New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Off the shelf generation from trained hyperformer++ #2
Comments
@rabeehk can you help me with the required parameters inside the ##### Do we need these for inference ? adapter_config.tasks = data_args.tasks |
Hi @tuhinjubcse Similarly Best |
Yes but in We only pass data_args.tasks Do you know what the value will be for data_args. adapters or data_args.task_embeddings but data_args.task_embeddings whats the value of it ? how to specify it. I also have another question , I tried modifying your config to add a dropout of 0.1 but i get
|
Hi,
and
About the dropout, I do not have access to run the codes, but for debug you can check the attributes name and make sure this attribute exist. Basically you need to check the T5Config, the version used in the codes and make sure the names are the same.
hyperformer/hyperformer/training_args.py Line 134 in cb21807
|
Ok you are awesome. These seem to something that will be very useful for zero shot inference :) where train and test task are different |
you're very welcome. |
The text was updated successfully, but these errors were encountered: