diff --git a/chapters/de/chapter3/2.mdx b/chapters/de/chapter3/2.mdx
index 1c9aaad0a..b9d38dfa9 100644
--- a/chapters/de/chapter3/2.mdx
+++ b/chapters/de/chapter3/2.mdx
@@ -95,7 +95,7 @@ Die Bibliothek 🤗 Datasets bietet einen leichten Befehl zum Herunterladen und
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/de/chapter3/3.mdx b/chapters/de/chapter3/3.mdx
index ef20299a4..ab6188961 100644
--- a/chapters/de/chapter3/3.mdx
+++ b/chapters/de/chapter3/3.mdx
@@ -19,7 +19,7 @@ In den folgenden Code-Beispielen wird davon ausgegangen, dass du die Beispiele a
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/de/chapter3/3_tf.mdx b/chapters/de/chapter3/3_tf.mdx
index 4d4cbb18b..efd6fcd3c 100644
--- a/chapters/de/chapter3/3_tf.mdx
+++ b/chapters/de/chapter3/3_tf.mdx
@@ -18,7 +18,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/de/chapter3/4.mdx b/chapters/de/chapter3/4.mdx
index 6395de2e0..841ad494f 100644
--- a/chapters/de/chapter3/4.mdx
+++ b/chapters/de/chapter3/4.mdx
@@ -15,7 +15,7 @@ In diesem Abschnitt befassen wir uns damit, wie wir die gleichen Ergebnisse wie
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/en/chapter3/2.mdx b/chapters/en/chapter3/2.mdx
index 232441b84..087134111 100644
--- a/chapters/en/chapter3/2.mdx
+++ b/chapters/en/chapter3/2.mdx
@@ -51,7 +51,7 @@ The 🤗 Datasets library provides a very simple command to download and cache a
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/en/chapter3/3.mdx b/chapters/en/chapter3/3.mdx
index 20c47152c..3db188ea7 100644
--- a/chapters/en/chapter3/3.mdx
+++ b/chapters/en/chapter3/3.mdx
@@ -22,7 +22,7 @@ The code examples below assume you have already executed the examples in the pre
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/en/chapter3/4.mdx b/chapters/en/chapter3/4.mdx
index 2bbcb8e57..065b333b0 100644
--- a/chapters/en/chapter3/4.mdx
+++ b/chapters/en/chapter3/4.mdx
@@ -18,7 +18,7 @@ Now we'll see how to achieve the same results as we did in the last section with
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/en/chapter5/6.mdx b/chapters/en/chapter5/6.mdx
index e7dfbbf49..25c8df033 100644
--- a/chapters/en/chapter5/6.mdx
+++ b/chapters/en/chapter5/6.mdx
@@ -102,7 +102,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/en/chapter5/8.mdx b/chapters/en/chapter5/8.mdx
index 27addf6b6..b49096680 100644
--- a/chapters/en/chapter5/8.mdx
+++ b/chapters/en/chapter5/8.mdx
@@ -38,7 +38,7 @@ Before moving on, though, let's test what you learned in this chapter.
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 Which of the following commands will produce a random sample of 50 elements from `dataset`?
@@ -128,7 +128,7 @@ Which of the following commands will produce a random sample of 50 elements from
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/en/chapter6/2.mdx b/chapters/en/chapter6/2.mdx
index cd50a0c85..b4b7e3991 100644
--- a/chapters/en/chapter6/2.mdx
+++ b/chapters/en/chapter6/2.mdx
@@ -24,7 +24,7 @@ The [🤗 Datasets](https://github.com/huggingface/datasets) library can help us
 from datasets import load_dataset
 
