Language modeling
Pre-trained models
| Name | License | Size | Date | Training data | Metadata |
|---|---|---|---|---|---|
| AraBERT @ GitHub | License, commercial use ✔️ | BERT-Base architechture | Feb 2020 | ~70M sentences or ~23GB (MSA) | Segmenter |
| Arabic-BERT | MIT | BERT-BASE | Mar 2020 | ~8.2 Billion words ~95GB | |
| hULMonA @ GitHub | undefined | ULMFiT architecture | Aug 2019 | 600,559 Wikipedia articles ~108M words |
More resources coming soon stay tuned ! 🤩 You are welcome to contribute to this project ! 🙏