The transfromer model architecture is in the model.py
file. The dataset file contains the data loader to train the transfromer and the train.py
is the code used to train it. We trained the model on a translation task using opus_books
dataset from Hugging Face.
You can choose many languages to train the model on, you just have to edit the config file with the src and target language.
-
Notifications
You must be signed in to change notification settings - Fork 0
MekkCyber/Transformer_scratch
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published