From 13c185771847370d695b8eee3cbf12f4edc2111c Mon Sep 17 00:00:00 2001
From: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Date: Mon, 12 Oct 2020 04:06:59 -0400
Subject: [PATCH] Fix typo in all model docs (#7714)

---
 src/transformers/modeling_albert.py             | 2 +-
 src/transformers/modeling_bart.py               | 2 +-
 src/transformers/modeling_bert_generation.py    | 4 ++--
 src/transformers/modeling_ctrl.py               | 2 +-
 src/transformers/modeling_distilbert.py         | 2 +-
 src/transformers/modeling_dpr.py                | 4 ++--
 src/transformers/modeling_electra.py            | 2 +-
 src/transformers/modeling_encoder_decoder.py    | 2 +-
 src/transformers/modeling_flaubert.py           | 2 +-
 src/transformers/modeling_fsmt.py               | 2 +-
 src/transformers/modeling_funnel.py             | 2 +-
 src/transformers/modeling_gpt2.py               | 2 +-
 src/transformers/modeling_longformer.py         | 2 +-
 src/transformers/modeling_lxmert.py             | 4 ++--
 src/transformers/modeling_mmbt.py               | 4 ++--
 src/transformers/modeling_mobilebert.py         | 4 ++--
 src/transformers/modeling_openai.py             | 2 +-
 src/transformers/modeling_rag.py                | 6 +++---
 src/transformers/modeling_reformer.py           | 2 +-
 src/transformers/modeling_retribert.py          | 2 +-
 src/transformers/modeling_roberta.py            | 2 +-
 src/transformers/modeling_squeezebert.py        | 2 +-
 src/transformers/modeling_t5.py                 | 2 +-
 src/transformers/modeling_tf_albert.py          | 2 +-
 src/transformers/modeling_tf_bert.py            | 2 +-
 src/transformers/modeling_tf_ctrl.py            | 2 +-
 src/transformers/modeling_tf_distilbert.py      | 2 +-
 src/transformers/modeling_tf_electra.py         | 2 +-
 src/transformers/modeling_tf_flaubert.py        | 2 +-
 src/transformers/modeling_tf_funnel.py          | 2 +-
 src/transformers/modeling_tf_gpt2.py            | 2 +-
 src/transformers/modeling_tf_longformer.py      | 2 +-
 src/transformers/modeling_tf_lxmert.py          | 4 ++--
 src/transformers/modeling_tf_mobilebert.py      | 2 +-
 src/transformers/modeling_tf_openai.py          | 2 +-
 src/transformers/modeling_tf_roberta.py         | 2 +-
 src/transformers/modeling_tf_t5.py              | 2 +-
 src/transformers/modeling_tf_xlm.py             | 2 +-
 src/transformers/modeling_tf_xlnet.py           | 2 +-
 src/transformers/modeling_xlm.py                | 2 +-
 src/transformers/modeling_xlnet.py              | 2 +-
 templates/adding_a_new_model/modeling_tf_xxx.py | 2 +-
 templates/adding_a_new_model/modeling_xxx.py    | 2 +-
 43 files changed, 51 insertions(+), 51 deletions(-)

