deepset / minilm-uncased-squad2

huggingface.co
Total runs: 35.6K
24-hour runs: 0
7-day runs: 5.6K
30-day runs: 7.8K
Model's Last Updated: 9月 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: vaishali.pal@deepset.ai
Branden Chan: branden.chan@deepset.ai
Timo Möller: timo.moeller@deepset.ai
Malte Pietsch: malte.pietsch@deepset.ai
Tanay Soni: tanay.soni@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:

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

35.6K
Total runs
0
24-hour runs
5.3K
3-day runs
5.6K
7-day runs
7.8K
30-day runs

More Information About minilm-uncased-squad2 huggingface.co Model

More minilm-uncased-squad2 license Visit here:

https://choosealicense.com/licenses/cc-by-4.0

minilm-uncased-squad2 huggingface.co

minilm-uncased-squad2 huggingface.co is an AI model on huggingface.co that provides minilm-uncased-squad2's model effect (), which can be used instantly with this deepset minilm-uncased-squad2 model. huggingface.co supports a free trial of the minilm-uncased-squad2 model, and also provides paid use of the minilm-uncased-squad2. Support call minilm-uncased-squad2 model through api, including Node.js, Python, http.

minilm-uncased-squad2 huggingface.co Url

https://huggingface.co/deepset/minilm-uncased-squad2

deepset minilm-uncased-squad2 online free

minilm-uncased-squad2 huggingface.co is an online trial and call api platform, which integrates minilm-uncased-squad2's modeling effects, including api services, and provides a free online trial of minilm-uncased-squad2, you can try minilm-uncased-squad2 online for free by clicking the link below.

deepset minilm-uncased-squad2 online free url in huggingface.co:

https://huggingface.co/deepset/minilm-uncased-squad2

minilm-uncased-squad2 install

minilm-uncased-squad2 is an open source model from GitHub that offers a free installation service, and any user can find minilm-uncased-squad2 on GitHub to install. At the same time, huggingface.co provides the effect of minilm-uncased-squad2 install, users can directly use minilm-uncased-squad2 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

minilm-uncased-squad2 install url in huggingface.co:

https://huggingface.co/deepset/minilm-uncased-squad2

Url of minilm-uncased-squad2

minilm-uncased-squad2 huggingface.co Url

Provider of minilm-uncased-squad2 huggingface.co

deepset
ORGANIZATIONS

Other API from deepset

huggingface.co

Total runs: 50.8K
Run Growth: 36.9K
Growth Rate: 72.72%
Updated: 9月 26 2024
huggingface.co

Total runs: 27.6K
Run Growth: 4.5K
Growth Rate: 16.49%
Updated: 9月 26 2024
huggingface.co

Total runs: 11.7K
Run Growth: 6.3K
Growth Rate: 53.10%
Updated: 5月 19 2021