This repository now contains code and implementation for:
- AraBERT v0.1/v1: Original
- AraBERT v0.2/v2: Base and large versions with better vocabulary, more data, more training, Read More..
- AraGPT2: base, medium, large and MEGA. Trained from scratch on Arabic, Read More..
- AraELECTRA: Trained from scratch on Arabic Read More..
If you want to clone the old repository:
git clone https://github.com/aub-mind/arabert/
cd arabert && git checkout 6a58ca118911ef311cbe8cdcdcc1d03601123291AraBERT now comes in 4 new variants to replace the old v1 versions:
More Detail in the AraBERT folder and in the README and in the AraBERT Paper
| Model | HuggingFace Model Name | Size (MB/Params) | Pre-Segmentation | DataSet (Sentences/Size/nWords) |
|---|---|---|---|---|
| AraBERTv0.2-base | bert-base-arabertv02 | 543MB / 136M | No | 200M / 77GB / 8.6B |
| AraBERTv0.2-large | bert-large-arabertv02 | 1.38G / 371M | No | 200M / 77GB / 8.6B |
| AraBERTv2-base | bert-base-arabertv2 | 543MB / 136M | Yes | 200M / 77GB / 8.6B |
| AraBERTv2-large | bert-large-arabertv2 | 1.38G / 371M | Yes | 200M / 77GB / 8.6B |
| AraBERTv0.1-base | bert-base-arabertv01 | 543MB / 136M | No | 77M / 23GB / 2.7B |
| AraBERTv1-base | bert-base-arabert | 543MB / 136M | Yes | 77M / 23GB / 2.7B |
All models are available in the HuggingFace model page under the aubmindlab name. Checkpoints are available in PyTorch, TF2 and TF1 formats.
We identified an issue with AraBERTv1's wordpiece vocabulary. The issue came from punctuations and numbers that were still attached to words when learned the wordpiece vocab. We now insert a space between numbers and characters and around punctuation characters.
The new vocabulary was learnt using the BertWordpieceTokenizer from the tokenizers library, and should now support the Fast tokenizer implementation from the transformers library.
P.S.: All the old BERT codes should work with the new BERT, just change the model name and check the new preprocessing function
Please read the section on how to use the preprocessing function
We used ~3.5 times more data, and trained for longer. For Dataset Sources see the Dataset Section
| Model | Hardware | num of examples with seq len (128 / 512) | 128 (Batch Size/ Num of Steps) | 512 (Batch Size/ Num of Steps) | Total Steps | Total Time (in Days) |
|---|---|---|---|---|---|---|
| AraBERTv0.2-base | TPUv3-8 | 420M / 207M | 2560 / 1M | 384/ 2M | 3M | 36 |
| AraBERTv0.2-large | TPUv3-128 | 420M / 207M | 13440 / 250K | 2056 / 300K | 550K | 7 |
| AraBERTv2-base | TPUv3-8 | 420M / 207M | 2560 / 1M | 384/ 2M | 3M | 36 |
| AraBERTv2-large | TPUv3-128 | 520M / 245M | 13440 / 250K | 2056 / 300K | 550K | 7 |
| AraBERT-base (v1/v0.1) | TPUv2-8 | - | 512 / 900K | 128 / 300K | 1.2M | 4 |
More details and code are available in the AraGPT2 folder and README
| Model | HuggingFace Model Name | Size / Params |
|---|---|---|
| AraGPT2-base | aragpt2-base | 527MB/135M |
| AraGPT2-medium | aragpt2-medium | 1.38G/370M |
| AraGPT2-large | aragpt2-large | 2.98GB/792M |
| AraGPT2-mega | aragpt2-mega | 5.5GB/1.46B |
All models are available in the HuggingFace model page under the aubmindlab name. Checkpoints are available in PyTorch, TF2 and TF1 formats.
For Dataset Source see the Dataset Section
| Model | Hardware | num of examples (seq len = 1024) | Batch Size | Num of Steps | Time (in days) |
|---|---|---|---|---|---|
| AraGPT2-base | TPUv3-128 | 9.7M | 1792 | 125K | 1.5 |
| AraGPT2-medium | TPUv3-128 | 9.7M | 1152 | 85K | 1.5 |
| AraGPT2-large | TPUv3-128 | 9.7M | 256 | 220k | 3 |
| AraGPT2-mega | TPUv3-128 | 9.7M | 256 | 800K | 9 |
More details and code are available in the AraELECTRA folder and README
| Model | HuggingFace Model Name | Size (MB/Params) |
|---|---|---|
| AraELECTRA-base-generator | araelectra-base-generator | 227MB/60M |
| AraELECTRA-base-discriminator | araelectra-base-discriminator | 516MB/135M |
| Model | Hardware | num of examples (seq len = 512) | Batch Size | Num of Steps | Time (in days) |
|---|---|---|---|---|---|
| ELECTRA-base | TPUv3-8 | - | 256 | 2M | 24 |
The pretraining data used for the new AraBERT model is also used for AraGPT2 and AraELECTRA.