diff --git a/src/transformers/modeling_albert.py b/src/transformers/modeling_albert.py
index 97a490468d..b705a37a10 100755
--- a/src/transformers/modeling_albert.py
+++ b/src/transformers/modeling_albert.py
@@ -539,7 +539,7 @@ ALBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_bart.py b/src/transformers/modeling_bart.py
index e96e84fe9c..59987fc3fc 100644
--- a/src/transformers/modeling_bart.py
+++ b/src/transformers/modeling_bart.py
@@ -113,7 +113,7 @@ BART_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         decoder_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, target_sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_bert_generation.py b/src/transformers/modeling_bert_generation.py
index 9a0114e3dc..bab7a9faac 100755
--- a/src/transformers/modeling_bert_generation.py
+++ b/src/transformers/modeling_bert_generation.py
@@ -218,7 +218,7 @@ BERT_GENERATION_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         position_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
@@ -450,7 +450,7 @@ class BertGenerationDecoder(BertGenerationPreTrainedModel):
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
         labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
             Labels for computing the left-to-right language modeling loss (next word prediction).
             Indices should be in ``[-100, 0, ..., config.vocab_size]`` (see ``input_ids`` docstring)
diff --git a/src/transformers/modeling_ctrl.py b/src/transformers/modeling_ctrl.py
index 69b0b1105f..b839fffab8 100644
--- a/src/transformers/modeling_ctrl.py
+++ b/src/transformers/modeling_ctrl.py
@@ -273,7 +273,7 @@ CTRL_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_distilbert.py b/src/transformers/modeling_distilbert.py
index cec34a0953..c6b7a08ddc 100755
--- a/src/transformers/modeling_distilbert.py
+++ b/src/transformers/modeling_distilbert.py
@@ -401,7 +401,7 @@ DISTILBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
diff --git a/src/transformers/modeling_dpr.py b/src/transformers/modeling_dpr.py
index 6230e45ce7..e88e7dcd77 100644
--- a/src/transformers/modeling_dpr.py
+++ b/src/transformers/modeling_dpr.py
@@ -358,7 +358,7 @@ DPR_ENCODERS_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
@@ -403,7 +403,7 @@ DPR_READER_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(n_passages, sequence_length, hidden_size)`, `optional`):
diff --git a/src/transformers/modeling_electra.py b/src/transformers/modeling_electra.py
index 31a7fd9ecd..caa48548d0 100644
--- a/src/transformers/modeling_electra.py
+++ b/src/transformers/modeling_electra.py
@@ -611,7 +611,7 @@ ELECTRA_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_encoder_decoder.py b/src/transformers/modeling_encoder_decoder.py
index 1f0cc18278..59e7fce521 100644
--- a/src/transformers/modeling_encoder_decoder.py
+++ b/src/transformers/modeling_encoder_decoder.py
@@ -74,7 +74,7 @@ ENCODER_DECODER_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         decoder_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, target_sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_flaubert.py b/src/transformers/modeling_flaubert.py
index a8fbb06105..eadafa58bc 100644
--- a/src/transformers/modeling_flaubert.py
+++ b/src/transformers/modeling_flaubert.py
@@ -81,7 +81,7 @@ FLAUBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_fsmt.py b/src/transformers/modeling_fsmt.py
index 9a842d8a9b..a11e4a54bf 100644
--- a/src/transformers/modeling_fsmt.py
+++ b/src/transformers/modeling_fsmt.py
@@ -224,7 +224,7 @@ FSMT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         decoder_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, target_sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_funnel.py b/src/transformers/modeling_funnel.py
index 67f13039d3..ec86490f28 100644
--- a/src/transformers/modeling_funnel.py
+++ b/src/transformers/modeling_funnel.py
@@ -857,7 +857,7 @@ FUNNEL_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_gpt2.py b/src/transformers/modeling_gpt2.py
index ed781ba128..af7e0d5148 100644
--- a/src/transformers/modeling_gpt2.py
+++ b/src/transformers/modeling_gpt2.py
@@ -429,7 +429,7 @@ GPT2_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, input_ids_length)`, `optional`):
diff --git a/src/transformers/modeling_longformer.py b/src/transformers/modeling_longformer.py
index 8667264e27..5fd5469a20 100755
--- a/src/transformers/modeling_longformer.py
+++ b/src/transformers/modeling_longformer.py
@@ -1018,7 +1018,7 @@ LONGFORMER_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         global_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_lxmert.py b/src/transformers/modeling_lxmert.py
index 646785f93e..e5d0c271e2 100644
--- a/src/transformers/modeling_lxmert.py
+++ b/src/transformers/modeling_lxmert.py
@@ -848,7 +848,7 @@ LXMERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         visual_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`({0})`, `optional`):
@@ -856,7 +856,7 @@ LXMERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_mmbt.py b/src/transformers/modeling_mmbt.py
index ac3bb153be..f7853c1b88 100644
--- a/src/transformers/modeling_mmbt.py
+++ b/src/transformers/modeling_mmbt.py
@@ -123,7 +123,7 @@ MMBT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (`optional`) ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
@@ -167,7 +167,7 @@ MMBT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
         output_attentions (:obj:`bool`, `optional`):
             Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned
diff --git a/src/transformers/modeling_mobilebert.py b/src/transformers/modeling_mobilebert.py
index 323c7e59f0..c3ab7d535a 100644
--- a/src/transformers/modeling_mobilebert.py
+++ b/src/transformers/modeling_mobilebert.py
@@ -756,7 +756,7 @@ MOBILEBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
@@ -792,7 +792,7 @@ MOBILEBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
         output_attentions (:obj:`bool`, `optional`):
             Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned
diff --git a/src/transformers/modeling_openai.py b/src/transformers/modeling_openai.py
index a3029c6ca2..1645e6ed3f 100644
--- a/src/transformers/modeling_openai.py
+++ b/src/transformers/modeling_openai.py
@@ -360,7 +360,7 @@ OPENAI_GPT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_rag.py b/src/transformers/modeling_rag.py
index c3ce0dc254..349e0583fe 100644
--- a/src/transformers/modeling_rag.py
+++ b/src/transformers/modeling_rag.py
@@ -406,7 +406,7 @@ RAG_FORWARD_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         encoder_outputs (:obj:`tuple(tuple(torch.FloatTensor)`, `optional`)
@@ -836,7 +836,7 @@ class RagSequenceForGeneration(RagPreTrainedModel):
                 Mask values selected in ``[0, 1]``:
 
