docs: update link huggingface map (#26077)

examples/pytorch/language-modeling/run_clm.py

@@ -533,7 +533,7 @@ def main():
     # to preprocess.
     #
     # To speed up this part, we use multiprocessing. See the documentation of the map method for more information:
-    # https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.map
+    # https://huggingface.co/docs/datasets/process#map
 
     with training_args.main_process_first(desc="grouping texts together"):
         if not data_args.streaming:

examples/pytorch/language-modeling/run_clm_no_trainer.py

@@ -473,7 +473,7 @@ def main():
     # to preprocess.
     #
     # To speed up this part, we use multiprocessing. See the documentation of the map method for more information:
-    # https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.map
+    # https://huggingface.co/docs/datasets/process#map
 
     with accelerator.main_process_first():
         lm_datasets = tokenized_datasets.map(

examples/pytorch/language-modeling/run_mlm.py

@@ -547,7 +547,7 @@ def main():
         # might be slower to preprocess.
         #
         # To speed up this part, we use multiprocessing. See the documentation of the map method for more information:
-        # https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.map
+        # https://huggingface.co/docs/datasets/process#map
 
         with training_args.main_process_first(desc="grouping texts together"):
             if not data_args.streaming:

examples/pytorch/language-modeling/run_mlm_no_trainer.py

@@ -504,7 +504,7 @@ def main():
         # might be slower to preprocess.
         #
         # To speed up this part, we use multiprocessing. See the documentation of the map method for more information:
-        # https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.map
+        # https://huggingface.co/docs/datasets/process#map
 
         with accelerator.main_process_first():
             tokenized_datasets = tokenized_datasets.map(

examples/pytorch/language-modeling/run_plm.py

@@ -478,7 +478,7 @@ def main():
         # might be slower to preprocess.
         #
         # To speed up this part, we use multiprocessing. See the documentation of the map method for more information:
-        # https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.map
+        # https://huggingface.co/docs/datasets/process#map
 
         with training_args.main_process_first(desc="grouping texts together"):
             tokenized_datasets = tokenized_datasets.map(