From e535c389aa4b8975561a5aff674f8f3d1c404f83 Mon Sep 17 00:00:00 2001 From: Ross Johnstone Date: Wed, 2 Mar 2022 23:37:05 +0900 Subject: [PATCH] Fix tiny typo (#15884) --- .../bert-loses-patience/pabee/modeling_pabee_bert.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/research_projects/bert-loses-patience/pabee/modeling_pabee_bert.py b/examples/research_projects/bert-loses-patience/pabee/modeling_pabee_bert.py index 7384d78fb9..ff5c2b51e8 100644 --- a/examples/research_projects/bert-loses-patience/pabee/modeling_pabee_bert.py +++ b/examples/research_projects/bert-loses-patience/pabee/modeling_pabee_bert.py @@ -56,7 +56,7 @@ class BertModelWithPabee(BertModel): the self-attention layers, following the architecture described in `Attention is all you need`_ by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin. - To behave as an decoder the model needs to be initialized with the + To behave as a decoder the model needs to be initialized with the :obj:`is_decoder` argument of the configuration set to :obj:`True`; an :obj:`encoder_hidden_states` is expected as an input to the forward pass.