Docs: add kwargs type to fix formatting (#24733)

src/transformers/configuration_utils.py

@@ -432,7 +432,7 @@ class PretrainedConfig(PushToHubMixin):
                 Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
                 repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                 namespace).
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
         if os.path.isfile(save_directory):

src/transformers/feature_extraction_utils.py

@@ -379,7 +379,7 @@ class FeatureExtractionMixin(PushToHubMixin):
                 Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
                 repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                 namespace).
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
         if os.path.isfile(save_directory):

src/transformers/generation/configuration_utils.py

@@ -353,7 +353,7 @@ class GenerationConfig(PushToHubMixin):
                 Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
                 repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                 namespace).
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
         config_file_name = config_file_name if config_file_name is not None else GENERATION_CONFIG_NAME

src/transformers/generation/flax_logits_process.py

@@ -38,7 +38,7 @@ LOGITS_PROCESSOR_INPUTS_DOCSTRING = r"""
         scores (`jnp.ndarray` of shape `(batch_size, config.vocab_size)`):
             Prediction scores of a language modeling head. These can be logits for each vocabulary when not using beam
             search or log softmax for each vocabulary token when using beam search
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             Additional logits processor specific kwargs.
 
     Return:

src/transformers/generation/flax_utils.py

@@ -296,7 +296,7 @@ class FlaxGenerationMixin:
                 Custom logits processors that complement the default logits processors built from arguments and
                 generation config. If a logit processor is passed that is already created with the arguments or a
                 generation config an error is thrown. This feature is intended for advanced users.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Ad hoc parametrization of `generate_config` and/or additional model-specific kwargs that will be
                 forwarded to the `forward` function of the model. If the model is an encoder-decoder model, encoder
                 specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with *decoder_*.

src/transformers/generation/logits_process.py

@@ -39,7 +39,7 @@ LOGITS_PROCESSOR_INPUTS_DOCSTRING = r"""
         scores (`torch.FloatTensor` of shape `(batch_size, config.vocab_size)`):
             Prediction scores of a language modeling head. These can be logits for each vocabulary when not using beam
             search or log softmax for each vocabulary token when using beam search
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             Additional logits processor specific kwargs.
 
     Return:

src/transformers/generation/stopping_criteria.py

@@ -24,7 +24,7 @@ STOPPING_CRITERIA_INPUTS_DOCSTRING = r"""
         scores (`torch.FloatTensor` of shape `(batch_size, config.vocab_size)`):
             Prediction scores of a language modeling head. These can be scores for each vocabulary token before SoftMax
             or scores for each vocabulary token after SoftMax.
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             Additional stopping criteria specific kwargs.
 
     Return:

src/transformers/generation/tf_logits_process.py

@@ -42,7 +42,7 @@ TF_LOGITS_PROCESSOR_INPUTS_DOCSTRING = r"""
         cur_len (`int`):
             The current length of valid input sequence tokens. In the TF implementation, the input_ids' sequence length
             is the maximum length generate can produce, and we need to know which of its tokens are valid.
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             Additional logits processor specific kwargs.
 
     Return:

src/transformers/generation/tf_utils.py

@@ -705,7 +705,7 @@ class TFGenerationMixin:
             seed (`List[int]`, *optional*):
                 Random seed to control sampling, containing two integers, used when `do_sample` is `True`. See the
                 `seed` argument from stateless functions in `tf.random`.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Ad hoc parametrization of `generate_config` and/or additional model-specific kwargs that will be
                 forwarded to the `forward` function of the model. If the model is an encoder-decoder model, encoder
                 specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with *decoder_*.

src/transformers/generation/utils.py

@@ -1225,7 +1225,7 @@ class GenerationMixin:
             streamer (`BaseStreamer`, *optional*):
                 Streamer object that will be used to stream the generated sequences. Generated tokens are passed
                 through `streamer.put(token_ids)` and the streamer is responsible for any further processing.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Ad hoc parametrization of `generate_config` and/or additional model-specific kwargs that will be
                 forwarded to the `forward` function of the model. If the model is an encoder-decoder model, encoder
                 specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with *decoder_*.