                 - 1 for tokens that are **not masked**,
-                - 0 for tokens that are **maked**.
+                - 0 for tokens that are **masked**.
 
                 `What are attention masks? <../glossary.html#attention-mask>`__
             context_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size * config.n_docs, config.max_combined_length)`, `optional`, returned when `output_retrieved=True`):
@@ -1221,7 +1221,7 @@ class RagTokenForGeneration(RagPreTrainedModel):
                 Mask values selected in ``[0, 1]``:
 
                 - 1 for tokens that are **not masked**,
-                - 0 for tokens that are **maked**.
+                - 0 for tokens that are **masked**.
 
                 `What are attention masks? <../glossary.html#attention-mask>`__
             context_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size * config.n_docs, config.max_combined_length)`, `optional`, returned when `output_retrieved=True`):
diff --git a/src/transformers/modeling_reformer.py b/src/transformers/modeling_reformer.py
index 2c9b5b9f38..7ac4e736cb 100755
--- a/src/transformers/modeling_reformer.py
+++ b/src/transformers/modeling_reformer.py
@@ -1926,7 +1926,7 @@ REFORMER_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         position_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_retribert.py b/src/transformers/modeling_retribert.py
index 3c4eed8852..38f24c90c0 100644
--- a/src/transformers/modeling_retribert.py
+++ b/src/transformers/modeling_retribert.py
@@ -185,7 +185,7 @@ class RetriBertModel(RetriBertPreTrainedModel):
                 Mask values selected in ``[0, 1]``:
 
                 - 1 for tokens that are **not masked**,
-                - 0 for tokens that are **maked**.
+                - 0 for tokens that are **masked**.
 
