This folder contains actively maintained examples of use of 🤗 Transformers using the TensorFlow backend, organized along NLP tasks. It is under construction so we thank you for your patience!
Files containing tf such as run_tf_glue.py are the old-style files that will be rewritten very soon! Files without this such as run_text_classification.py are the newer ones. This message will be removed when the revamp is complete.
Here is the list of all our examples:
- with information on whether they are built on top of
Keras(if not, they still work, they might just lack some features), - whether or not they leverage the 🤗 Datasets library.
- links to Colab notebooks to walk through the scripts and run them easily,
| Task | Example datasets | Keras support | 🤗 Datasets | Colab |
|---|---|---|---|---|
language-modeling |
WikiText-2 | - | - | - |
multiple-choice |
SWAG | - | - | - |
question-answering |
SQuAD | - | - | - |
summarization |
XSum | - | - | - |
text-classification |
GLUE | - | - | - |
text-generation |
n/a | - | n/a | - |
token-classification |
CoNLL NER | - | - | - |
translation |
WMT | - | - | - |