[Docs] Fix spelling and grammar mistakes (#28825)

* Fix typos and grammar mistakes in docs and examples

* Fix typos in docstrings and comments

* Fix spelling of `tokenizer` in model tests

* Remove erroneous spaces in decorators

* Remove extra spaces in Markdown link texts

src/transformers/models/clap/configuration_clap.py

@@ -202,7 +202,7 @@ class ClapAudioConfig(PretrainedConfig):
             Whether or not to enable patch fusion. This is the main contribution of the authors, and should give the
             best results.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the encoder.
+            The dropout probability for all fully connected layers in the encoder.
         fusion_type (`[type]`, *optional*):
             Fusion type used for the patch fusion.
         patch_embed_input_channels (`int`, *optional*, defaults to 1):

src/transformers/models/convbert/configuration_convbert.py

@@ -61,7 +61,7 @@ class ConvBertConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/cpmant/configuration_cpmant.py

@@ -51,7 +51,7 @@ class CpmAntConfig(PretrainedConfig):
         num_hidden_layers (`int`, *optional*, defaults to 48):
             Number of layers of the Transformer encoder.
         dropout_p (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder.
+            The dropout probability for all fully connected layers in the embeddings, encoder.
         position_bias_num_buckets (`int`, *optional*, defaults to 512):
             The number of position_bias buckets.
         position_bias_max_distance (`int`, *optional*, defaults to 2048):

src/transformers/models/deit/configuration_deit.py

@@ -59,7 +59,7 @@ class DeiTConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/deprecated/mctct/configuration_mctct.py

@@ -64,7 +64,7 @@ class MCTCTConfig(PretrainedConfig):
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.3):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.3):
             The dropout ratio for the attention probabilities.
         pad_token_id (`int`, *optional*, defaults to 1):

src/transformers/models/distilbert/modeling_flax_distilbert.py

@@ -146,7 +146,7 @@ class FlaxEmbeddings(nn.Module):
             position_embeds = self.position_embeddings(position_ids.astype("i4"))
         else:
             position_embeds = self.pos_encoding[:, :seq_length, :]
-            # explictly cast the positions here, since self.embed_positions are not registered as parameters
+            # explicitly cast the positions here, since self.embed_positions are not registered as parameters
             position_embeds = position_embeds.astype(inputs_embeds.dtype)
 
         # Sum all embeddings

src/transformers/models/dpt/configuration_dpt.py

@@ -54,7 +54,7 @@ class DPTConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/esm/modeling_esmfold.py

@@ -1915,7 +1915,7 @@ class EsmFoldingTrunk(nn.Module):
         # This parameter means the axial attention will be computed
         # in a chunked manner. This should make the memory used more or less O(L) instead of O(L^2).
         # It's equivalent to running a for loop over chunks of the dimension we're iterative over,
-        # where the chunk_size is the size of the chunks, so 128 would mean to parse 128-lengthed chunks.
+        # where the chunk_size is the size of the chunks, so 128 would mean to parse 128-length chunks.
         self.chunk_size = chunk_size
 
     def forward(self, seq_feats, pair_feats, true_aa, residx, mask, no_recycles):

src/transformers/models/flava/configuration_flava.py

@@ -53,7 +53,7 @@ class FlavaImageConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):
@@ -188,7 +188,7 @@ class FlavaTextConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):
@@ -302,7 +302,7 @@ class FlavaMultimodalConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/fnet/configuration_fnet.py

@@ -52,7 +52,7 @@ class FNetConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         max_position_embeddings (`int`, *optional*, defaults to 512):
             The maximum sequence length that this model might ever be used with. Typically set this to something large
             just in case (e.g., 512 or 1024 or 2048).