 # This can take a few minutes to load, so grab a coffee or tea while you wait!
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 We can have a look at the training split to see which columns we have access to:
diff --git a/chapters/en/chapter6/8.mdx b/chapters/en/chapter6/8.mdx
index 71bcafbe2..1e7c3192d 100644
--- a/chapters/en/chapter6/8.mdx
+++ b/chapters/en/chapter6/8.mdx
@@ -43,7 +43,7 @@ To train our new tokenizer, we will use a small corpus of text (so the examples
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/en/chapter7/7.mdx b/chapters/en/chapter7/7.mdx
index b708071f3..dce2ddc40 100644
--- a/chapters/en/chapter7/7.mdx
+++ b/chapters/en/chapter7/7.mdx
@@ -46,7 +46,7 @@ As usual, we can download and cache the dataset in just one step thanks to `load
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("squad")
+raw_datasets = load_dataset("rajpurkar/squad")
 ```
 
 We can then have a look at this object to learn more about the SQuAD dataset:
diff --git a/chapters/en/chapter8/4.mdx b/chapters/en/chapter8/4.mdx
index 888073f40..8f7301d44 100644
--- a/chapters/en/chapter8/4.mdx
+++ b/chapters/en/chapter8/4.mdx
@@ -31,7 +31,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -108,7 +108,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -300,7 +300,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -426,7 +426,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -631,7 +631,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/en/chapter8/4_tf.mdx b/chapters/en/chapter8/4_tf.mdx
index 9358bcba9..af90b869b 100644
--- a/chapters/en/chapter8/4_tf.mdx
+++ b/chapters/en/chapter8/4_tf.mdx
@@ -29,7 +29,7 @@ from transformers import (
     TFAutoModelForSequenceClassification,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/es/chapter3/2.mdx b/chapters/es/chapter3/2.mdx
index 7bd2d8fd2..069ad8541 100644
--- a/chapters/es/chapter3/2.mdx
+++ b/chapters/es/chapter3/2.mdx
@@ -98,7 +98,7 @@ La librería 🤗 Datasets provee un comando muy simple para descargar y memoriz
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/es/chapter3/3.mdx b/chapters/es/chapter3/3.mdx
index bb2b0bfb8..2f878647e 100644
--- a/chapters/es/chapter3/3.mdx
+++ b/chapters/es/chapter3/3.mdx
@@ -29,7 +29,7 @@ Los siguientes ejemplos de código suponen que ya has ejecutado los ejemplos de
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/es/chapter3/3_tf.mdx b/chapters/es/chapter3/3_tf.mdx
index 0850b6667..b664e923d 100644
--- a/chapters/es/chapter3/3_tf.mdx
+++ b/chapters/es/chapter3/3_tf.mdx
@@ -28,7 +28,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/es/chapter3/4.mdx b/chapters/es/chapter3/4.mdx
index f223d596b..41a340fee 100644
--- a/chapters/es/chapter3/4.mdx
+++ b/chapters/es/chapter3/4.mdx
@@ -15,7 +15,7 @@ Ahora veremos como obtener los mismos resultados de la última sección sin hace
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/es/chapter5/6.mdx b/chapters/es/chapter5/6.mdx
index fde2e87b4..a57fe7337 100644
--- a/chapters/es/chapter5/6.mdx
+++ b/chapters/es/chapter5/6.mdx
@@ -114,7 +114,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/es/chapter5/8.mdx b/chapters/es/chapter5/8.mdx
index 99f5e0ffd..0ccfd562f 100644
--- a/chapters/es/chapter5/8.mdx
+++ b/chapters/es/chapter5/8.mdx
@@ -38,7 +38,7 @@ Antes de seguir, probemos lo que aprendiste en este capítulo:
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 ¿Cuál de los siguientes comandos a a producir una muestra aleatoria de 50 elementos de `dataset`?
@@ -128,7 +128,7 @@ dataset = load_dataset("glue", "mrpc", split="train")
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/es/chapter6/2.mdx b/chapters/es/chapter6/2.mdx
index 951da5b35..9c5a6b194 100644
--- a/chapters/es/chapter6/2.mdx
+++ b/chapters/es/chapter6/2.mdx
@@ -25,7 +25,7 @@ La librería [🤗 Datasets](https://github.com/huggingface/datasets) nos puede
 from datasets import load_dataset
 
