---
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/tinybert-6l-768d-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: 73.8248
name: Exact Match
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGFmZmFiN2E5ODZkOTkyMjQ1NTUzMmQwMjc0M2RlYzVlNmM4YTFlNzA4YzIwY2JkY2EyNDg2ZTY3OTdjZTVlZiIsInZlcnNpb24iOjF9.ZZ6c2OI3lzeNhuSWTh28j00zk-sPrqkTvdVBZv2wJc1D4YnR-xOj72haybT6MV_xeYqTg3-x9L8PsWSS20NaDw
- type: f1
value: 77.1684
name: F1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzAxMDk1YzI5ZjA2N2ZmMzAxNjgxYzJiNzAzYmI1ZWU5ZDRmYWY3OWJmMjlmNDcyMGE0YWY5NjNhZTk4YWY5ZSIsInZlcnNpb24iOjF9.rF3raNGUSYv5D2xzWLZztD99vwDKvWb22LG32RomrDGP6XKTbCVqZzAw5UFw93jKb0VoLApbQQ-AOGxLj3U_Cg
---
# tinybert for Extractive QA
## Overview
**Language model:** deepset/tinybert-6L-768D-squad2
**Language:** English
**Training data:** SQuAD 2.0 training set x 20 augmented + SQuAD 2.0 training set without augmentation
**Eval data:** SQuAD 2.0 dev set
**Code:** See [an example extractive QA pipeline built with Haystack](https://haystack.deepset.ai/tutorials/34_extractive_qa_pipeline)
**Infrastructure**: 1x V100 GPU
**Published**: Dec 8th, 2021
## Details
- Haystack's intermediate layer and prediction layer distillation features were used for training (based on [TinyBERT](https://arxiv.org/pdf/1909.10351.pdf)). deepset/bert-base-uncased-squad2 was used as the teacher model and huawei-noah/TinyBERT_General_6L_768D was used as the student model.
## Hyperparameters
### Intermediate layer distillation
```
batch_size = 26
n_epochs = 5
max_seq_len = 384
learning_rate = 5e-5
lr_schedule = LinearWarmup
embeds_dropout_prob = 0.1
temperature = 1
```
### Prediction layer distillation
```
batch_size = 26
n_epochs = 5
max_seq_len = 384
learning_rate = 3e-5
lr_schedule = LinearWarmup
embeds_dropout_prob = 0.1
temperature = 1
distillation_loss_weight = 1.0
```
## 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](https://github.com/deepset-ai/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/tinybert-6l-768d-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](https://haystack.deepset.ai/tutorials/34_extractive_qa_pipeline).
### In Transformers
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
model_name = "deepset/tinybert-6l-768d-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
```
"exact": 71.87736882001179
"f1": 76.36111895973675
```
## 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](http://deepset.ai/) is the company behind the production-ready open-source AI framework [Haystack](https://haystack.deepset.ai/).
Some of our other work:
- [Distilled roberta-base-squad2 (aka "tinyroberta-squad2")](https://huggingface.co/deepset/tinyroberta-squad2)
- [German BERT](https://deepset.ai/german-bert), [GermanQuAD and GermanDPR](https://deepset.ai/germanquad), [German embedding model](https://huggingface.co/mixedbread-ai/deepset-mxbai-embed-de-large-v1)
- [deepset Cloud](https://www.deepset.ai/deepset-cloud-product), [deepset Studio](https://www.deepset.ai/deepset-studio)
## 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](https://twitter.com/Haystack_AI) | [LinkedIn](https://www.linkedin.com/company/deepset-ai/) | [Discord](https://haystack.deepset.ai/community) | [GitHub Discussions](https://github.com/deepset-ai/haystack/discussions) | [Website](https://haystack.deepset.ai/) | [YouTube](https://www.youtube.com/@deepset_ai)
By the way: [we're hiring!](http://www.deepset.ai/jobs) 
