Total runs:
1.9M
Run Growth:
98.8K
Growth Rate:
5.17%
deepset / deberta-v3-base-squad2
Model's Last Updated: September 24 2024
question-answering
Introduction of deberta-v3-base-squad2
Model Details of deberta-v3-base-squad2
deberta-v3-base for QA
This is the deberta-v3-base model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering.
Overview
Language model:
deberta-v3-base
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 NVIDIA A10G
Hyperparameters
batch_size = 12
n_epochs = 4
base_LM_model = "deberta-v3-base"
max_seq_len = 512
learning_rate = 2e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride = 128
max_query_length = 64
Usage
In Haystack
Haystack is an NLP framework by deepset. You can use this model in a Haystack pipeline to do question answering at scale (over many documents). To load the model in Haystack :
reader = FARMReader(model_name_or_path="deepset/deberta-v3-base-squad2")
# or
reader = TransformersReader(model_name_or_path="deepset/deberta-v3-base-squad2",tokenizer="deepset/deberta-v3-base-squad2")
In Transformers
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/deberta-v3-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)
Authors
Sebastian Lee:
sebastian.lee [at] deepset.ai
Timo Möller:
timo.moeller [at] deepset.ai
Malte Pietsch:
malte.pietsch [at] deepset.ai
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
Runs of deepset deberta-v3-base-squad2 on huggingface.co
3.2K
Total runs
-3
24-hour runs
22
3-day runs
-15
7-day runs
-2.5K
30-day runs
More Information About deberta-v3-base-squad2 huggingface.co Model
Url of deberta-v3-base-squad2
deberta-v3-base-squad2 huggingface.co Url
Provider of deberta-v3-base-squad2 huggingface.co
Other API from deepset
Updated: September 24 2024
Total runs:
222.4K
Run Growth:
11.0K
Growth Rate:
4.96%
Total runs:
98.6K
Run Growth:
14.3K
Growth Rate:
14.52%
Total runs:
67.3K
Run Growth:
-1.3M
Growth Rate:
-1140.74%
Total runs:
47.9K
Run Growth:
33.9K
Growth Rate:
70.82%
Total runs:
34.2K
Run Growth:
2.8K
Growth Rate:
8.26%
Total runs:
34.2K
Run Growth:
19.8K
Growth Rate:
60.63%
Total runs:
28.1K
Run Growth:
-74.3K
Growth Rate:
-264.54%
Total runs:
27.4K
Run Growth:
4.5K
Growth Rate:
16.35%
Total runs:
9.7K
Run Growth:
4.0K
Growth Rate:
41.87%
Total runs:
8.5K
Run Growth:
-2.0K
Growth Rate:
-23.50%
Total runs:
5.3K
Run Growth:
1.9K
Growth Rate:
35.67%
Total runs:
5.2K
Run Growth:
-468
Growth Rate:
-8.99%
Total runs:
3.6K
Run Growth:
1.9K
Growth Rate:
53.93%
Total runs:
1.9K
Run Growth:
474
Growth Rate:
24.55%
Total runs:
896
Run Growth:
-25
Growth Rate:
-2.88%
Total runs:
881
Run Growth:
116
Growth Rate:
13.17%
Total runs:
602
Run Growth:
-1.5K
Growth Rate:
-241.69%
Total runs:
429
Run Growth:
394
Growth Rate:
91.84%
Total runs:
418
Run Growth:
-407
Growth Rate:
-97.37%
Total runs:
413
Run Growth:
-31
Growth Rate:
-7.51%
Total runs:
379
Run Growth:
-1.3K
Growth Rate:
-353.03%
Total runs:
316
Run Growth:
-106
Growth Rate:
-33.54%
Total runs:
231
Run Growth:
154
Growth Rate:
67.25%
Total runs:
196
Run Growth:
133
Growth Rate:
67.86%
Total runs:
186
Run Growth:
24
Growth Rate:
12.90%
Total runs:
179
Run Growth:
115
Growth Rate:
64.25%
Total runs:
146
Run Growth:
-196
Growth Rate:
-134.25%
Total runs:
131
Run Growth:
95
Growth Rate:
72.52%
Total runs:
131
Run Growth:
113
Growth Rate:
84.96%
Total runs:
120
Run Growth:
-70
Growth Rate:
-58.33%
Total runs:
112
Run Growth:
-2
Growth Rate:
-1.79%
Total runs:
63
Run Growth:
37
Growth Rate:
58.73%
Total runs:
56
Run Growth:
-87
Growth Rate:
-155.36%
Total runs:
54
Run Growth:
21
Growth Rate:
38.89%
Total runs:
48
Run Growth:
32
Growth Rate:
66.67%
Total runs:
29
Run Growth:
12
Growth Rate:
40.00%
Total runs:
21
Run Growth:
-100
Growth Rate:
-476.19%
Total runs:
21
Run Growth:
-91
Growth Rate:
-433.33%
Total runs:
20
Run Growth:
-40
Growth Rate:
-200.00%
Total runs:
19
Run Growth:
6
Growth Rate:
31.58%
Total runs:
19
Run Growth:
-55
Growth Rate:
-289.47%
Total runs:
17
Run Growth:
-12
Growth Rate:
-70.59%
Total runs:
5
Run Growth:
-188
Growth Rate:
-3760.00%