Modelpublic

deepset/deberta-v3-large-squad2

sourceHugging Facecc-by-4.0updated 2y agoView on Hugging Face

52likes7.3kdownloads

Model Card

deberta-v3-large for Extractive QA

This is the deberta-v3-large model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Extractive Question Answering.

Overview

Language model: deberta-v3-large Language: English Downstream-task: Extractive QA Training data: SQuAD 2.0 Eval data: SQuAD 2.0 Code: See an example extractive QA pipeline built with Haystack Infrastructure: 1x NVIDIA A10G

Hyperparameters

batch_size = 2
grad_acc_steps = 32
n_epochs = 6
base_LM_model = "microsoft/deberta-v3-large"
max_seq_len = 512
learning_rate = 7e-6
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64

Usage

In Haystack

Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack:

python

# After running pip install haystack-ai "transformers[torch,sentencepiece]"

from haystack import Document
from haystack.components.readers import ExtractiveReader

docs = [
    Document(content="Python is a popular programming language"),
    Document(content="python ist eine beliebte Programmiersprache"),
]

reader = ExtractiveReader(model="deepset/deberta-v3-large-squad2")
reader.warm_up()

question = "What is a popular programming language?"
result = reader.run(query=question, documents=docs)
# {'answers': [ExtractedAnswer(query='What is a popular programming language?', score=0.5740374326705933, data='python', document=Document(id=..., content: '...'), context=None, document_offset=ExtractedAnswer.Span(start=0, end=6),...)]}

For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial.

In Transformers

python

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/deberta-v3-large-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)

Performance

Evaluated on the SQuAD 2.0 dev set with the official eval script.

"exact": 87.6105449338836,
"f1": 90.75307008866517,

"total": 11873,
"HasAns_exact": 84.37921727395411,
"HasAns_f1": 90.6732795483674,
"HasAns_total": 5928,
"NoAns_exact": 90.83263246425568,
"NoAns_f1": 90.83263246425568,
"NoAns_total": 5945

About us

deepset is the company behind the production-ready open-source AI framework Haystack.

Some of our other work:

Get in touch and join the Haystack community

<p>For more info on Haystack, visit our <strong><a href="https://github.com/deepset-ai/haystack">GitHub</a></strong> repo and <strong><a href="https://docs.haystack.deepset.ai">Documentation</a></strong>.

We also have a <strong><a class="h-7" href="https://haystack.deepset.ai/community">Discord community open to everyone!</a></strong></p>

By the way: we're hiring!