List of legal arch parameters

Part 1 (2019)
1

Hello!

I wasn’t able to find a list of legal parameters for ‘arch’ , or stated differently a list of available models in fastai, or list of available models in fastai.

I am especially interested in arch’s for text_classifier_learner I’m doing a binary classification problem for where the inputs are 8000 integers.

2

Hi @JakobV,

You can find the list of available models here : https://fastai1.fast.ai/text.learner.html

The model used is given by arch and config. It can be:

Those are the same for the text_classifier_learner :

Blockquote
Here again, the backbone of the model is determined by arch and config

For the classifier, only the last layer is modified. The architecture remains the same.

Best,
Charles

3

Note that that is only applicable to fastai v1. In v2 the Transformer and TransformerXL are not a thing anymore that can be used by text_learner. We just have an AWD-LSTM and QRNN

4

Ah yes, my bad. Thanks for the correction ! :slight_smile:

5

Thank you very much your your answers!
So I guess if I want to implement a transformer I will have to dive a a bit deeper down to the mid-levels and follow this guide https://docs.fast.ai/tutorial.transformers

1 Like