The dataset consists of 77GB or 200,095,961 lines or 8,655,948,860 words or 82,232,988,358 chars (before applying Farasa Segmentation)
For the new dataset we added the unshuffled OSCAR corpus, after we thoroughly filter it, to the previous dataset used in AraBERTv1 but with out the websites that we previously crawled:
- OSCAR unshuffled and filtered.
- Arabic Wikipedia dump from 2020/09/01
- The 1.5B words Arabic Corpus
- The OSIAN Corpus
- Assafir news articles. Huge thank you for Assafir for giving us the data
It is recommended to apply our preprocessing function before training/testing on any dataset.
Install farasapy to segment text for AraBERT v1 & v2 pip install farasapy
from arabert.preprocess import ArabertPreprocessor
model_name = "bert-base-arabertv2"
arabert_prep = ArabertPreprocessor(model_name=model_name, keep_emojis=False)
text = "ولن نبالغ إذا قلنا إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري"
arabert_prep.preprocess(text)
>>>"و+ لن نبالغ إذا قل +نا إن هاتف أو كمبيوتر ال+ مكتب في زمن +نا هذا ضروري"bert-base-arabertv01
bert-base-arabert
bert-base-arabertv02
bert-base-arabertv2
bert-large-arabertv02
bert-large-arabertv2
araelectra-base
araelectra-base-discriminator
araelectra-base-generator
aragpt2-base
aragpt2-medium
aragpt2-large
aragpt2-mega
- You can find the old examples that work with AraBERTv1 in the
examples/oldfolder - Check the Readme.md file in the examples folder for new links to colab notebooks
The TF1.x model are available in the HuggingFace models repo. You can download them as follows:
- via git-lfs: clone all the models in a repo
curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash
sudo apt-get install git-lfs
git lfs install
git clone https://huggingface.co/aubmindlab/MODEL_NAME
tar -C ./MODEL_NAME -zxvf /content/MODEL_NAME/tf1_model.tar.gzwhere MODEL_NAME is any model under the aubmindlab name
- via
wget:- Go to the tf1_model.tar.gz file on huggingface.co/models/aubmindlab/MODEL_NAME.
- copy the
oid sha256 - then run
wget https://cdn-lfs.huggingface.co/aubmindlab/aragpt2-base/INSERT_THE_SHA_HERE(ex: foraragpt2-base:wget https://cdn-lfs.huggingface.co/aubmindlab/aragpt2-base/3766fc03d7c2593ff2fb991d275e96b81b0ecb2098b71ff315611d052ce65248)
Google Scholar has our Bibtex wrong (missing name), use this instead
@inproceedings{antoun2020arabert,
title={AraBERT: Transformer-based Model for Arabic Language Understanding},
author={Antoun, Wissam and Baly, Fady and Hajj, Hazem},
booktitle={LREC 2020 Workshop Language Resources and Evaluation Conference 11--16 May 2020},
pages={9}
}
@misc{antoun2020aragpt2,
title={AraGPT2: Pre-Trained Transformer for Arabic Language Generation},
author={Wissam Antoun and Fady Baly and Hazem Hajj},
year={2020},
eprint={2012.15520},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@misc{antoun2020araelectra,
title={AraELECTRA: Pre-Training Text Discriminators for Arabic Language Understanding},
author={Wissam Antoun and Fady Baly and Hazem Hajj},
year={2020},
eprint={2012.15516},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Thanks to TensorFlow Research Cloud (TFRC) for the free access to Cloud TPUs, couldn't have done it without this program, and to the AUB MIND Lab Members for the continous support. Also thanks to Yakshof and Assafir for data and storage access. Another thanks for Habib Rahal (https://www.behance.net/rahalhabib), for putting a face to AraBERT.
Wissam Antoun: Linkedin | Twitter | Github | [email protected] | [email protected]
Fady Baly: Linkedin | Twitter | Github | [email protected] | [email protected]