Update README.md

README.md

@@ -10,7 +10,7 @@ tags:
 # CuBERT: Learning and Evaluating Contextual Embedding of Source Code
 
 ## Overview
-This model is the unofficial HuggingFace version of "[CuBERT](https://github.com/google-research/google-research/tree/master/cubert)". In particular, this version comes from [gs://cubert/20210711_Python/pre_trained_model_epochs_2__length_512](https://console.cloud.google.com/storage/browser/cubert/20210711_Python/pre_trained_model_epochs_2__length_512). It was trained 2021-07-11 for 2 epochs with a 512 token context window on the Python BigQuery dataset. I manually converted the Tensorflow checkpoint to PyTorch, the tokenizer to a HuggingFace tokenizer, and have uploaded them here. All credit goes to Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, and Kensen Shi.
+This model is the unofficial HuggingFace version of "[CuBERT](https://github.com/google-research/google-research/tree/master/cubert)". In particular, this version comes from [gs://cubert/20210711_Python/pre_trained_model_epochs_2__length_512](https://console.cloud.google.com/storage/browser/cubert/20210711_Python/pre_trained_model_epochs_2__length_512). It was trained 2021-07-11 for 2 epochs with a 512 token context window on the Python BigQuery dataset. I manually converted the Tensorflow checkpoint to PyTorch and have uploaded it here. The [tokenizer](https://github.com/google-research/google-research/blob/master/cubert/python_tokenizer.py) has not been converted yet. All credit goes to Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, and Kensen Shi.
 
 Citation:
 ```bibtex