Broken links fixed related to datasets docs (#27569)

fixed the broken links belogs to dataset library of transformers

examples/flax/image-captioning/README.md

@@ -10,7 +10,7 @@ way which enables simple and efficient model parallelism.
 `run_image_captioning_flax.py` is a lightweight example of how to download and preprocess a dataset from the 🤗 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 and you also will find examples of these below.
+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.
 
 ### Download COCO dataset (2017)
 This example uses COCO dataset (2017) through a custom dataset script, which requires users to manually download the

examples/flax/image-captioning/run_image_captioning_flax.py

@@ -494,7 +494,7 @@ 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
     model = FlaxVisionEncoderDecoderModel.from_pretrained(

examples/flax/language-modeling/run_bart_dlm_flax.py

@@ -589,7 +589,7 @@ def main():
                 num_proc=data_args.preprocessing_num_workers,
             )
     # 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/flax/language-modeling/run_clm_flax.py

@@ -484,7 +484,7 @@ def main():
                 num_proc=data_args.preprocessing_num_workers,
             )
     # 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/flax/language-modeling/run_mlm_flax.py

@@ -516,7 +516,7 @@ def main():
                 num_proc=data_args.preprocessing_num_workers,
             )
     # 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/flax/language-modeling/run_t5_mlm_flax.py

@@ -630,7 +630,7 @@ def main():
                 num_proc=data_args.preprocessing_num_workers,
             )
     # 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/flax/question-answering/run_qa.py

@@ -536,7 +536,7 @@ 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.
     # endregion
 
     # region Load pretrained model and tokenizer

examples/flax/summarization/README.md

@@ -9,7 +9,7 @@ way which enables simple and efficient model parallelism.
 
 `run_summarization_flax.py` is a lightweight example of how to download and preprocess a dataset from the 🤗 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 and you also will find examples of these below.
+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.
 
 ### Train the model
 Next we can run the example script to train the model:

examples/flax/summarization/run_summarization_flax.py

@@ -521,7 +521,7 @@ 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/flax/text-classification/run_flax_glue.py

@@ -410,7 +410,7 @@ 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:
@@ -427,7 +427,7 @@ 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/flax/token-classification/run_flax_ner.py

@@ -465,7 +465,7 @@ 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.
 
     if raw_datasets["train"] is not None:
         column_names = raw_datasets["train"].column_names

