diff --git a/src/transformers/models/bart/modeling_tf_bart.py b/src/transformers/models/bart/modeling_tf_bart.py index a75fb4ceb5..a5a6b907c6 100644 --- a/src/transformers/models/bart/modeling_tf_bart.py +++ b/src/transformers/models/bart/modeling_tf_bart.py @@ -1364,7 +1364,7 @@ class TFBartForConditionalGeneration(TFBartPretrainedModel, TFCausalLanguageMode past_key_values=outputs.past_key_values, # index 1 of d outputs decoder_hidden_states=outputs.decoder_hidden_states, # index 2 of d outputs decoder_attentions=outputs.decoder_attentions, # index 3 of d outputs - encoder_last_hidden_state=outputs.last_hidden_state, # index 0 of encoder outputs + encoder_last_hidden_state=outputs.encoder_last_hidden_state, # index 0 of encoder outputs encoder_hidden_states=outputs.encoder_hidden_states, # 1 of e out encoder_attentions=outputs.encoder_attentions, # 2 of e out ) diff --git a/src/transformers/models/blenderbot/modeling_tf_blenderbot.py b/src/transformers/models/blenderbot/modeling_tf_blenderbot.py index cb935a35f0..258591c7f7 100644 --- a/src/transformers/models/blenderbot/modeling_tf_blenderbot.py +++ b/src/transformers/models/blenderbot/modeling_tf_blenderbot.py @@ -1394,7 +1394,7 @@ class TFBlenderbotForConditionalGeneration(TFBlenderbotPreTrainedModel, TFCausal past_key_values=outputs.past_key_values, # index 1 of d outputs decoder_hidden_states=outputs.decoder_hidden_states, # index 2 of d outputs decoder_attentions=outputs.decoder_attentions, # index 3 of d outputs - encoder_last_hidden_state=outputs.last_hidden_state, # index 0 of encoder outputs + encoder_last_hidden_state=outputs.encoder_last_hidden_state, # index 0 of encoder outputs encoder_hidden_states=outputs.encoder_hidden_states, # 1 of e out encoder_attentions=outputs.encoder_attentions, # 2 of e out ) diff --git a/src/transformers/models/blenderbot_small/modeling_tf_blenderbot_small.py b/src/transformers/models/blenderbot_small/modeling_tf_blenderbot_small.py index ab7fb68bde..2ef1f9c149 100644 --- a/src/transformers/models/blenderbot_small/modeling_tf_blenderbot_small.py +++ b/src/transformers/models/blenderbot_small/modeling_tf_blenderbot_small.py @@ -1369,7 +1369,7 @@ class TFBlenderbotSmallForConditionalGeneration(TFBlenderbotSmallPreTrainedModel past_key_values=outputs.past_key_values, # index 1 of d outputs decoder_hidden_states=outputs.decoder_hidden_states, # index 2 of d outputs decoder_attentions=outputs.decoder_attentions, # index 3 of d outputs - encoder_last_hidden_state=outputs.last_hidden_state, # index 0 of encoder outputs + encoder_last_hidden_state=outputs.encoder_last_hidden_state, # index 0 of encoder outputs encoder_hidden_states=outputs.encoder_hidden_states, # 1 of e out encoder_attentions=outputs.encoder_attentions, # 2 of e out ) diff --git a/src/transformers/models/mbart/modeling_tf_mbart.py b/src/transformers/models/mbart/modeling_tf_mbart.py index 71ea3d0877..cddd6917f5 100644 --- a/src/transformers/models/mbart/modeling_tf_mbart.py +++ b/src/transformers/models/mbart/modeling_tf_mbart.py @@ -1385,7 +1385,7 @@ class TFMBartForConditionalGeneration(TFMBartPreTrainedModel, TFCausalLanguageMo past_key_values=outputs.past_key_values, # index 1 of d outputs decoder_hidden_states=outputs.decoder_hidden_states, # index 2 of d outputs decoder_attentions=outputs.decoder_attentions, # index 3 of d outputs - encoder_last_hidden_state=outputs.last_hidden_state, # index 0 of encoder outputs + encoder_last_hidden_state=outputs.encoder_last_hidden_state, # index 0 of encoder outputs encoder_hidden_states=outputs.encoder_hidden_states, # 1 of e out encoder_attentions=outputs.encoder_attentions, # 2 of e out ) diff --git a/src/transformers/models/pegasus/modeling_tf_pegasus.py b/src/transformers/models/pegasus/modeling_tf_pegasus.py index 73f9e4e8d3..3eb7b3f5a2 100644 --- a/src/transformers/models/pegasus/modeling_tf_pegasus.py +++ b/src/transformers/models/pegasus/modeling_tf_pegasus.py @@ -1400,7 +1400,7 @@ class TFPegasusForConditionalGeneration(TFPegasusPreTrainedModel, TFCausalLangua past_key_values=outputs.past_key_values, # index 1 of d outputs decoder_hidden_states=outputs.decoder_hidden_states, # index 2 of d outputs decoder_attentions=outputs.decoder_attentions, # index 3 of d outputs - encoder_last_hidden_state=outputs.last_hidden_state, # index 0 of encoder outputs + encoder_last_hidden_state=outputs.encoder_last_hidden_state, # index 0 of encoder outputs encoder_hidden_states=outputs.encoder_hidden_states, # 1 of e out encoder_attentions=outputs.encoder_attentions, # 2 of e out ) diff --git a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_tf_{{cookiecutter.lowercase_modelname}}.py b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_tf_{{cookiecutter.lowercase_modelname}}.py index 0d5a61206b..ebcd0e3a70 100644 --- a/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_tf_{{cookiecutter.lowercase_modelname}}.py +++ b/templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_tf_{{cookiecutter.lowercase_modelname}}.py @@ -2823,7 +2823,7 @@ class TF{{cookiecutter.camelcase_modelname}}ForConditionalGeneration(TF{{cookiec past_key_values=outputs.past_key_values, # index 1 of d outputs decoder_hidden_states=outputs.decoder_hidden_states, # index 2 of d outputs decoder_attentions=outputs.decoder_attentions, # index 3 of d outputs - encoder_last_hidden_state=outputs.last_hidden_state, # index 0 of encoder outputs + encoder_last_hidden_state=outputs.encoder_last_hidden_state, # index 0 of encoder outputs encoder_hidden_states=outputs.encoder_hidden_states, # 1 of e out encoder_attentions=outputs.encoder_attentions, # 2 of e out )