[Optional] Provide TFAutoModels for different head types #18
Labels
enhancement
New feature or request
feature request
New feature or functionality wanted
good first issue
Good for newcomers
When creating a TF Resuable SavedModel, it would be great to use to some extent be able to not need to create your own custom model for every model head
The basic example covers currently covers tokenizer and a base MLM model.
It would be great if to provide a
TFTAutoModelForSequenceClassification
, that creates a reusable saved model for with tokenizer and model. This could then be extended to every transformer headCan be done without major changes
Require Different changing Tokenizer masking?
Require tokenizer to except multiple inputs
The text was updated successfully, but these errors were encountered: