From f88c104d8f79e78a98c8ce6c1f4a78db73142eab Mon Sep 17 00:00:00 2001 From: Julien Chaumond Date: Tue, 5 Nov 2019 19:56:43 -0500 Subject: [PATCH] [run_tf_glue] Add comment for context --- examples/run_tf_glue.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/examples/run_tf_glue.py b/examples/run_tf_glue.py index 8878ce726e..54282277d2 100644 --- a/examples/run_tf_glue.py +++ b/examples/run_tf_glue.py @@ -73,6 +73,8 @@ model.save_pretrained('./save/') if TASK == "mrpc": # Load the TensorFlow model in PyTorch for inspection + # This is to demo the interoperability between the two frameworks, you don't have to + # do this in real life (you can run the inference on the TF model). pytorch_model = BertForSequenceClassification.from_pretrained('./save/', from_tf=True) # Quickly test a few predictions - MRPC is a paraphrasing task, let's see if our model learned the task