Sponsored by
APIMart
optimum / roberta-base-squad2
Model's Last Updated: March 25 2022
question-answering
Introduction of roberta-base-squad2
Model Details of roberta-base-squad2
ONNX convert roberta-base for QA
Conversion of deepset/roberta-base-squad2
NOTE: This is version 2 of the model. See
this github issue
from the FARM repository for an explanation of why we updated. If you'd like to use version 1, specify
revision="v1.0"
when loading the model in Transformers 3.5. For exmaple:
model_name = "deepset/roberta-base-squad2"
pipeline(model=model_name, tokenizer=model_name, revision="v1.0", task="question-answering")
Overview
Language model:
roberta-base
Language:
English
Downstream-task:
Extractive QA
Training data:
SQuAD 2.0
Eval data:
SQuAD 2.0
Code:
See
example
in
FARM
Infrastructure
: 4x Tesla v100
Hyperparameters
batch_size = 96
n_epochs = 2
base_LM_model = "roberta-base"
max_seq_len = 386
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
Using a distilled model instead
Please note that we have also released a distilled version of this model called deepset/tinyroberta-squad2 . The distilled model has a comparable prediction quality and runs at twice the speed of the base model.
Performance
Evaluated on the SQuAD 2.0 dev set with the official eval script .
"exact": 79.87029394424324,
"f1": 82.91251169582613,
"total": 11873,
"HasAns_exact": 77.93522267206478,
"HasAns_f1": 84.02838248389763,
"HasAns_total": 5928,
"NoAns_exact": 81.79983179142137,
"NoAns_f1": 81.79983179142137,
"NoAns_total": 5945
Usage
In Transformers
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/roberta-base-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)
In FARM
from farm.modeling.adaptive_model import AdaptiveModel
from farm.modeling.tokenization import Tokenizer
from farm.infer import Inferencer
model_name = "deepset/roberta-base-squad2"
# a) Get predictions
nlp = Inferencer.load(model_name, task_type="question_answering")
QA_input = [{"questions": ["Why is model conversion important?"],
"text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}]
res = nlp.inference_from_dicts(dicts=QA_input, rest_api_schema=True)
# b) Load model & tokenizer
model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering")
tokenizer = Tokenizer.load(model_name)
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")
# or
reader = TransformersReader(model_name_or_path="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2")
Authors
Branden Chan:
branden.chan [at] deepset.ai
Timo Möller:
timo.moeller [at] deepset.ai
Malte Pietsch:
malte.pietsch [at] deepset.ai
Tanay Soni:
tanay.soni [at] deepset.ai
About us
Our focus: Industry specific language models & large scale QA systems.
Some of our work:
- German BERT (aka "bert-base-german-cased")
- GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")
- FARM
- Haystack
Get in touch: Twitter | LinkedIn | Slack | GitHub Discussions | Website
By the way: we're hiring!
Runs of optimum roberta-base-squad2 on huggingface.co
12
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
-14
30-day runs
More Information About roberta-base-squad2 huggingface.co Model
Url of roberta-base-squad2
roberta-base-squad2 huggingface.co Url
Provider of roberta-base-squad2 huggingface.co
Other API from optimum
Total runs:
4.8K
Run Growth:
2.8K
Growth Rate:
58.04%
Total runs:
2.0K
Run Growth:
234
Growth Rate:
11.82%
Total runs:
1.2K
Run Growth:
797
Growth Rate:
65.92%
Total runs:
450
Run Growth:
248
Growth Rate:
55.11%
Total runs:
334
Run Growth:
219
Growth Rate:
65.57%
Total runs:
134
Run Growth:
132
Growth Rate:
98.51%
Total runs:
59
Run Growth:
43
Growth Rate:
72.88%
Total runs:
35
Run Growth:
25
Growth Rate:
71.43%
Total runs:
32
Run Growth:
19
Growth Rate:
59.38%
Total runs:
31
Run Growth:
-19
Growth Rate:
-61.29%
Total runs:
27
Run Growth:
15
Growth Rate:
55.56%
Total runs:
14
Run Growth:
6
Growth Rate:
42.86%
Total runs:
14
Run Growth:
14
Growth Rate:
100.00%
Total runs:
11
Run Growth:
-21
Growth Rate:
-190.91%
Total runs:
9
Run Growth:
7
Growth Rate:
77.78%
Total runs:
8
Run Growth:
6
Growth Rate:
75.00%
Total runs:
8
Run Growth:
8
Growth Rate:
100.00%
Total runs:
6
Run Growth:
-4
Growth Rate:
-66.67%
Total runs:
6
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4
Run Growth:
3
Growth Rate:
75.00%
Total runs:
4
Run Growth:
3
Growth Rate:
75.00%
Total runs:
4
Run Growth:
2
Growth Rate:
50.00%
Total runs:
4
Run Growth:
3
Growth Rate:
75.00%
Total runs:
4
Run Growth:
0
Growth Rate:
0.00%
Total runs:
3
Run Growth:
2
Growth Rate:
66.67%
Total runs:
3
Run Growth:
-27
Growth Rate:
-900.00%
Total runs:
2
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
2
Run Growth:
1
Growth Rate:
50.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
2
Run Growth:
-3
Growth Rate:
-150.00%
Total runs:
1
Run Growth:
1
Growth Rate:
100.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
-5
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%