 # Esto puede tomar varios minutos para cargarse, así que ¡Agarra un té o un café mientras esperas!
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 Podemos echar un vistazo a la porción de entrenamiento para ver a qué columnas tenemos acceso:
 
diff --git a/chapters/es/chapter6/8.mdx b/chapters/es/chapter6/8.mdx
index f6fdb1e43..8f487578f 100644
--- a/chapters/es/chapter6/8.mdx
+++ b/chapters/es/chapter6/8.mdx
@@ -43,7 +43,7 @@ Para entrenar nuestro nuevo tokenizador, usaremos un pequeño corpus de texto (p
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/fa/chapter3/2.mdx b/chapters/fa/chapter3/2.mdx
index 433823fe8..e3bb7b478 100644
--- a/chapters/fa/chapter3/2.mdx
+++ b/chapters/fa/chapter3/2.mdx
@@ -111,7 +111,7 @@ model.train_on_batch(batch, labels)
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/fa/chapter3/3.mdx b/chapters/fa/chapter3/3.mdx
index 3126fa20b..33e092019 100644
--- a/chapters/fa/chapter3/3.mdx
+++ b/chapters/fa/chapter3/3.mdx
@@ -24,7 +24,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/fa/chapter3/3_tf.mdx b/chapters/fa/chapter3/3_tf.mdx
index 13125f967..963669100 100644
--- a/chapters/fa/chapter3/3_tf.mdx
+++ b/chapters/fa/chapter3/3_tf.mdx
@@ -22,7 +22,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/fr/chapter3/2.mdx b/chapters/fr/chapter3/2.mdx
index ffec8b9e4..09b42c8c0 100644
--- a/chapters/fr/chapter3/2.mdx
+++ b/chapters/fr/chapter3/2.mdx
@@ -103,7 +103,7 @@ La bibliothèque 🤗 *Datasets* propose une commande très simple pour téléch
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/fr/chapter3/3.mdx b/chapters/fr/chapter3/3.mdx
index 36e2ec914..305fd68cd 100644
--- a/chapters/fr/chapter3/3.mdx
+++ b/chapters/fr/chapter3/3.mdx
@@ -21,7 +21,7 @@ Les exemples de code ci-dessous supposent que vous avez déjà exécuté les exe
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/fr/chapter3/3_tf.mdx b/chapters/fr/chapter3/3_tf.mdx
index 3188f3a53..51ac8530f 100644
--- a/chapters/fr/chapter3/3_tf.mdx
+++ b/chapters/fr/chapter3/3_tf.mdx
@@ -20,7 +20,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/fr/chapter3/4.mdx b/chapters/fr/chapter3/4.mdx
index dd4fb0e0e..c076c3e7a 100644
--- a/chapters/fr/chapter3/4.mdx
+++ b/chapters/fr/chapter3/4.mdx
@@ -17,7 +17,7 @@ Maintenant nous allons voir comment obtenir les mêmes résultats que dans la de
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/fr/chapter5/6.mdx b/chapters/fr/chapter5/6.mdx
index 9f4647b2a..dbb250472 100644
--- a/chapters/fr/chapter5/6.mdx
+++ b/chapters/fr/chapter5/6.mdx
@@ -117,7 +117,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/fr/chapter5/8.mdx b/chapters/fr/chapter5/8.mdx
index 6abf66b0a..214bf1306 100644
--- a/chapters/fr/chapter5/8.mdx
+++ b/chapters/fr/chapter5/8.mdx
@@ -38,7 +38,7 @@ Avant de poursuivre, testons ce que vous avez appris dans ce chapitre.
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 Laquelle des commandes suivantes produira un échantillon aléatoire de 50 éléments à partir de `dataset` ?
@@ -128,7 +128,7 @@ Laquelle des commandes suivantes produira un échantillon aléatoire de 50 élé
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/fr/chapter6/2.mdx b/chapters/fr/chapter6/2.mdx
index fbcaccbe3..a4e7ea993 100644
--- a/chapters/fr/chapter6/2.mdx
+++ b/chapters/fr/chapter6/2.mdx
@@ -26,7 +26,7 @@ La bibliothèque [🤗 *Datasets*](https://github.com/huggingface/datasets) peut
 from datasets import load_dataset
 
