Total runs:
1.9M
Run Growth:
103.9K
Growth Rate:
5.43%
deepset / minilm-uncased-squad2
Model's Last Updated: September 26 2024
question-answering
Introduction of minilm-uncased-squad2
Model Details of minilm-uncased-squad2
MiniLM-L12-H384-uncased for QA
Overview
Language model:
microsoft/MiniLM-L12-H384-uncased
Language:
English
Downstream-task:
Extractive QA
Training data:
SQuAD 2.0
Eval data:
SQuAD 2.0
Code:
See an
example QA pipeline on Haystack
Infrastructure
: 1x Tesla v100
Hyperparameters
seed=42
batch_size = 12
n_epochs = 4
base_LM_model = "microsoft/MiniLM-L12-H384-uncased"
max_seq_len = 384
learning_rate = 4e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
grad_acc_steps=4
Performance
Evaluated on the SQuAD 2.0 dev set with the official eval script .
"exact": 76.13071675229513,
"f1": 79.49786500219953,
"total": 11873,
"HasAns_exact": 78.35695006747639,
"HasAns_f1": 85.10090269418276,
"HasAns_total": 5928,
"NoAns_exact": 73.91084945332211,
"NoAns_f1": 73.91084945332211,
"NoAns_total": 5945
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/minilm-uncased-squad2")
# or
reader = TransformersReader(model="deepset/minilm-uncased-squad2",tokenizer="deepset/minilm-uncased-squad2")
In Transformers
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/minilm-uncased-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
Vaishali Pal:
[email protected]
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 minilm-uncased-squad2 on huggingface.co
30.5K
Total runs
0
24-hour runs
695
3-day runs
1.8K
7-day runs
221
30-day runs
More Information About minilm-uncased-squad2 huggingface.co Model
Url of minilm-uncased-squad2
minilm-uncased-squad2 huggingface.co Url
Provider of minilm-uncased-squad2 huggingface.co
Other API from deepset
Updated: September 24 2024
Total runs:
222.5K
Run Growth:
10.9K
Growth Rate:
4.90%
Total runs:
152.1K
Run Growth:
-1.2M
Growth Rate:
-795.98%
Total runs:
96.0K
Run Growth:
11.9K
Growth Rate:
12.39%
Total runs:
46.7K
Run Growth:
33.6K
Growth Rate:
71.94%
Total runs:
31.1K
Run Growth:
18.2K
Growth Rate:
58.71%
Total runs:
27.4K
Run Growth:
-74.9K
Growth Rate:
-273.64%
Total runs:
27.4K
Run Growth:
4.8K
Growth Rate:
17.60%
Total runs:
9.3K
Run Growth:
3.8K
Growth Rate:
40.14%
Total runs:
7.8K
Run Growth:
-2.8K
Growth Rate:
-35.77%
Total runs:
5.3K
Run Growth:
1.9K
Growth Rate:
35.35%
Total runs:
5.1K
Run Growth:
-525
Growth Rate:
-10.22%
Total runs:
3.6K
Run Growth:
2.0K
Growth Rate:
53.89%
Total runs:
3.2K
Run Growth:
-2.5K
Growth Rate:
-78.03%
Total runs:
2.0K
Run Growth:
644
Growth Rate:
31.52%
Total runs:
877
Run Growth:
119
Growth Rate:
13.57%
Total runs:
840
Run Growth:
-109
Growth Rate:
-12.98%
Total runs:
590
Run Growth:
-1.5K
Growth Rate:
-248.64%
Total runs:
431
Run Growth:
396
Growth Rate:
91.88%
Total runs:
430
Run Growth:
-395
Growth Rate:
-91.86%
Total runs:
367
Run Growth:
-1.4K
Growth Rate:
-368.94%
Total runs:
309
Run Growth:
-113
Growth Rate:
-36.57%
Total runs:
243
Run Growth:
177
Growth Rate:
72.84%
Total runs:
190
Run Growth:
28
Growth Rate:
14.74%
Total runs:
173
Run Growth:
108
Growth Rate:
62.43%
Total runs:
150
Run Growth:
-28
Growth Rate:
-18.67%
Total runs:
146
Run Growth:
-204
Growth Rate:
-139.73%
Total runs:
135
Run Growth:
117
Growth Rate:
86.67%
Total runs:
133
Run Growth:
98
Growth Rate:
73.68%
Total runs:
121
Run Growth:
58
Growth Rate:
47.93%
Total runs:
112
Run Growth:
-2
Growth Rate:
-1.79%
Total runs:
65
Run Growth:
36
Growth Rate:
55.38%
Total runs:
58
Run Growth:
-102
Growth Rate:
-175.86%
Total runs:
56
Run Growth:
23
Growth Rate:
41.07%
Total runs:
48
Run Growth:
32
Growth Rate:
66.67%
Total runs:
32
Run Growth:
14
Growth Rate:
43.75%
Total runs:
21
Run Growth:
-40
Growth Rate:
-190.48%
Total runs:
21
Run Growth:
-100
Growth Rate:
-476.19%
Total runs:
21
Run Growth:
-91
Growth Rate:
-433.33%
Total runs:
19
Run Growth:
6
Growth Rate:
31.58%
Total runs:
19
Run Growth:
-55
Growth Rate:
-289.47%
Total runs:
18
Run Growth:
-12
Growth Rate:
-66.67%
Total runs:
5
Run Growth:
-188
Growth Rate:
-3760.00%