src/transformers/hf_argparser.py

@@ -122,8 +122,8 @@ class HfArgumentParser(ArgumentParser):
         Args:
             dataclass_types:
                 Dataclass type, or list of dataclass types for which we will "fill" instances with the parsed args.
-            kwargs:
-                (Optional) Passed to `argparse.ArgumentParser()` in the regular way.
+            kwargs (`Dict[str, Any]`, *optional*):
+                Passed to `argparse.ArgumentParser()` in the regular way.
         """
         # To make the default appear when using --help
         if "formatter_class" not in kwargs:

src/transformers/image_processing_utils.py

@@ -208,7 +208,7 @@ class ImageProcessingMixin(PushToHubMixin):
                 Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
                 repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                 namespace).
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
         if os.path.isfile(save_directory):

src/transformers/modeling_flax_utils.py

@@ -1043,7 +1043,7 @@ class FlaxPreTrainedModel(PushToHubMixin, FlaxGenerationMixin):
 
                 </Tip>
 
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
         if os.path.isfile(save_directory):

src/transformers/modeling_tf_utils.py

@@ -2371,8 +2371,7 @@ class TFPreTrainedModel(tf.keras.Model, TFModelUtilsMixin, TFGenerationMixin, Pu
                 Whether or not to create a PR with the uploaded files or directly commit.
             safe_serialization (`bool`, *optional*, defaults to `False`):
                 Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
-
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
         if os.path.isfile(save_directory):
@@ -3166,7 +3165,7 @@ class TFConv1D(tf.keras.layers.Layer):
             The number of input features.
         initializer_range (`float`, *optional*, defaults to 0.02):
             The standard deviation to use to initialize the weights.
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             Additional keyword arguments passed along to the `__init__` of `tf.keras.layers.Layer`.
     """
 
@@ -3208,7 +3207,7 @@ class TFSharedEmbeddings(tf.keras.layers.Layer):
         initializer_range (`float`, *optional*):
             The standard deviation to use when initializing the weights. If no value is provided, it will default to
             \\(1/\sqrt{hidden\_size}\\).
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             Additional keyword arguments passed along to the `__init__` of `tf.keras.layers.Layer`.
     """
     # TODO (joao): flagged for delection due to embeddings refactor
@@ -3322,7 +3321,7 @@ class TFSequenceSummary(tf.keras.layers.Layer):
             - **summary_last_dropout** (`float`)-- Optional dropout probability after the projection and activation.
 
         initializer_range (`float`, defaults to 0.02): The standard deviation to use to initialize the weights.
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             Additional keyword arguments passed along to the `__init__` of `tf.keras.layers.Layer`.
     """
 

src/transformers/modeling_utils.py

@@ -1700,8 +1700,7 @@ class PreTrainedModel(nn.Module, ModuleUtilsMixin, GenerationMixin, PushToHubMix
                 Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
             variant (`str`, *optional*):
                 If specified, weights are saved in the format pytorch_model.<variant>.bin.
-
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
         # Checks if the model has been loaded in 8-bit

src/transformers/models/jukebox/tokenization_jukebox.py

@@ -202,9 +202,6 @@ class JukeboxTokenizer(PreTrainedTokenizer):
         """
         Performs any necessary transformations before tokenization.
 
-        This method should pop the arguments from kwargs and return the remaining `kwargs` as well. We test the
-        `kwargs` at the end of the encoding process to be sure all the arguments have been used.
-
         Args:
             artist (`str`):
                 The artist name to prepare. This will mostly lower the string
@@ -216,8 +213,6 @@ class JukeboxTokenizer(PreTrainedTokenizer):
                 Whether or not the input is already pre-tokenized (e.g., split into words). If set to `True`, the
                 tokenizer assumes the input is already split into words (for instance, by splitting it on whitespace)
                 which it will tokenize. This is useful for NER or token classification.
-            kwargs:
-                Keyword arguments to use for the tokenization.
         """
         for idx in range(len(self.version)):
             if self.version[idx] == "v3":