src/transformers/models/gpt_neo/configuration_gpt_neo.py

@@ -70,7 +70,7 @@ class GPTNeoConfig(PretrainedConfig):
         resid_dropout (`float`, *optional*, defaults to 0.0):
             Residual dropout used in the attention pattern.
         embed_dropout (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         classifier_dropout (`float`, *optional*, defaults to 0.1):

src/transformers/models/groupvit/configuration_groupvit.py

@@ -177,7 +177,7 @@ class GroupViTVisionConfig(PretrainedConfig):
         layer_norm_eps (`float`, *optional*, defaults to 1e-5):
             The epsilon used by the layer normalization layers.
         dropout (`float`, *optional*, defaults to 0.0):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         initializer_range (`float`, *optional*, defaults to 0.02):

src/transformers/models/hubert/configuration_hubert.py

@@ -63,7 +63,7 @@ class HubertConfig(PretrainedConfig):
         attention_dropout(`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         final_dropout (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for the final projection layer of [`Wav2Vec2ForCTC`].
+            The dropout probability for the final projection layer of [`Wav2Vec2ForCTC`].
         layerdrop (`float`, *optional*, defaults to 0.1):
             The LayerDrop probability. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more
             details.

src/transformers/models/layoutlmv2/configuration_layoutlmv2.py

@@ -57,7 +57,7 @@ class LayoutLMv2Config(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/layoutlmv3/configuration_layoutlmv3.py

@@ -63,7 +63,7 @@ class LayoutLMv3Config(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/marian/modeling_flax_marian.py

@@ -711,7 +711,7 @@ class FlaxMarianEncoder(nn.Module):
         inputs_embeds = self.embed_tokens(input_ids) * self.embed_scale
 
         positions = jnp.take(self.embed_positions, position_ids, axis=0)
-        # explictly cast the positions here, since self.embed_positions are not registered as parameters
+        # explicitly cast the positions here, since self.embed_positions are not registered as parameters
         positions = positions.astype(inputs_embeds.dtype)
 
         hidden_states = inputs_embeds + positions
@@ -771,7 +771,7 @@ class FlaxMarianDecoder(nn.Module):
 
         # embed positions
         positions = jnp.take(self.embed_positions, position_ids, axis=0)
-        # explictly cast the positions here, since self.embed_positions are not registered as parameters
+        # explicitly cast the positions here, since self.embed_positions are not registered as parameters
         positions = positions.astype(inputs_embeds.dtype)
 
         hidden_states = inputs_embeds + positions

src/transformers/models/mobilevit/configuration_mobilevit.py

@@ -77,7 +77,7 @@ class MobileViTConfig(PretrainedConfig):
         output_stride (`int`, *optional*, defaults to 32):
             The ratio of the spatial resolution of the output to the resolution of the input image.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the Transformer encoder.
+            The dropout probability for all fully connected layers in the Transformer encoder.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
         classifier_dropout_prob (`float`, *optional*, defaults to 0.1):

src/transformers/models/mra/configuration_mra.py

@@ -52,7 +52,7 @@ class MraConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/nystromformer/configuration_nystromformer.py

@@ -52,7 +52,7 @@ class NystromformerConfig(PretrainedConfig):
             The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
             `"relu"`, `"selu"` and `"gelu_new"` are supported.
         hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
-            The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
         attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
             The dropout ratio for the attention probabilities.
         max_position_embeddings (`int`, *optional*, defaults to 512):

src/transformers/models/pegasus/modeling_flax_pegasus.py

@@ -707,7 +707,7 @@ class FlaxPegasusEncoder(nn.Module):
 
         # embed positions
         embed_pos = jnp.take(self.embed_positions, position_ids, axis=0)
-        # explictly cast the positions here, since self.embed_positions are not registered as parameters
+        # explicitly cast the positions here, since self.embed_positions are not registered as parameters
         embed_pos = embed_pos.astype(inputs_embeds.dtype)
 
         hidden_states = inputs_embeds + embed_pos
@@ -778,7 +778,7 @@ class FlaxPegasusDecoder(nn.Module):
 
         # embed positions
         positions = jnp.take(self.embed_positions, position_ids, axis=0)
-        # explictly cast the positions here, since self.embed_positions are not registered as parameters
+        # explicitly cast the positions here, since self.embed_positions are not registered as parameters
         positions = positions.astype(inputs_embeds.dtype)
 
         hidden_states = inputs_embeds + positions