Add many missing spaces in adjacent strings (#26751)

Add missing spaces in adjacent strings

src/transformers/models/auto/processing_auto.py

@@ -314,7 +314,7 @@ class AutoProcessor:
 
         raise ValueError(
             f"Unrecognized processing class in {pretrained_model_name_or_path}. Can't instantiate a processor, a "
-            "tokenizer, an image processor or a feature extractor for this model. Make sure the repository contains"
+            "tokenizer, an image processor or a feature extractor for this model. Make sure the repository contains "
             "the files of at least one of those processing classes."
         )
 

src/transformers/models/codegen/tokenization_codegen_fast.py

@@ -144,7 +144,7 @@ class CodeGenTokenizerFast(PreTrainedTokenizerFast):
         if kwargs.pop("add_bos_token", False):
             model_id = kwargs.pop("name_or_path", "")
             raise ValueError(
-                "Currenty GPT2's fast tokenizer does NOT support adding a BOS token."
+                "Currenty GPT2's fast tokenizer does NOT support adding a BOS token. "
                 "Instead you should use GPT2's slow tokenizer class `CodeGenTokenizer` as follows: \n"
                 f"`CodeGenTokenizer.from_pretrained('{model_id}')`\nor\n"
                 f"`AutoTokenizer.from_pretrained('{model_id}', use_fast=False)`\n"

src/transformers/models/conditional_detr/image_processing_conditional_detr.py

@@ -1233,7 +1233,7 @@ class ConditionalDetrImageProcessor(BaseImageProcessor):
         if annotations is not None:
             if format == AnnotionFormat.COCO_DETECTION and not valid_coco_detection_annotations(annotations):
                 raise ValueError(
-                    "Invalid COCO detection annotations. Annotations must a dict (single image) of list of dicts"
+                    "Invalid COCO detection annotations. Annotations must a dict (single image) of list of dicts "
                     "(batch of images) with the following keys: `image_id` and `annotations`, with the latter "
                     "being a list of annotations in the COCO format."
                 )

src/transformers/models/data2vec/modeling_data2vec_audio.py

@@ -991,7 +991,7 @@ class Data2VecAudioForCTC(Data2VecAudioPreTrainedModel):
         not be updated during training.
         """
         warnings.warn(
-            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5."
+            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5. "
             "Please use the equivalent `freeze_feature_encoder` method instead.",
             FutureWarning,
         )
@@ -1116,7 +1116,7 @@ class Data2VecAudioForSequenceClassification(Data2VecAudioPreTrainedModel):
         not be updated during training.
         """
         warnings.warn(
-            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5."
+            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5. "
             "Please use the equivalent `freeze_feature_encoder` method instead.",
             FutureWarning,
         )
@@ -1237,7 +1237,7 @@ class Data2VecAudioForAudioFrameClassification(Data2VecAudioPreTrainedModel):
         not be updated during training.
         """
         warnings.warn(
-            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5."
+            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5. "
             "Please use the equivalent `freeze_feature_encoder` method instead.",
             FutureWarning,
         )
@@ -1403,7 +1403,7 @@ class Data2VecAudioForXVector(Data2VecAudioPreTrainedModel):
         not be updated during training.
         """
         warnings.warn(
-            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5."
+            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5. "
             "Please use the equivalent `freeze_feature_encoder` method instead.",
             FutureWarning,
         )

src/transformers/models/deformable_detr/image_processing_deformable_detr.py

@@ -1231,7 +1231,7 @@ class DeformableDetrImageProcessor(BaseImageProcessor):
         if annotations is not None:
             if format == AnnotionFormat.COCO_DETECTION and not valid_coco_detection_annotations(annotations):
                 raise ValueError(
-                    "Invalid COCO detection annotations. Annotations must a dict (single image) of list of dicts"
+                    "Invalid COCO detection annotations. Annotations must a dict (single image) of list of dicts "
                     "(batch of images) with the following keys: `image_id` and `annotations`, with the latter "
                     "being a list of annotations in the COCO format."
                 )

src/transformers/models/deta/image_processing_deta.py

@@ -895,7 +895,7 @@ class DetaImageProcessor(BaseImageProcessor):
         if annotations is not None:
             if format == AnnotionFormat.COCO_DETECTION and not valid_coco_detection_annotations(annotations):
                 raise ValueError(
-                    "Invalid COCO detection annotations. Annotations must a dict (single image) of list of dicts"
+                    "Invalid COCO detection annotations. Annotations must a dict (single image) of list of dicts "
                     "(batch of images) with the following keys: `image_id` and `annotations`, with the latter "
                     "being a list of annotations in the COCO format."
                 )

