🤗 + 📚 dbmdz Distilled Turkish BERT model
In this repository the MDZ Digital Library team (dbmdz) at the Bavarian State Library open sources a (cased) distilled model for Turkish 🎉
DistilBERTurk is a community-driven cased distilled BERT model for Turkish.
DistilBERTurk was trained on 7GB of the original training data that was used for training BERTurk, using the cased version of BERTurk as teacher model.
DistilBERTurk was trained with the official Hugging Face implementation from here for 5 days on 4 RTX 2080 TI.
More details about distillation can be found in the "DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter" paper by Sanh et al. (2019).
With Transformers >= 2.3 our DistilBERTurk model can be loaded like:
from transformers import AutoModel, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("dbmdz/distilbert-base-turkish-cased") model = AutoModel.from_pretrained("dbmdz/distilbert-base-turkish-cased")
For results on PoS tagging or NER tasks, please refer to this repository.
For PoS tagging, DistilBERTurk outperforms the 24-layer XLM-RoBERTa model.
The overall performance difference between DistilBERTurk and the original (teacher) BERTurk model is ~1.18%.
Huggingface model hub
All models are available on the Huggingface model hub.
Contact (Bugs, Feedback, Contribution and more)
For questions about our BERT models just open an issue here 🤗
Thanks to Kemal Oflazer for providing us additional large corpora for Turkish. Many thanks to Reyyan Yeniterzi for providing us the Turkish NER dataset for evaluation.
Research supported with Cloud TPUs from Google's TensorFlow Research Cloud (TFRC). Thanks for providing access to the TFRC ❤️
Thanks to the generous support from the Hugging Face team, it is possible to download both cased and uncased models from their S3 storage 🤗
- Downloads last month
Unable to determine this model’s pipeline type. Check the docs .