runs:
43.9K
Run Growth:
-2.3K
Growth Rate:
-5.15%
Total runs:
35.4K
Run Growth:
-7.9K
Growth Rate:
-22.34%
Total runs:
15.9K
Run Growth:
-1.0K
Growth Rate:
-6.41%
Total runs:
15.9K
Run Growth:
-5.0K
Growth Rate:
-31.72%
Total runs:
15.2K
Run Growth:
-1.2K
Growth Rate:
-8.00%
Total runs:
13.7K
Run Growth:
4.2K
Growth Rate:
30.86%
Total runs:
11.5K
Run Growth:
-20.3K
Growth Rate:
-176.00%
Total runs:
9.5K
Run Growth:
6.2K
Growth Rate:
65.52%
Total runs:
9.4K
Run Growth:
190
Growth Rate:
2.15%
Total runs:
8.9K
Run Growth:
-241.8K
Growth Rate:
-3196.34%
Total runs:
8.2K
Run Growth:
522
Growth Rate:
6.39%
Total runs:
7.5K
Run Growth:
4.5K
Growth Rate:
60.22%
Total runs:
4.2K
Run Growth:
2.3K
Growth Rate:
55.32%
Total runs:
4.2K
Run Growth:
2.3K
Growth Rate:
54.21%
Total runs:
3.5K
Run Growth:
1.8K
Growth Rate:
51.61%
Total runs:
3.4K
Run Growth:
-8.6K
Growth Rate:
-257.65%
Total runs:
2.7K
Run Growth:
1.7K
Growth Rate:
62.84%
Total runs:
2.6K
Run Growth:
1.6K
Growth Rate:
61.61%
Total runs:
1.6K
Run Growth:
-212
Growth Rate:
-13.20%
Total runs:
1.4K
Run Growth:
476
Growth Rate:
33.40%
Total runs:
1.1K
Run Growth:
510
Growth Rate:
46.36%
Total runs:
859
Run Growth:
72
Growth Rate:
8.38%
Total runs:
819
Run Growth:
-3
Growth Rate:
-0.37%
Total runs:
547
Run Growth:
310
Growth Rate:
56.67%
Total runs:
448
Run Growth:
163
Growth Rate:
36.38%
Total runs:
164
Run Growth:
16
Growth Rate:
9.82%
Total runs:
142
Run Growth:
41
Growth Rate:
28.87%
Total runs:
124
Run Growth:
43
Growth Rate:
34.68%
Total runs:
101
Run Growth:
53
Growth Rate:
52.48%
Total runs:
95
Run Growth:
-6
Growth Rate:
-6.32%
Total runs:
87
Run Growth:
39
Growth Rate:
44.83%
Total runs:
77
Run Growth:
41
Growth Rate:
53.25%
Total runs:
63
Run Growth:
-27
Growth Rate:
-42.86%
Total runs:
61
Run Growth:
-30
Growth Rate:
-49.18%
Total runs:
53
Run Growth:
16
Growth Rate:
29.63%
Total runs:
33
Run Growth:
14
Growth Rate:
42.42%
Total runs:
23
Run Growth:
-41
Growth Rate:
-178.26%
Total runs:
8
Run Growth:
-5
Growth Rate:
-62.50%