src/transformers/models/detr/image_processing_detr.py

@@ -1203,7 +1203,7 @@ class DetrImageProcessor(BaseImageProcessor):
         if annotations is not None:
             if format == AnnotionFormat.COCO_DETECTION and not valid_coco_detection_annotations(annotations):
                 raise ValueError(
-                    "Invalid COCO detection annotations. Annotations must a dict (single image) of list of dicts"
+                    "Invalid COCO detection annotations. Annotations must a dict (single image) of list of dicts "
                     "(batch of images) with the following keys: `image_id` and `annotations`, with the latter "
                     "being a list of annotations in the COCO format."
                 )

src/transformers/models/esm/modeling_esmfold.py

@@ -1204,7 +1204,7 @@ class EsmFoldTriangularSelfAttentionBlock(nn.Module):
 
         if sequence_state_dim != self.config.sequence_state_dim:
             raise ValueError(
-                "`sequence_state` last dimension should be equal to `self.sequence_state_dim`. Got"
+                "`sequence_state` last dimension should be equal to `self.sequence_state_dim`. Got "
                 f"{sequence_state_dim} != {self.config.sequence_state_dim}."
             )
         if pairwise_state_dim != self.config.pairwise_state_dim:

src/transformers/models/gptsan_japanese/modeling_gptsan_japanese.py

@@ -770,7 +770,7 @@ class GPTSanJapanesePreTrainedModel(PreTrainedModel):
 
         if decoder_start_token_id is None:
             raise ValueError(
-                "self.model.config.decoder_start_token_id has to be defined. In T5 it is usually set to the pad_token_id."
+                "self.model.config.decoder_start_token_id has to be defined. In T5 it is usually set to the pad_token_id. "
                 "See T5 docs for more information."
             )
 

src/transformers/models/groupvit/modeling_tf_groupvit.py

@@ -58,7 +58,7 @@ if is_tensorflow_probability_available():
         _ = tfp.distributions.Normal(loc=0.0, scale=1.0)
     except ImportError:
         logger.error(
-            "GroupViT models are not usable since `tensorflow_probability` can't be loaded."
+            "GroupViT models are not usable since `tensorflow_probability` can't be loaded. "
             "It seems you have `tensorflow_probability` installed with the wrong tensorflow version."
             "Please try to reinstall it following the instructions here: https://github.com/tensorflow/probability."
         )

src/transformers/models/hubert/modeling_hubert.py

@@ -1183,7 +1183,7 @@ class HubertForCTC(HubertPreTrainedModel):
         not be updated during training.
         """
         warnings.warn(
-            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5."
+            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5. "
             "Please use the equivalent `freeze_feature_encoder` method instead.",
             FutureWarning,
         )
@@ -1316,7 +1316,7 @@ class HubertForSequenceClassification(HubertPreTrainedModel):
         not be updated during training.
         """
         warnings.warn(
-            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5."
+            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5. "
             "Please use the equivalent `freeze_feature_encoder` method instead.",
             FutureWarning,
         )

src/transformers/models/hubert/modeling_tf_hubert.py

@@ -1364,7 +1364,7 @@ class TFHubertForCTC(TFHubertPreTrainedModel):
         not be updated during training.
         """
         warnings.warn(
-            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5."
+            "The method `freeze_feature_extractor` is deprecated and will be removed in Transformers v5. "
             "Please use the equivalent `freeze_feature_encoder` method instead.",
             FutureWarning,
         )

src/transformers/models/idefics/vision.py

@@ -115,8 +115,8 @@ class IdeficsVisionEmbeddings(nn.Module):
         fp32_upcasting = patch_pos_embed.dtype == torch.bfloat16
         if fp32_upcasting:
             logger.warning_once(
-                "Upcasting patch_pos_embed to fp32 for interpolation since `upsample_bicubic2d_out_frame` in nn.functional.interpolate"
-                "is not implemented for 'torch.bfloat16' dtype. This will result in a slight overhead"
+                "Upcasting patch_pos_embed to fp32 for interpolation since `upsample_bicubic2d_out_frame` in nn.functional.interpolate "
+                "is not implemented for 'torch.bfloat16' dtype. This will result in a slight overhead."
             )
             patch_pos_embed = patch_pos_embed.to(torch.float)
         patch_pos_embed = nn.functional.interpolate(

