Closed cbalkig closed 4 years ago
Hi @balki7 ,
thanks for your interest 🤗
I did document the training commands in this cheatsheet.
But if you just want to fine-tune the language model, I think you can also use the Transformers library. More precisely, you could use the steps documented here:
https://github.com/huggingface/transformers/tree/master/examples#language-model-training
:)
Thanx Stefan again and again. My MS Thesis is related to BERT in Turkish. If it is OK for you, I'll point your project also. :)
Hi @balki7 ,
sure, that would be awesome :)
Just a few upcoming news: uncased BERT model is coming soon. And I've trained cased and uncased models with a larger vocab size (128k instead of 32k). Only evaluation is missing.
Stefan,
Is it possible to share the commands that you've used for generating the model? I'll add some domain specific data to the model and for retraining I need you commands.
Thanx a lot.