Name: bert medium squad2 distilled
Author: deepset

Overview

The bert-medium-squad2-distilled model is a streamlined version of BERT optimized specifically for extractive question answering. By leveraging knowledge distillation from a larger teacher model and training on the SQuAD 2.0 dataset, it maintains high accuracy in identifying answer spans within a given context while significantly reducing latency and memory overhead. This makes it an ideal choice for developers building RAG pipelines or FAQ bots where inference speed is critical and deployment environments have limited hardware resources. It integrates seamlessly with the Hugging Face Transformers library, offering a pragmatic balance between the performance of BERT-large and the efficiency required for real-time production APIs.

Highlights

Optimized for fast extractive question answering tasks
Reduced latency via knowledge distillation process
Trained on SQuAD 2.0 for better noise handling
Low memory footprint for efficient production deployment
Full compatibility with Hugging Face Transformers ecosystem

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-medium-squad2-distilled")
tokenizer = AutoTokenizer.from_pretrained("deepset/bert-medium-squad2-distilled")

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-medium-squad2-distilled

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

huggingface-cli download deepset/bert-medium-squad2-distilled 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-medium-squad2-distilled')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/deepset/bert-medium-squad2-distilled

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/deepset/bert-medium-squad2-distilled

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-medium-squad2-distilled')
tokenizer = AutoTokenizer.from_pretrained('deepset/bert-medium-squad2-distilled')

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-medium-squad2-distilled

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

modelscope download --model deepset/bert-medium-squad2-distilled 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-medium-squad2-distilled')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/deepset/bert-medium-squad2-distilled.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/deepset/bert-medium-squad2-distilled.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-medium-squad2-distilled')

Full Documentation

来源: HuggingFace

---
language: en
license: mit
tags:

exbert

datasets:

squad_v2

thumbnail: https://thumb.tildacdn.com/tild3433-3637-4830-a533-353833613061/-/resize/720x/-/format/webp/germanquad.jpg
model-index:

name: deepset/bert-medium-squad2-distilled

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: 69.8231
name: Exact Match
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmE4MGRkZTVjNmViMGNjYjVhY2E1NzcyOGQ1OWE1MWMzMjY5NWU0MmU0Y2I4OWU4YTU5OWQ5YTI2NWE1NmM0ZSIsInZlcnNpb24iOjF9.tnCJvWzMctTwiQu5yig_owO2ZI1t1MZz1AN2lQy4COAGOzuMovD-74acQvMbxJQoRfNNkIetz2hqYivf1lJKDw
- type: f1
value: 72.9232
name: F1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTMwNzk0ZDRjNGUyMjQyNzc1NzczZmUwMTU2MTM5MGQ3M2NhODlmOTU4ZDI0YjhlNTVjNDA1MGEwM2M1MzIyZSIsInZlcnNpb24iOjF9.eElGmTOXH_qHTNaPwZ-dUJfVz9VMvCutDCof_6UG_625MwctT_j7iVkWcGwed4tUnunuq1BPm-0iRh1RuuB-AQ
---

bert-medium-squad2-distilled for Extractive QA

Overview

Language model: deepset/roberta-base-squad2-distilled Language: English Training data: SQuAD 2.0 training set Eval data: SQuAD 2.0 dev set Infrastructure: 1x V100 GPU Published: Apr 21st, 2021

Details

Haystack version 1.x distillation feature was used for training. deepset/bert-large-uncased-whole-word-masking-squad2 was used as the teacher model.

Hyperparameters

code

batch_size = 6
n_epochs = 2
max_seq_len = 384
learning_rate = 3e-5
lr_schedule = LinearWarmup
embeds_dropout_prob = 0.1
temperature = 5
distillation_loss_weight = 1

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-medium-squad2-distilled")
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-medium-squad2-distilled"
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

code

"exact": 68.6431398972458
"f1": 72.7637083790805

Authors

Timo Möller: timo.moeller [at] deepset.ai

Julian Risch: julian.risch [at] deepset.ai

Malte Pietsch: malte.pietsch [at] deepset.ai

Michel Bartels: michel.bartels [at] deepset.ai

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, GermanQuAD and GermanDPR, German embedding model

deepset Cloud, deepset Studio

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!