                 `What are attention masks? <../glossary.html#attention-mask>`__
             input_ids_doc (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`):
diff --git a/src/transformers/modeling_roberta.py b/src/transformers/modeling_roberta.py
index 6e258ba7d4..3a39067070 100644
--- a/src/transformers/modeling_roberta.py
+++ b/src/transformers/modeling_roberta.py
@@ -506,7 +506,7 @@ ROBERTA_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_squeezebert.py b/src/transformers/modeling_squeezebert.py
index d7e755ed25..5ca780a120 100644
--- a/src/transformers/modeling_squeezebert.py
+++ b/src/transformers/modeling_squeezebert.py
@@ -461,7 +461,7 @@ SQUEEZEBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_t5.py b/src/transformers/modeling_t5.py
index ac41f7fa92..8e3c3f9681 100644
--- a/src/transformers/modeling_t5.py
+++ b/src/transformers/modeling_t5.py
@@ -843,7 +843,7 @@ T5_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         decoder_input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, target_sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_tf_albert.py b/src/transformers/modeling_tf_albert.py
index be115c616c..4594451a4d 100644
--- a/src/transformers/modeling_tf_albert.py
+++ b/src/transformers/modeling_tf_albert.py
@@ -690,7 +690,7 @@ ALBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_tf_bert.py b/src/transformers/modeling_tf_bert.py
index 5b7a333f47..f1dcab7695 100644
--- a/src/transformers/modeling_tf_bert.py
+++ b/src/transformers/modeling_tf_bert.py
@@ -735,7 +735,7 @@ BERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_tf_ctrl.py b/src/transformers/modeling_tf_ctrl.py
index c9fdb5473d..35583cc39a 100644
--- a/src/transformers/modeling_tf_ctrl.py
+++ b/src/transformers/modeling_tf_ctrl.py
@@ -495,7 +495,7 @@ CTRL_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_tf_distilbert.py b/src/transformers/modeling_tf_distilbert.py
index 0d1a820bc6..a6d18933f7 100644
--- a/src/transformers/modeling_tf_distilbert.py
+++ b/src/transformers/modeling_tf_distilbert.py
@@ -550,7 +550,7 @@ DISTILBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         head_mask (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
diff --git a/src/transformers/modeling_tf_electra.py b/src/transformers/modeling_tf_electra.py
index c680042a8a..49e775ae86 100644
--- a/src/transformers/modeling_tf_electra.py
+++ b/src/transformers/modeling_tf_electra.py
@@ -665,7 +665,7 @@ ELECTRA_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         position_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_tf_flaubert.py b/src/transformers/modeling_tf_flaubert.py
index 231cfb7d1d..1e277eafba 100644
--- a/src/transformers/modeling_tf_flaubert.py
+++ b/src/transformers/modeling_tf_flaubert.py
@@ -96,7 +96,7 @@ FLAUBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - ``1`` for tokens that are **not masked**,
-            - ``0`` for tokens that are **maked**.
+            - ``0`` for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         langs (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_tf_funnel.py b/src/transformers/modeling_tf_funnel.py
index 8130f03fc0..a81e27dc79 100644
--- a/src/transformers/modeling_tf_funnel.py
+++ b/src/transformers/modeling_tf_funnel.py
@@ -1099,7 +1099,7 @@ FUNNEL_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_tf_gpt2.py b/src/transformers/modeling_tf_gpt2.py
index 5e1b6185dc..2f6a602aba 100644
--- a/src/transformers/modeling_tf_gpt2.py
+++ b/src/transformers/modeling_tf_gpt2.py
@@ -508,7 +508,7 @@ GPT2_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_tf_longformer.py b/src/transformers/modeling_tf_longformer.py
index 1918a21022..c23a6191df 100644
--- a/src/transformers/modeling_tf_longformer.py
+++ b/src/transformers/modeling_tf_longformer.py
@@ -1534,7 +1534,7 @@ LONGFORMER_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         global_attention_mask (:obj:`tf.Tensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_tf_lxmert.py b/src/transformers/modeling_tf_lxmert.py
index bd9da4e2ba..eeb576d3b8 100644
--- a/src/transformers/modeling_tf_lxmert.py