 # Cela peut prendre quelques minutes alors prenez un thé ou un café pendant que vous patientez !
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 Nous pouvons jeter un coup d'œil au jeu d'entraînement pour voir quelles sont les colonnes auxquelles nous avons accès :
diff --git a/chapters/fr/chapter6/8.mdx b/chapters/fr/chapter6/8.mdx
index 44dd5298d..788384d72 100644
--- a/chapters/fr/chapter6/8.mdx
+++ b/chapters/fr/chapter6/8.mdx
@@ -47,7 +47,7 @@ Pour entraîner notre nouveau *tokenizer*, nous utiliserons un petit corpus de t
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/fr/chapter7/7.mdx b/chapters/fr/chapter7/7.mdx
index f3c06be25..fda7c8a5e 100644
--- a/chapters/fr/chapter7/7.mdx
+++ b/chapters/fr/chapter7/7.mdx
@@ -47,7 +47,7 @@ Comme d'habitude, nous pouvons télécharger et mettre en cache le jeu de donné
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("squad")
+raw_datasets = load_dataset("rajpurkar/squad")
 ```
 
 Nous pouvons jeter un coup d'œil à cet objet pour en savoir plus sur le jeu de données SQuAD :
diff --git a/chapters/fr/chapter8/4.mdx b/chapters/fr/chapter8/4.mdx
index 95b46f9e4..45df78142 100644
--- a/chapters/fr/chapter8/4.mdx
+++ b/chapters/fr/chapter8/4.mdx
@@ -33,7 +33,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -110,7 +110,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -302,7 +302,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -429,7 +429,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -634,7 +634,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/fr/chapter8/4_tf.mdx b/chapters/fr/chapter8/4_tf.mdx
index 4c776415e..65d1e936d 100644
--- a/chapters/fr/chapter8/4_tf.mdx
+++ b/chapters/fr/chapter8/4_tf.mdx
@@ -33,7 +33,7 @@ from transformers import (
     TFAutoModelForSequenceClassification,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/hi/chapter3/2.mdx b/chapters/hi/chapter3/2.mdx
index 5a9b28acf..3881fcd0c 100644
--- a/chapters/hi/chapter3/2.mdx
+++ b/chapters/hi/chapter3/2.mdx
@@ -95,7 +95,7 @@ model.train_on_batch(batch, labels)
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/hi/chapter3/3.mdx b/chapters/hi/chapter3/3.mdx
index 387e2f799..a2c1530de 100644
--- a/chapters/hi/chapter3/3.mdx
+++ b/chapters/hi/chapter3/3.mdx
@@ -19,7 +19,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/hi/chapter3/3_tf.mdx b/chapters/hi/chapter3/3_tf.mdx
index 38072f990..87ae60719 100644
--- a/chapters/hi/chapter3/3_tf.mdx
+++ b/chapters/hi/chapter3/3_tf.mdx
@@ -18,7 +18,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/hi/chapter3/4.mdx b/chapters/hi/chapter3/4.mdx
index 5bb87dfca..2c7412441 100644
--- a/chapters/hi/chapter3/4.mdx
+++ b/chapters/hi/chapter3/4.mdx
@@ -15,7 +15,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/it/chapter3/2.mdx b/chapters/it/chapter3/2.mdx
index c04650429..3adb362e3 100644
--- a/chapters/it/chapter3/2.mdx
+++ b/chapters/it/chapter3/2.mdx
@@ -95,7 +95,7 @@ La libreria 🤗 Datasets fornisce un comando molto semplice per scaricare e met
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/it/chapter3/3.mdx b/chapters/it/chapter3/3.mdx
index 878a546ef..fd2a370c6 100644
--- a/chapters/it/chapter3/3.mdx
+++ b/chapters/it/chapter3/3.mdx
@@ -19,7 +19,7 @@ Gli esempi di codice qui sotto partono dal presupposto che gli esempi nella sezi
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/it/chapter3/3_tf.mdx b/chapters/it/chapter3/3_tf.mdx
index 567399dc8..7091028ac 100644
--- a/chapters/it/chapter3/3_tf.mdx
+++ b/chapters/it/chapter3/3_tf.mdx
@@ -18,7 +18,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/it/chapter3/4.mdx b/chapters/it/chapter3/4.mdx
index e0836f604..3a1e9d170 100644
--- a/chapters/it/chapter3/4.mdx
+++ b/chapters/it/chapter3/4.mdx
@@ -15,7 +15,7 @@ Ora vedremo come ottenere gli stessi risultati della sezione precedente senza ut
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/it/chapter5/6.mdx b/chapters/it/chapter5/6.mdx
index 86fd6c62e..c44ee72e8 100644
--- a/chapters/it/chapter5/6.mdx
+++ b/chapters/it/chapter5/6.mdx
@@ -114,7 +114,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/it/chapter5/8.mdx b/chapters/it/chapter5/8.mdx
index 15288bf23..c8c94801e 100644
--- a/chapters/it/chapter5/8.mdx
+++ b/chapters/it/chapter5/8.mdx
@@ -38,7 +38,7 @@ Prima di andare oltre, mettiamo alla prova ciò che hai imparato in questo capit
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 Quale dei comandi seguenti produce un campione di 50 elementi casuali da `dataset`?