src/transformers/models/musicgen/modeling_musicgen.py

@@ -1228,7 +1228,7 @@ class MusicgenForCausalLM(MusicgenPreTrainedModel):
                 generation config an error is thrown. This feature is intended for advanced users.
             synced_gpus (`bool`, *optional*, defaults to `False`):
                 Whether to continue running the while loop until max_length (needed for ZeRO stage 3)
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Ad hoc parametrization of `generate_config` and/or additional model-specific kwargs that will be
                 forwarded to the `forward` function of the model. If the model is an encoder-decoder model, encoder
                 specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with *decoder_*.
@@ -2225,7 +2225,7 @@ class MusicgenForConditionalGeneration(PreTrainedModel):
                 generation config an error is thrown. This feature is intended for advanced users.
             synced_gpus (`bool`, *optional*, defaults to `False`):
                 Whether to continue running the while loop until max_length (needed for ZeRO stage 3)
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Ad hoc parametrization of `generate_config` and/or additional model-specific kwargs that will be
                 forwarded to the `forward` function of the model. If the model is an encoder-decoder model, encoder
                 specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with *decoder_*.

src/transformers/models/rag/modeling_rag.py

@@ -962,7 +962,7 @@ class RagSequenceForGeneration(RagPreTrainedModel):
                 Number of beams for beam search. 1 means no beam search.
             n_docs (`int`, *optional*, defaults to `config.n_docs`)
                 Number of documents to retrieve and/or number of documents for which to generate an answer.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional kwargs will be passed to [`~generation.GenerationMixin.generate`].
 
         Return:
@@ -1444,7 +1444,7 @@ class RagTokenForGeneration(RagPreTrainedModel):
                 Custom stopping criteria that complement the default stopping criteria built from arguments and a
                 model's config. If a stopping criteria is passed that is already created with the arguments or a
                 model's config an error is thrown.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Ad hoc parametrization of `generate_config` and/or additional model-specific kwargs that will be
                 forwarded to the `forward` function of the model.
 

src/transformers/models/rag/modeling_tf_rag.py

@@ -1051,7 +1051,7 @@ class TFRagTokenForGeneration(TFRagPreTrainedModel, TFCausalLanguageModelingLoss
                 Custom logits processors that complement the default logits processors built from arguments and a
                 model's config. If a logit processor is passed that is already created with the arguments or a model's
                 config an error is thrown.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Ad hoc parametrization of `generate_config` and/or additional model-specific kwargs that will be
                 forwarded to the `forward` function of the model.
 
@@ -1629,7 +1629,7 @@ class TFRagSequenceForGeneration(TFRagPreTrainedModel, TFCausalLanguageModelingL
                 Number of beams for beam search. 1 means no beam search.
             n_docs (`int`, *optional*, defaults to `config.n_docs`)
                 Number of documents to retrieve and/or number of documents for which to generate an answer.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional kwargs will be passed to [`~generation.GenerationMixin.generate`]
 
         Return:

src/transformers/models/whisper/modeling_tf_whisper.py

@@ -1394,7 +1394,7 @@ class TFWhisperForConditionalGeneration(TFWhisperPreTrainedModel, TFCausalLangua
                 Whether to return token-level timestamps with the text. This can be used with or without the
                 `return_timestamps` option. To get word-level timestamps, use the tokenizer to group the tokens into
                 words.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Ad hoc parametrization of `generate_config` and/or additional model-specific kwargs that will be
                 forwarded to the `forward` function of the model. If the model is an encoder-decoder model, encoder
                 specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with *decoder_*.

src/transformers/models/whisper/modeling_whisper.py

@@ -1608,7 +1608,7 @@ class WhisperForConditionalGeneration(WhisperPreTrainedModel):
                 Whether to return token-level timestamps with the text. This can be used with or without the
                 `return_timestamps` option. To get word-level timestamps, use the tokenizer to group the tokens into
                 words.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Ad hoc parametrization of `generate_config` and/or additional model-specific kwargs that will be
                 forwarded to the `forward` function of the model. If the model is an encoder-decoder model, encoder
                 specific kwargs should not be prefixed and decoder specific kwargs should be prefixed with *decoder_*.

