Diagnostics

Diagnostics

Diagnostics

Correct dimension of consistency cosine

Using torch.nn.CosineSimilarity to simplify code

Use keepdim option when normalising vectors

Make EPSILON a tensor

torch.maximum, not torch.max

PyTorch implementation of HugggingFace PreTrainedModel class does not allow direct setting of base_model. Rejig constructors accordingly

Removed superfluous ()

Converted QaracTrainerModel to use PyTorch

Removed extraneous self

Superclass __init__

Fix typos

Fix typos

Fix imports

Components for managing training corpora

More work on models

Encoder, Decoder and Trainer models (assuming RoBERTa base models)