where is the trained model parameters ?
fsalmasri opened this issue · 1 comments
fsalmasri commented
Is it possible to have the trained model params ?
bentrevett commented
For NLP models you can't just save the parameters, you also need to save the vocabulary and the tokenizer.
I mainly wanted the tutorials to discuss how these models worked in terms of their architecture and how to build and train them with PyTorch - without going into the inference/deployment side - so I'm considering saving/loading for deployment as out of scope for this repo.
If you want to train a model yourself, use the Google Colab links as they have free access to GPUs if you go Runtime > Change runtime type
and change the Hardware accelerator
to GPU
.