src/transformers/optimization_tf.py

@@ -201,7 +201,7 @@ class AdamWeightDecay(Adam):
             `include_in_weight_decay` is passed, the names in it will supersede this list.
         name (`str`, *optional*, defaults to 'AdamWeightDecay'):
             Optional name for the operations created when applying gradients.
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             Keyword arguments. Allowed to be {`clipnorm`, `clipvalue`, `lr`, `decay`}. `clipnorm` is clip gradients by
             norm; `clipvalue` is clip gradients by value, `decay` is included for backward compatibility to allow time
             inverse decay of learning rate. `lr` is included for backward compatibility, recommended to use

src/transformers/pipelines/__init__.py

@@ -634,10 +634,10 @@ def pipeline(
             Whether or not to allow for custom code defined on the Hub in their own modeling, configuration,
             tokenization or even pipeline files. This option should only be set to `True` for repositories you trust
             and in which you have read the code, as it will execute code present on the Hub on your local machine.
-        model_kwargs:
+        model_kwargs (`Dict[str, Any]`, *optional*):
             Additional dictionary of keyword arguments passed along to the model's `from_pretrained(...,
             **model_kwargs)` function.
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             Additional keyword arguments passed along to the specific pipeline init (see the documentation for the
             corresponding pipeline class for possible values).
 

src/transformers/processing_utils.py

@@ -111,7 +111,7 @@ class ProcessorMixin(PushToHubMixin):
                 Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
                 repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                 namespace).
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
         """
         os.makedirs(save_directory, exist_ok=True)

src/transformers/tokenization_utils.py

@@ -834,7 +834,7 @@ class PreTrainedTokenizer(PreTrainedTokenizerBase):
                 Whether or not the input is already pre-tokenized (e.g., split into words). If set to `True`, the
                 tokenizer assumes the input is already split into words (for instance, by splitting it on whitespace)
                 which it will tokenize. This is useful for NER or token classification.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Keyword arguments to use for the tokenization.
 
         Returns:

src/transformers/tokenization_utils_base.py

@@ -2133,7 +2133,7 @@ class PreTrainedTokenizerBase(SpecialTokensMixin, PushToHubMixin):
                 Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
                 repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                 namespace).
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
 
         Returns:

src/transformers/tokenization_utils_fast.py

@@ -630,7 +630,7 @@ class PreTrainedTokenizerFast(PreTrainedTokenizerBase):
             special_tokens_map (`Dict[str, str]`, *optional*):
                 If you want to rename some of the special tokens this tokenizer uses, pass along a mapping old special
                 token name to new special token name in this argument.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional keyword arguments passed along to the trainer from the 🤗 Tokenizers library.
 
         Returns:

src/transformers/tools/agents.py

@@ -704,7 +704,7 @@ class LocalAgent(Agent):
         Args:
             pretrained_model_name_or_path (`str` or `os.PathLike`):
                 The name of a repo on the Hub or a local path to a folder containing both model and tokenizer.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Keyword arguments passed along to [`~PreTrainedModel.from_pretrained`].
 
         Example:

src/transformers/trainer.py

@@ -1475,7 +1475,7 @@ class Trainer:
             ignore_keys_for_eval (`List[str]`, *optional*)
                 A list of keys in the output of your model (if it is a dictionary) that should be ignored when
                 gathering predictions for evaluation during the training.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional keyword arguments used to hide deprecated arguments
         """
         if resume_from_checkpoint is False:
@@ -3567,7 +3567,7 @@ class Trainer:
                 Message to commit while pushing.
             blocking (`bool`, *optional*, defaults to `True`):
                 Whether the function should return only when the `git push` has finished.
-            kwargs:
+            kwargs (`Dict[str, Any]`, *optional*):
                 Additional keyword arguments passed along to [`~Trainer.create_model_card`].
 
         Returns:

src/transformers/trainer_pt_utils.py

@@ -257,7 +257,7 @@ class DistributedSamplerWithLoop(DistributedSampler):
             Dataset used for sampling.
         batch_size (`int`):
             The batch size used with this sampler
-        kwargs:
+        kwargs (`Dict[str, Any]`, *optional*):
             All other keyword arguments passed to `DistributedSampler`.
     """