+++ b/src/transformers/modeling_tf_lxmert.py
@@ -921,7 +921,7 @@ LXMERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         visual_attention_mask (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
@@ -929,7 +929,7 @@ LXMERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`tf.Tensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_tf_mobilebert.py b/src/transformers/modeling_tf_mobilebert.py
index dbf8c716fa..7ae12be7f6 100644
--- a/src/transformers/modeling_tf_mobilebert.py
+++ b/src/transformers/modeling_tf_mobilebert.py
@@ -903,7 +903,7 @@ MOBILEBERT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_tf_openai.py b/src/transformers/modeling_tf_openai.py
index d76d276226..16a4cd080e 100644
--- a/src/transformers/modeling_tf_openai.py
+++ b/src/transformers/modeling_tf_openai.py
@@ -444,7 +444,7 @@ OPENAI_GPT_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`(batch_size, sequence_length)`, `optional`):
diff --git a/src/transformers/modeling_tf_roberta.py b/src/transformers/modeling_tf_roberta.py
index 54334bdccb..30a4983230 100644
--- a/src/transformers/modeling_tf_roberta.py
+++ b/src/transformers/modeling_tf_roberta.py
@@ -654,7 +654,7 @@ ROBERTA_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_tf_t5.py b/src/transformers/modeling_tf_t5.py
index 3d53da4913..c3e6802be4 100644
--- a/src/transformers/modeling_tf_t5.py
+++ b/src/transformers/modeling_tf_t5.py
@@ -913,7 +913,7 @@ T5_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         decoder_attention_mask (:obj:`tf.Tensor` of shape :obj:`(batch_size, tgt_seq_len)`, `optional`):
diff --git a/src/transformers/modeling_tf_xlm.py b/src/transformers/modeling_tf_xlm.py
index 0fa6eb30a3..511a5b5f26 100644
--- a/src/transformers/modeling_tf_xlm.py
+++ b/src/transformers/modeling_tf_xlm.py
@@ -626,7 +626,7 @@ XLM_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         langs (:obj:`tf.Tensor` or :obj:`Numpy array` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_tf_xlnet.py b/src/transformers/modeling_tf_xlnet.py
index ffb99b1aa1..b20e46599f 100644
--- a/src/transformers/modeling_tf_xlnet.py
+++ b/src/transformers/modeling_tf_xlnet.py
@@ -1057,7 +1057,7 @@ XLNET_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         mems (:obj:`List[torch.FloatTensor]` of length :obj:`config.n_layers`):
diff --git a/src/transformers/modeling_xlm.py b/src/transformers/modeling_xlm.py
index a665aa4a1c..e674cb35ee 100755
--- a/src/transformers/modeling_xlm.py
+++ b/src/transformers/modeling_xlm.py
@@ -337,7 +337,7 @@ XLM_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         langs (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):
diff --git a/src/transformers/modeling_xlnet.py b/src/transformers/modeling_xlnet.py
index 3b2e7163a8..e226d747d7 100755
--- a/src/transformers/modeling_xlnet.py
+++ b/src/transformers/modeling_xlnet.py
@@ -866,7 +866,7 @@ XLNET_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         mems (:obj:`List[torch.FloatTensor]` of length :obj:`config.n_layers`):
diff --git a/templates/adding_a_new_model/modeling_tf_xxx.py b/templates/adding_a_new_model/modeling_tf_xxx.py
index 585da6aecd..7135b29c62 100644
--- a/templates/adding_a_new_model/modeling_tf_xxx.py
+++ b/templates/adding_a_new_model/modeling_tf_xxx.py
@@ -310,7 +310,7 @@ XXX_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`Numpy array` or :obj:`tf.Tensor` of shape :obj:`({0})`, `optional`):
diff --git a/templates/adding_a_new_model/modeling_xxx.py b/templates/adding_a_new_model/modeling_xxx.py
index db0de52a8e..b5634459c6 100644
--- a/templates/adding_a_new_model/modeling_xxx.py
+++ b/templates/adding_a_new_model/modeling_xxx.py
@@ -243,7 +243,7 @@ XXX_INPUTS_DOCSTRING = r"""
             Mask values selected in ``[0, 1]``:
 
             - 1 for tokens that are **not masked**,
-            - 0 for tokens that are **maked**.
+            - 0 for tokens that are **masked**.
 
             `What are attention masks? <../glossary.html#attention-mask>`__
         token_type_ids (:obj:`torch.LongTensor` of shape :obj:`({0})`, `optional`):