@@ -127,7 +127,7 @@ Quale dei comandi seguenti produce un campione di 50 elementi casuali da `datase
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/it/chapter8/4.mdx b/chapters/it/chapter8/4.mdx
index dbe02325c..6db449356 100644
--- a/chapters/it/chapter8/4.mdx
+++ b/chapters/it/chapter8/4.mdx
@@ -30,7 +30,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -106,7 +106,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -297,7 +297,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -422,7 +422,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -626,7 +626,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/it/chapter8/4_tf.mdx b/chapters/it/chapter8/4_tf.mdx
index cdc16e2bc..7ac26fac8 100644
--- a/chapters/it/chapter8/4_tf.mdx
+++ b/chapters/it/chapter8/4_tf.mdx
@@ -28,7 +28,7 @@ from transformers import (
     TFAutoModelForSequenceClassification,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/ja/chapter7/7.mdx b/chapters/ja/chapter7/7.mdx
index 04159df08..65e3c5e2f 100644
--- a/chapters/ja/chapter7/7.mdx
+++ b/chapters/ja/chapter7/7.mdx
@@ -49,7 +49,7 @@
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("squad")
+raw_datasets = load_dataset("rajpurkar/squad")
 ```
 
 そして、このオブジェクトを見て、SQuADデータセットについてもっと知ることができます。
diff --git a/chapters/ko/chapter3/2.mdx b/chapters/ko/chapter3/2.mdx
index 25b180f3f..3b51e7024 100644
--- a/chapters/ko/chapter3/2.mdx
+++ b/chapters/ko/chapter3/2.mdx
@@ -51,7 +51,7 @@ Hub에는 모델뿐만 아니라 다양한 언어로 된 여러 데이터 세트
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/ko/chapter3/3.mdx b/chapters/ko/chapter3/3.mdx
index 5f3604aa4..753976ed5 100644
--- a/chapters/ko/chapter3/3.mdx
+++ b/chapters/ko/chapter3/3.mdx
@@ -22,7 +22,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/ko/chapter8/4.mdx b/chapters/ko/chapter8/4.mdx
index 878ccc25e..6c17a1894 100644
--- a/chapters/ko/chapter8/4.mdx
+++ b/chapters/ko/chapter8/4.mdx
@@ -31,7 +31,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -107,7 +107,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -296,7 +296,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -416,7 +416,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -613,7 +613,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/ko/chapter8/4_tf.mdx b/chapters/ko/chapter8/4_tf.mdx
index 2f53385da..8f36d00e6 100644
--- a/chapters/ko/chapter8/4_tf.mdx
+++ b/chapters/ko/chapter8/4_tf.mdx
@@ -29,7 +29,7 @@ from transformers import (
     TFAutoModelForSequenceClassification,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/my/chapter3/2.mdx b/chapters/my/chapter3/2.mdx
index 12925ae06..5ec44cfc3 100644
--- a/chapters/my/chapter3/2.mdx
+++ b/chapters/my/chapter3/2.mdx
@@ -52,7 +52,7 @@ Hub မှာ model တွေပဲ ပါဝင်တာ မဟုတ်ပါ
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/my/chapter3/3.mdx b/chapters/my/chapter3/3.mdx
index 65029db63..a8f59584b 100644
--- a/chapters/my/chapter3/3.mdx
+++ b/chapters/my/chapter3/3.mdx
@@ -22,7 +22,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/my/chapter3/4.mdx b/chapters/my/chapter3/4.mdx
index ce8b440dd..6a019a61f 100644
--- a/chapters/my/chapter3/4.mdx
+++ b/chapters/my/chapter3/4.mdx
@@ -18,7 +18,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/my/chapter5/6.mdx b/chapters/my/chapter5/6.mdx
index c3a81c424..8c73e2594 100644
--- a/chapters/my/chapter5/6.mdx
+++ b/chapters/my/chapter5/6.mdx
@@ -102,7 +102,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/my/chapter5/8.mdx b/chapters/my/chapter5/8.mdx
