Broken links fixed related to datasets docs (#27569)

fixed the broken links belogs to dataset library of transformers

examples/pytorch/contrastive-image-text/run_clip.py

@@ -340,7 +340,7 @@ def main():
             token=model_args.token,
         )
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # 5. Load pretrained model, tokenizer, and image processor
     if model_args.tokenizer_name:

examples/pytorch/language-modeling/run_clm.py

@@ -388,7 +388,7 @@ def main():
             )
 
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/language-modeling/run_clm_no_trainer.py

@@ -368,7 +368,7 @@ def main():
             )
 
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/language-modeling/run_mlm.py

@@ -382,7 +382,7 @@ def main():
             )
 
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/language-modeling/run_mlm_no_trainer.py

@@ -371,7 +371,7 @@ def main():
             )
 
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/language-modeling/run_plm.py

@@ -352,7 +352,7 @@ def main():
             )
 
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/multiple-choice/run_swag.py

@@ -329,7 +329,7 @@ def main():
             token=model_args.token,
         )
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
 

examples/pytorch/multiple-choice/run_swag_no_trainer.py

@@ -366,7 +366,7 @@ def main():
         for split in raw_datasets.keys():
             raw_datasets[split] = raw_datasets[split].select(range(100))
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     if raw_datasets["train"] is not None:
         column_names = raw_datasets["train"].column_names

examples/pytorch/question-answering/run_qa.py

@@ -337,7 +337,7 @@ def main():
             token=model_args.token,
         )
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/question-answering/run_qa_beam_search.py

@@ -325,7 +325,7 @@ def main():
             token=model_args.token,
         )
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/question-answering/run_qa_beam_search_no_trainer.py

@@ -369,7 +369,7 @@ def main():
         extension = args.train_file.split(".")[-1]
         raw_datasets = load_dataset(extension, data_files=data_files, field="data")
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/question-answering/run_qa_no_trainer.py

@@ -417,7 +417,7 @@ def main():
         extension = args.train_file.split(".")[-1]
         raw_datasets = load_dataset(extension, data_files=data_files, field="data")
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/question-answering/run_seq2seq_qa.py

@@ -382,7 +382,7 @@ def main():
             token=model_args.token,
         )
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/speech-recognition/README.md

@@ -134,7 +134,7 @@ of **0.36**.
 
 ### Multi GPU CTC with Dataset Streaming
 
-The following command shows how to use [Dataset Streaming mode](https://huggingface.co/docs/datasets/dataset_streaming.html)
+The following command shows how to use [Dataset Streaming mode](https://huggingface.co/docs/datasets/dataset_streaming)
 to fine-tune [XLS-R](https://huggingface.co/transformers/main/model_doc/xls_r.html) 
 on [Common Voice](https://huggingface.co/datasets/common_voice) using 4 GPUs in half-precision.
 

examples/pytorch/summarization/README.md

@@ -33,7 +33,7 @@ For the old `finetune_trainer.py` and related utils, see [`examples/legacy/seq2s
 
 `run_summarization.py` is a lightweight example of how to download and preprocess a dataset from the [🤗 Datasets](https://github.com/huggingface/datasets) library or use your own files (jsonlines or csv), then fine-tune one of the architectures above on it.
 
-For custom datasets in `jsonlines` format please see: https://huggingface.co/docs/datasets/loading_datasets.html#json-files
+For custom datasets in `jsonlines` format please see: https://huggingface.co/docs/datasets/loading_datasets#json-files
 and you also will find examples of these below.
 
 ## With Trainer

examples/pytorch/summarization/run_summarization.py

@@ -432,7 +432,7 @@ def main():
             token=model_args.token,
         )
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/summarization/run_summarization_no_trainer.py

@@ -409,7 +409,7 @@ def main():
         extension = args.train_file.split(".")[-1]
         raw_datasets = load_dataset(extension, data_files=data_files)
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #

examples/pytorch/text-classification/run_classification.py

@@ -396,7 +396,7 @@ def main():
             )
 
     # See more about loading any type of standard or custom dataset at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     if data_args.remove_splits is not None:
         for split in data_args.remove_splits.split(","):

examples/pytorch/text-classification/run_glue.py

@@ -355,7 +355,7 @@ def main():
                 token=model_args.token,
             )
     # See more about loading any type of standard or custom dataset at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Labels
     if data_args.task_name is not None:
@@ -372,7 +372,7 @@ def main():
             num_labels = 1
         else:
             # A useful fast method:
-            # https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.unique
+            # https://huggingface.co/docs/datasets/package_reference/main_classes#datasets.Dataset.unique
             label_list = raw_datasets["train"].unique("label")
             label_list.sort()  # Let's sort it for determinism
             num_labels = len(label_list)

examples/pytorch/text-classification/run_glue_no_trainer.py

@@ -293,7 +293,7 @@ def main():
         extension = (args.train_file if args.train_file is not None else args.validation_file).split(".")[-1]
         raw_datasets = load_dataset(extension, data_files=data_files)
     # See more about loading any type of standard or custom dataset at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Labels
     if args.task_name is not None:

examples/pytorch/token-classification/run_ner.py

@@ -318,7 +318,7 @@ def main():
         extension = data_args.train_file.split(".")[-1]
         raw_datasets = load_dataset(extension, data_files=data_files, cache_dir=model_args.cache_dir)
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     if training_args.do_train:
         column_names = raw_datasets["train"].column_names

examples/pytorch/token-classification/run_ner_no_trainer.py

@@ -348,7 +348,7 @@ def main():
         for split in raw_datasets.keys():
             raw_datasets[split] = raw_datasets[split].select(range(100))
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     if raw_datasets["train"] is not None:
         column_names = raw_datasets["train"].column_names

examples/pytorch/translation/README.md

@@ -33,7 +33,7 @@ For the old `finetune_trainer.py` and related utils, see [`examples/legacy/seq2s
 
 `run_translation.py` is a lightweight examples of how to download and preprocess a dataset from the [🤗 Datasets](https://github.com/huggingface/datasets) library or use your own files (jsonlines or csv), then fine-tune one of the architectures above on it.
 
-For custom datasets in `jsonlines` format please see: https://huggingface.co/docs/datasets/loading_datasets.html#json-files
+For custom datasets in `jsonlines` format please see: https://huggingface.co/docs/datasets/loading_datasets#json-files
 and you also will find examples of these below.
 
 

examples/pytorch/translation/run_translation_no_trainer.py

@@ -389,7 +389,7 @@ def main():
         extension = args.train_file.split(".")[-1]
         raw_datasets = load_dataset(extension, data_files=data_files)
     # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
-    # https://huggingface.co/docs/datasets/loading_datasets.html.
+    # https://huggingface.co/docs/datasets/loading_datasets.
 
     # Load pretrained model and tokenizer
     #