transformer-models icon indicating copy to clipboard operation
transformer-models copied to clipboard

Deep Learning Transformer models in MATLAB

Results 12 transformer-models issues
Sort by recently updated
recently updated
newest added

when i try to run mdl = bert It stays an infinite time running. When I open the file that it creates on the computer "Parameters" it cannot be opened

bug

How can I train a BERT model from scratch?

enhancement
question

I have opened this issue so that everyone can post which example they would like to use.

documentation
enhancement

We would like to use these issues to gauge user interest. It is possible to use the GPT-2 implementation for further language model training. There is no example demonstrating this...

enhancement

See [CircleCI](https://app.circleci.com/pipelines/github/matlab-deep-learning/transformer-models/43/workflows/6d79f2e1-d34c-45f0-9dec-4fe59b62a955/jobs/42) We can update the error ID we're testing against, or add extra validation for `bert.model`.

test_bug

We would like to use these issues to gauge user interest. The BERT tokenizer is intended as an identical reimplementation of the original BERT tokenization. However it is possible to...

enhancement

In addition to the NLP applications, what about the CV applications? Are there any examples of transformer being used for "object detection", "behaviour recognition" or even "image classification"? It would...

enhancement
question

We would like to use these issues to gauge user interest. The GPT-2 implementation does not include dropout layers. This would be useful for further pre-training and fine-tuning workflows to...

enhancement

We would like to use these issues to gauge user interest. Sparse cross entropy allows the computation of cross entropy loss without one-hot encoding of the target class. This is...

enhancement