index e70c2a1df..e74d6e912 100644
--- a/chapters/my/chapter5/8.mdx
+++ b/chapters/my/chapter5/8.mdx
@@ -38,7 +38,7 @@
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 အောက်ပါ commands တွေထဲက ဘယ်ဟာက `dataset` ကနေ elements ၅၀ ကို random sample အဖြစ် ထုတ်လုပ်ပေးမလဲ။
@@ -128,7 +128,7 @@ dataset = load_dataset("glue", "mrpc", split="train")
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/my/chapter6/2.mdx b/chapters/my/chapter6/2.mdx
index b2a1212fa..fd73a2fed 100644
--- a/chapters/my/chapter6/2.mdx
+++ b/chapters/my/chapter6/2.mdx
@@ -24,7 +24,7 @@
 from datasets import load_dataset
 
 # ဒါကို load လုပ်ဖို့ အချိန်အနည်းငယ် ကြာနိုင်ပါတယ်၊ ဒါကြောင့် ကော်ဖီ ဒါမှမဟုတ် လက်ဖက်ရည် သောက်ရင်း စောင့်ဆိုင်းပါ။
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 ကျွန်တော်တို့ ရရှိနိုင်တဲ့ columns တွေကို ကြည့်ရှုဖို့ training split ကို ကြည့်နိုင်ပါတယ်-
diff --git a/chapters/my/chapter6/8.mdx b/chapters/my/chapter6/8.mdx
index e01ed69c3..8df58d0a9 100644
--- a/chapters/my/chapter6/8.mdx
+++ b/chapters/my/chapter6/8.mdx
@@ -43,7 +43,7 @@ building blocks တွေရဲ့ စာရင်းအပြည့်အစု
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/my/chapter7/7.mdx b/chapters/my/chapter7/7.mdx
index 93ba6dc69..9eb581a4c 100644
--- a/chapters/my/chapter7/7.mdx
+++ b/chapters/my/chapter7/7.mdx
@@ -46,7 +46,7 @@ extractive question answering အတွက် academic benchmark အဖြစ်
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("squad")
+raw_datasets = load_dataset("rajpurkar/squad")
 ```
 
 ပြီးရင် SQuAD dataset အကြောင်း ပိုမိုသိရှိနိုင်ဖို့ ဒီ object ကို ကြည့်နိုင်ပါတယ်။
diff --git a/chapters/my/chapter8/4.mdx b/chapters/my/chapter8/4.mdx
index 1f1a83e2f..f04d6f21e 100644
--- a/chapters/my/chapter8/4.mdx
+++ b/chapters/my/chapter8/4.mdx
@@ -31,7 +31,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -108,7 +108,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -300,7 +300,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -426,7 +426,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -631,7 +631,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/my/chapter8/4_tf.mdx b/chapters/my/chapter8/4_tf.mdx
index 31551cc42..7452d4986 100644
--- a/chapters/my/chapter8/4_tf.mdx
+++ b/chapters/my/chapter8/4_tf.mdx
@@ -29,7 +29,7 @@ from transformers import (
     TFAutoModelForSequenceClassification,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/pt/chapter5/6.mdx b/chapters/pt/chapter5/6.mdx
index 689512757..7b1c80c87 100644
--- a/chapters/pt/chapter5/6.mdx
+++ b/chapters/pt/chapter5/6.mdx
@@ -113,7 +113,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/pt/chapter5/8.mdx b/chapters/pt/chapter5/8.mdx
index 51a04768b..1dd983b5b 100644
--- a/chapters/pt/chapter5/8.mdx
+++ b/chapters/pt/chapter5/8.mdx
@@ -36,7 +36,7 @@ Antes de prosseguir, vamos testar o que você aprendeu neste capítulo.
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 Qual dos seguintes comandos produzirá uma amostra aleatória de 50 elementos do `conjunto de dados`?
@@ -126,7 +126,7 @@ Qual dos seguintes comandos produzirá uma amostra aleatória de 50 elementos do
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/pt/chapter6/2.mdx b/chapters/pt/chapter6/2.mdx
index 35e02f6a0..3afd1f979 100644
--- a/chapters/pt/chapter6/2.mdx
+++ b/chapters/pt/chapter6/2.mdx
@@ -24,7 +24,7 @@ A biblioteca [🤗 Datasets](https://github.com/huggingface/datasets) pode nos a
 from datasets import load_dataset
 
