Name: bert base cased squad2
Author: deepset

Overview

BERT-base-cased-SQuAD2 is a transformer-based encoder specifically fine-tuned for extractive question answering. Unlike standard BERT, this version is trained on the SQuAD 2.0 dataset, meaning it can distinguish between answerable questions and those where the answer is missing from the provided context—a critical feature for reducing hallucinations in production RAG pipelines. It processes cased text, making it more effective for tasks where proper nouns and capitalization are key to entity recognition. For developers, this model serves as a reliable, lightweight baseline for building knowledge-base bots or document search tools where precise span extraction is required over generative synthesis.

Highlights

Optimized for extractive question answering tasks
Handles unanswerable questions to reduce hallucinations
Case-sensitive processing for improved entity recognition
Efficient baseline for RAG-based retrieval systems
Open-source CC-BY-4.0 licensing for flexible deployment

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("deepset/bert-base-cased-squad2")
tokenizer = AutoTokenizer.from_pretrained("deepset/bert-base-cased-squad2")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download deepset/bert-base-cased-squad2

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download deepset/bert-base-cased-squad2 config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('deepset/bert-base-cased-squad2')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/deepset/bert-base-cased-squad2

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/deepset/bert-base-cased-squad2

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('deepset/bert-base-cased-squad2')
tokenizer = AutoTokenizer.from_pretrained('deepset/bert-base-cased-squad2')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model deepset/bert-base-cased-squad2

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model deepset/bert-base-cased-squad2 README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('deepset/bert-base-cased-squad2')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/deepset/bert-base-cased-squad2.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/deepset/bert-base-cased-squad2.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'deepset/bert-base-cased-squad2')

Full Documentation

来源: HuggingFace

---
language: en
license: cc-by-4.0
datasets:

squad_v2

model-index:

name: deepset/bert-base-cased-squad2

results:
- task:
type: question-answering
name: Question Answering
dataset:
name: squad_v2
type: squad_v2
config: squad_v2
split: validation
metrics:
- type: exact_match
value: 71.1517
name: Exact Match
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGZlNmQ1YzIzMWUzNTg4YmI4NWVhYThiMzE2ZGZmNWUzNDM3NWI0ZGJkNzliNGUxNTY2MDA5MWVkYjAwYWZiMCIsInZlcnNpb24iOjF9.iUvVdy5c4hoXkwlThJankQqG9QXzNilvfF1_4P0oL8X-jkY5Q6YSsZx6G6cpgXogqFpn7JlE_lP6_OT0VIamCg
- type: f1
value: 74.6714
name: F1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWE5OGNjODhmY2Y0NWIyZDIzMmQ2NmRjZGYyYTYzOWMxZDUzYzg4YjBhNTRiNTY4NTc0M2IxNjI5NWI5ZDM0NCIsInZlcnNpb24iOjF9.IqU9rbzUcKmDEoLkwCUZTKSH0ZFhtqgnhOaEDKKnaRMGBJLj98D5V4VirYT6jLh8FlR0FiwvMTMjReBcfTisAQ
---

This is a BERT base cased model trained on SQuAD v2

Overview

Language model: bert-base-cased 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

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/bert-base-cased-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/bert-base-cased-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)

About us

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

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

<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!