You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Dec 16, 2022. It is now read-only.
I would like to use transformer_qa_eval to generate metrics using BERT Large Cased on a QA task with the SQuAD v2.0 dataset. transformer_qa_eval is not well documented, so if it's the wrong tool for the job, please stop me here.
However, to use transformer_qa_eval, I must pass the path to my model archive as a string via the qa_model parameter. When I specify "bert-large-cased" in a dataset reader and use allennlp train, everything works, so I know that allennlp is somehow able to interface with BERT Large Cased. However, since transformer_qa_eval requires the path to the actual model archive, not simply the registered model name, I'm stuck, because I have no idea how to find the correct path.
Can anyone clarify this point? What path should I use to get transformer_qa_eval to work with BERT Large Cased? Thank you!
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I would like to use
transformer_qa_eval
to generate metrics using BERT Large Cased on a QA task with the SQuAD v2.0 dataset.transformer_qa_eval
is not well documented, so if it's the wrong tool for the job, please stop me here.However, to use
transformer_qa_eval
, I must pass the path to my model archive as a string via theqa_model
parameter. When I specify"bert-large-cased"
in a dataset reader and useallennlp train
, everything works, so I know that allennlp is somehow able to interface with BERT Large Cased. However, sincetransformer_qa_eval
requires the path to the actual model archive, not simply the registered model name, I'm stuck, because I have no idea how to find the correct path.Can anyone clarify this point? What path should I use to get
transformer_qa_eval
to work with BERT Large Cased? Thank you!Beta Was this translation helpful? Give feedback.
All reactions