 # Isto pode levar alguns minutos para carregar, então pegue um copo de café enquanto espera!
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 Podemos dar uma olhada na divisão de treinamento para ver a quais colunas temos acesso:
diff --git a/chapters/ro/chapter3/2.mdx b/chapters/ro/chapter3/2.mdx
index 8662bc931..f7e697337 100644
--- a/chapters/ro/chapter3/2.mdx
+++ b/chapters/ro/chapter3/2.mdx
@@ -94,7 +94,7 @@ Biblioteca 🤗 Datasets oferă o comandă foarte simplă pentru a descărca și
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/ro/chapter3/3.mdx b/chapters/ro/chapter3/3.mdx
index 2368e6046..27e3b1af9 100644
--- a/chapters/ro/chapter3/3.mdx
+++ b/chapters/ro/chapter3/3.mdx
@@ -19,7 +19,7 @@ Exemplele de cod de mai jos presupun că ați executat deja exemplele din secți
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/ro/chapter3/3_tf.mdx b/chapters/ro/chapter3/3_tf.mdx
index 25cec3088..3e67587f5 100644
--- a/chapters/ro/chapter3/3_tf.mdx
+++ b/chapters/ro/chapter3/3_tf.mdx
@@ -18,7 +18,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/ro/chapter3/4.mdx b/chapters/ro/chapter3/4.mdx
index 6ea1f50f7..b4b67af38 100644
--- a/chapters/ro/chapter3/4.mdx
+++ b/chapters/ro/chapter3/4.mdx
@@ -15,7 +15,7 @@ Acum vom vedea cum să obținem aceleași rezultate ca în secțiunea anterioar
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/ro/chapter5/6.mdx b/chapters/ro/chapter5/6.mdx
index f917fdeac..74cc1caf8 100644
--- a/chapters/ro/chapter5/6.mdx
+++ b/chapters/ro/chapter5/6.mdx
@@ -102,7 +102,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/ro/chapter5/8.mdx b/chapters/ro/chapter5/8.mdx
index fc619da62..bd675ffa1 100644
--- a/chapters/ro/chapter5/8.mdx
+++ b/chapters/ro/chapter5/8.mdx
@@ -36,7 +36,7 @@ Acest capitol a acoperit o mulțime de subiecte! Nu vă faceți griji dacă nu a
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 Care dintre următoarele comenzi va produce un exemplu aleatoriu de 50 de elemente din `dataset`?
@@ -126,7 +126,7 @@ Care dintre următoarele comenzi va produce un exemplu aleatoriu de 50 de elemen
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/ro/chapter6/2.mdx b/chapters/ro/chapter6/2.mdx
index fca53211e..26ca2d079 100644
--- a/chapters/ro/chapter6/2.mdx
+++ b/chapters/ro/chapter6/2.mdx
@@ -24,7 +24,7 @@ Biblioteca [🤗 Datasets](https://github.com/huggingface/datasets) ne poate aju
 from datasets import load_dataset
 
 # Acest lucru poate dura câteva minute pentru a încărca, așa că luați o pauză și beți o ceașcă de cafea sau ceai în timp ce așteptați!
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 Putem să ne uităm la splitul de antrenare pentru a vedea la care coloane avem acces:
diff --git a/chapters/ro/chapter6/8.mdx b/chapters/ro/chapter6/8.mdx
index d0ccf8e0b..37fee50cd 100644
--- a/chapters/ro/chapter6/8.mdx
+++ b/chapters/ro/chapter6/8.mdx
@@ -43,7 +43,7 @@ Pentru a antrena noul nostru tokenizer, vom utiliza un corpus mic de text (astfe
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/ro/chapter7/7.mdx b/chapters/ro/chapter7/7.mdx
index bcf38863e..d71bf9f20 100644
--- a/chapters/ro/chapter7/7.mdx
+++ b/chapters/ro/chapter7/7.mdx
@@ -46,7 +46,7 @@ Ca de obicei, putem descărca și stoca în cache datasetul într-un singur pas
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("squad")
+raw_datasets = load_dataset("rajpurkar/squad")
 ```
 
 Ne putem uita apoi la acest obiect pentru a afla mai multe despre datasetul SQuAD:
diff --git a/chapters/ro/chapter8/4.mdx b/chapters/ro/chapter8/4.mdx
index ffc274d13..29017ddfd 100644
--- a/chapters/ro/chapter8/4.mdx
+++ b/chapters/ro/chapter8/4.mdx
@@ -31,7 +31,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -108,7 +108,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -300,7 +300,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -426,7 +426,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -632,7 +632,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/ro/chapter8/4_tf.mdx b/chapters/ro/chapter8/4_tf.mdx
index 620901446..748adc5e7 100644
--- a/chapters/ro/chapter8/4_tf.mdx
+++ b/chapters/ro/chapter8/4_tf.mdx
@@ -29,7 +29,7 @@ from transformers import (
