facebookresearch / XLM

PyTorch original implementation of Cross-lingual Language Model Pretraining.
Other
2.87k stars 495 forks source link

Training data details for XLM-15 model #345

Open somani-iitb opened 2 years ago

somani-iitb commented 2 years ago

Hii,

Thanks for sharing the repo with all the details. I was trying to use xlm-15 model for MLM fine-tuning and downstream tasks and need to know the training data using in the MLM fine-tuning stage.

The repo list the languages used but a reference to the data source would be helpful. Thanks.

somani-iitb commented 2 years ago

Following up on the above.