src/transformers/models/longt5/configuration_longt5.py

@@ -135,7 +135,7 @@ class LongT5Config(PretrainedConfig):
 
         if len(act_info) > 1 and act_info[0] != "gated" or len(act_info) > 2:
             raise ValueError(
-                f"`feed_forward_proj`: {feed_forward_proj} is not a valid activation function of the dense layer."
+                f"`feed_forward_proj`: {feed_forward_proj} is not a valid activation function of the dense layer. "
                 "Please make sure `feed_forward_proj` is of the format `gated-{ACT_FN}` or `{ACT_FN}`, e.g. "
                 "'gated-gelu' or 'relu'"
             )

src/transformers/models/longt5/modeling_longt5.py

@@ -1352,7 +1352,7 @@ class LongT5PreTrainedModel(PreTrainedModel):
 
         if decoder_start_token_id is None:
             raise ValueError(
-                "self.model.config.decoder_start_token_id has to be defined. In LongT5 it is usually set to the pad_token_id."
+                "self.model.config.decoder_start_token_id has to be defined. In LongT5 it is usually set to the pad_token_id. "
                 "See LongT5 docs for more information."
             )
 

src/transformers/models/mt5/configuration_mt5.py

@@ -129,7 +129,7 @@ class MT5Config(PretrainedConfig):
 
         if len(act_info) > 1 and act_info[0] != "gated" or len(act_info) > 2:
             raise ValueError(
-                f"`feed_forward_proj`: {feed_forward_proj} is not a valid activation function of the dense layer."
+                f"`feed_forward_proj`: {feed_forward_proj} is not a valid activation function of the dense layer. "
                 "Please make sure `feed_forward_proj` is of the format `gated-{ACT_FN}` or `{ACT_FN}`, e.g. "
                 "'gated-gelu' or 'relu'"
             )

src/transformers/models/mt5/modeling_mt5.py

@@ -855,7 +855,7 @@ class MT5PreTrainedModel(PreTrainedModel):
 
         if decoder_start_token_id is None:
             raise ValueError(
-                "self.model.config.decoder_start_token_id has to be defined. In MT5 it is usually set to the pad_token_id."
+                "self.model.config.decoder_start_token_id has to be defined. In MT5 it is usually set to the pad_token_id. "
                 "See MT5 docs for more information."
             )
 

src/transformers/models/musicgen/modeling_musicgen.py

@@ -1428,7 +1428,7 @@ class MusicgenForCausalLM(MusicgenPreTrainedModel):
 
         else:
             raise ValueError(
-                "Got incompatible mode for generation, should be one of greedy or sampling."
+                "Got incompatible mode for generation, should be one of greedy or sampling. "
                 "Ensure that beam search is de-activated by setting `num_beams=1` and `num_beam_groups=1`."
             )
 
@@ -1453,7 +1453,7 @@ class MusicgenForCausalLM(MusicgenPreTrainedModel):
 
 
 @add_start_docstrings(
-    "The composite MusicGen model with a text encoder, audio encoder and Musicgen decoder,"
+    "The composite MusicGen model with a text encoder, audio encoder and Musicgen decoder, "
     "for music generation tasks with one or both of text and audio prompts.",
     MUSICGEN_START_DOCSTRING,
 )
@@ -2475,7 +2475,7 @@ class MusicgenForConditionalGeneration(PreTrainedModel):
 
         else:
             raise ValueError(
-                "Got incompatible mode for generation, should be one of greedy or sampling."
+                "Got incompatible mode for generation, should be one of greedy or sampling. "
                 "Ensure that beam search is de-activated by setting `num_beams=1` and `num_beam_groups=1`."
             )
 

src/transformers/models/oneformer/convert_to_hf_oneformer.py

@@ -1118,7 +1118,7 @@ if __name__ == "__main__":
         required=True,
         type=Path,
         help=(
-            "A path to OneFormer's original implementation directory. You can download from here:"
+            "A path to OneFormer's original implementation directory. You can download from here: "
             "https://github.com/SHI-Labs/OneFormer"
         ),
     )

src/transformers/models/pix2struct/modeling_pix2struct.py

@@ -481,7 +481,7 @@ class Pix2StructPreTrainedModel(PreTrainedModel):
 
         if decoder_start_token_id is None:
             raise ValueError(
-                "self.model.config.decoder_start_token_id has to be defined. In Pix2Struct it is usually set to the pad_token_id."
+                "self.model.config.decoder_start_token_id has to be defined. In Pix2Struct it is usually set to the pad_token_id. "
                 "See Pix2Struct docs for more information."
             )