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
     #

examples/research_projects/jax-projects/README.md

@@ -227,7 +227,7 @@ the forum and making use of the [🤗 hub](http://huggingface.co/) to have a ver
 control for your models and training logs.
 - When debugging, it is important that the debugging cycle is kept as short as possible to 
 be able to effectively debug. *E.g.* if there is a problem with your training script, 
-you should run it with just a couple of hundreds of examples and not the whole dataset script. This can be done by either making use of [datasets streaming](https://huggingface.co/docs/datasets/master/dataset_streaming.html?highlight=streaming) or by selecting just the first 
+you should run it with just a couple of hundreds of examples and not the whole dataset script. This can be done by either making use of [datasets streaming](https://huggingface.co/docs/datasets/master/dataset_streaming?highlight=streaming) or by selecting just the first 
 X number of data samples after loading:
 
 ```python

examples/research_projects/jax-projects/dataset-streaming/README.md

@@ -23,7 +23,7 @@ JAX/Flax allows you to trace pure functions and compile them into efficient, fus
 Models written in JAX/Flax are **immutable** and updated in a purely functional
 way which enables simple and efficient model parallelism.
 
-All of the following examples make use of [dataset streaming](https://huggingface.co/docs/datasets/master/dataset_streaming.html), therefore allowing to train models on massive datasets\
+All of the following examples make use of [dataset streaming](https://huggingface.co/docs/datasets/master/dataset_streaming), therefore allowing to train models on massive datasets\
 without ever having to download the full dataset.
 
 ## Masked language modeling

examples/research_projects/jax-projects/model_parallel/run_clm_mp.py

@@ -304,7 +304,7 @@ def main():
             extension = "text"
         dataset = 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.
 
     # Load pretrained config and tokenizer
     if model_args.config_name:

examples/research_projects/jax-projects/wav2vec2/README.md

@@ -10,7 +10,7 @@ way which enables simple and efficient model parallelism.
 
 `run_wav2vec2_pretrain_flax.py` is a lightweight example of how to download and preprocess a dataset from the 🤗 Datasets library or use your own files (jsonlines or csv), then pretrain the wav2vec2 architectures above on it.
 
-For custom datasets in `jsonlines` format please see: [the Datasets documentation](https://huggingface.co/docs/datasets/loading_datasets.html#json-files) and you also will find examples of these below.
+For custom datasets in `jsonlines` format please see: [the Datasets documentation](https://huggingface.co/docs/datasets/loading_datasets#json-files) and you also will find examples of these below.
 
 Let's start by creating a model repository to save the trained model and logs.
 Here we call the model `"wav2vec2-base-robust"`, but you can change the model name as you like.

examples/research_projects/luke/run_luke_ner_no_trainer.py

@@ -294,7 +294,7 @@ 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/research_projects/mlm_wwm/run_mlm_wwm.py

@@ -278,7 +278,7 @@ def main():
             extension = "text"
         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/research_projects/performer/run_mlm_performer.py

@@ -524,7 +524,7 @@ if __name__ == "__main__":
             extension = "text"
         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/research_projects/quantization-qdqbert/evaluate-hf-trt-qa.py

@@ -272,7 +272,7 @@ if args.dataset_name is not None:
 else:
     raise ValueError("Evaluation requires a dataset name")
 # 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.
 
 # Preprocessing the datasets.
 # Preprocessing is slighlty different for training and evaluation.

examples/research_projects/quantization-qdqbert/run_quant_qa.py

@@ -308,7 +308,7 @@ def main():
             extension = data_args.test_file.split(".")[-1]
         raw_datasets = load_dataset(extension, data_files=data_files, field="data", 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.
 
     # set default quantization parameters before building model
     quant_trainer.set_default_quantizers(quant_trainer_args)

examples/research_projects/rag-end2end-retriever/use_own_knowledge_dataset.py

@@ -65,7 +65,7 @@ def main(
         "csv", data_files=[rag_example_args.csv_path], split="train", delimiter="\t", column_names=["title", "text"]
     )
 
-    # More info about loading csv files in the documentation: https://huggingface.co/docs/datasets/loading_datasets.html?highlight=csv#csv-files
+    # More info about loading csv files in the documentation: https://huggingface.co/docs/datasets/loading_datasets?highlight=csv#csv-files
 
     # Then split the documents into passages of 100 words
     dataset = dataset.map(split_documents, batched=True, num_proc=processing_args.num_proc)

examples/research_projects/rag/use_own_knowledge_dataset.py

@@ -73,7 +73,7 @@ def main(
         "csv", data_files=[rag_example_args.csv_path], split="train", delimiter="\t", column_names=["title", "text"]
     )
 
-    # More info about loading csv files in the documentation: https://huggingface.co/docs/datasets/loading_datasets.html?highlight=csv#csv-files
+    # More info about loading csv files in the documentation: https://huggingface.co/docs/datasets/loading_datasets?highlight=csv#csv-files
 
     # Then split the documents into passages of 100 words
     dataset = dataset.map(split_documents, batched=True, num_proc=processing_args.num_proc)

examples/research_projects/robust-speech-event/README.md

@@ -112,7 +112,7 @@ Hugging Face Hub for additional audio data, for example by selecting the categor
 ["speech-processing"](https://huggingface.co/datasets?task_categories=task_categories:speech-processing&sort=downloads).
 All datasets that are available on the Hub can be downloaded via the 🤗 Datasets library in the same way Common Voice is downloaded.
 If one wants to combine multiple datasets for training, it might make sense to take a look at 
-the [`interleave_datasets`](https://huggingface.co/docs/datasets/package_reference/main_classes.html?highlight=interleave#datasets.interleave_datasets) function.
+the [`interleave_datasets`](https://huggingface.co/docs/datasets/package_reference/main_classes?highlight=interleave#datasets.interleave_datasets) function.
 
 In addition, participants can also make use of their audio data. Here, please make sure that you **are allowed to use the audio data**. E.g., if audio data 
 is taken from media platforms, such as YouTube, it should be verified that the media platform and the owner of the data have given her/his approval to use the audio 

examples/research_projects/tapex/run_tabfact_with_tapex.py

@@ -277,7 +277,7 @@ def main():
             # Loading a dataset from local json files
             raw_datasets = load_dataset("json", data_files=data_files, cache_dir=model_args.cache_dir)
     # 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
     label_list = raw_datasets["train"].features["label"].names

examples/research_projects/tapex/run_wikisql_with_tapex.py

@@ -317,7 +317,7 @@ def main():
         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.
 
     # Load pretrained model and tokenizer
     #

examples/research_projects/tapex/run_wikitablequestions_with_tapex.py

@@ -315,7 +315,7 @@ def main():
         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.
 
     # Load pretrained model and tokenizer
     #

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

@@ -361,7 +361,7 @@ 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/tensorflow/image-classification/run_image_classification.py

@@ -316,7 +316,7 @@ def main():
             task="image-classification",
         )
     # 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.
 
     # Prepare label mappings.
     # We'll include these in the model's config to get human readable labels in the Inference API.

examples/tensorflow/language-modeling/run_clm.py

@@ -371,7 +371,7 @@ def main():
                 **dataset_args,
             )
     # 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.
     # endregion
 
     # region Load pretrained model and tokenizer

examples/tensorflow/language-modeling/run_mlm.py

@@ -353,7 +353,7 @@ 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.
     # endregion
 
     # region Load pretrained model and tokenizer

examples/tensorflow/multiple-choice/run_swag.py

@@ -338,7 +338,7 @@ 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.
 
     # When using your own dataset or a different dataset from swag, you will probably need to change this.
     ending_names = [f"ending{i}" for i in range(4)]

examples/tensorflow/question-answering/run_qa.py

@@ -352,7 +352,7 @@ 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.
     # endregion
 
     # region Load pretrained model and tokenizer

examples/tensorflow/summarization/run_summarization.py

@@ -401,7 +401,7 @@ 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.
     # endregion
 
     # region Load model config and tokenizer

examples/tensorflow/text-classification/run_glue.py

@@ -271,7 +271,7 @@ 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.
 
     is_regression = data_args.task_name == "stsb"
     if not is_regression:

examples/tensorflow/text-classification/run_text_classification.py

@@ -290,7 +290,7 @@ def main():
         # Loading a dataset from local json files
         datasets = load_dataset("json", data_files=data_files, cache_dir=model_args.cache_dir)
     # 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.
     # endregion
 
     # region Label preprocessing

examples/tensorflow/token-classification/run_ner.py

@@ -269,7 +269,7 @@ 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.
 
     if raw_datasets["train"] is not None:
         column_names = raw_datasets["train"].column_names