     TFAutoModelForSequenceClassification,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/ru/chapter3/2.mdx b/chapters/ru/chapter3/2.mdx
index b52ac2f16..968506980 100644
--- a/chapters/ru/chapter3/2.mdx
+++ b/chapters/ru/chapter3/2.mdx
@@ -95,7 +95,7 @@ Hub содержит не только модели, там также расп
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/ru/chapter3/3.mdx b/chapters/ru/chapter3/3.mdx
index 38ec64670..e9a7f2194 100644
--- a/chapters/ru/chapter3/3.mdx
+++ b/chapters/ru/chapter3/3.mdx
@@ -19,7 +19,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/ru/chapter3/3_tf.mdx b/chapters/ru/chapter3/3_tf.mdx
index 06a49c730..eb92bac76 100644
--- a/chapters/ru/chapter3/3_tf.mdx
+++ b/chapters/ru/chapter3/3_tf.mdx
@@ -18,7 +18,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/ru/chapter3/4.mdx b/chapters/ru/chapter3/4.mdx
index 64002b330..6c03f96b7 100644
--- a/chapters/ru/chapter3/4.mdx
+++ b/chapters/ru/chapter3/4.mdx
@@ -15,7 +15,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/ru/chapter5/6.mdx b/chapters/ru/chapter5/6.mdx
index d1a98c017..3b518c8bc 100644
--- a/chapters/ru/chapter5/6.mdx
+++ b/chapters/ru/chapter5/6.mdx
@@ -114,7 +114,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/ru/chapter5/8.mdx b/chapters/ru/chapter5/8.mdx
index 1810b32bd..d42d164e0 100644
--- a/chapters/ru/chapter5/8.mdx
+++ b/chapters/ru/chapter5/8.mdx
@@ -37,7 +37,7 @@
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 Какая из следующих команд создаст случайную выборку из 50 элементов из `dataset`?
@@ -127,7 +127,7 @@ dataset = load_dataset("glue", "mrpc", split="train")
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/ru/chapter6/2.mdx b/chapters/ru/chapter6/2.mdx
index 8d59cb8af..f2cc92d3d 100644
--- a/chapters/ru/chapter6/2.mdx
+++ b/chapters/ru/chapter6/2.mdx
@@ -24,7 +24,7 @@
 from datasets import load_dataset
 
 # Загрузка может занять несколько минут, так что выпейте кофе или чай, пока ждете!
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 Мы можем взглянуть на тренировочную часть датасета, чтобы узнать, к каким столбцам у нас есть доступ:
diff --git a/chapters/ru/chapter6/8.mdx b/chapters/ru/chapter6/8.mdx
index 98ca7d600..a3538177d 100644
--- a/chapters/ru/chapter6/8.mdx
+++ b/chapters/ru/chapter6/8.mdx
@@ -43,7 +43,7 @@
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/ru/chapter7/7.mdx b/chapters/ru/chapter7/7.mdx
index 2afc87576..f1501e7ca 100644
--- a/chapters/ru/chapter7/7.mdx
+++ b/chapters/ru/chapter7/7.mdx
@@ -46,7 +46,7 @@
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("squad")
+raw_datasets = load_dataset("rajpurkar/squad")
 ```
 
 Мы можем взглянуть на этот объект, чтобы узнать больше о датасете SQuAD:
diff --git a/chapters/ru/chapter8/4.mdx b/chapters/ru/chapter8/4.mdx
index 38561cd07..d9e603f24 100644
--- a/chapters/ru/chapter8/4.mdx
+++ b/chapters/ru/chapter8/4.mdx
@@ -31,7 +31,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -108,7 +108,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -300,7 +300,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -426,7 +426,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -631,7 +631,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/ru/chapter8/4_tf.mdx b/chapters/ru/chapter8/4_tf.mdx
index 1574389cc..89448ec4c 100644
--- a/chapters/ru/chapter8/4_tf.mdx
+++ b/chapters/ru/chapter8/4_tf.mdx
@@ -29,7 +29,7 @@ from transformers import (
     TFAutoModelForSequenceClassification,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/th/chapter3/2.mdx b/chapters/th/chapter3/2.mdx
index ecacf2b63..2c89e92f8 100644
--- a/chapters/th/chapter3/2.mdx
+++ b/chapters/th/chapter3/2.mdx
@@ -95,7 +95,7 @@ Hub นั้นไม่ได้เก็บเพียงแค่โมเ
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/th/chapter3/3.mdx b/chapters/th/chapter3/3.mdx
index df54574bb..eb8397472 100644
--- a/chapters/th/chapter3/3.mdx
+++ b/chapters/th/chapter3/3.mdx
@@ -19,7 +19,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/th/chapter3/3_tf.mdx b/chapters/th/chapter3/3_tf.mdx
index 09ecd1509..978db9db9 100644
--- a/chapters/th/chapter3/3_tf.mdx
+++ b/chapters/th/chapter3/3_tf.mdx
@@ -18,7 +18,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/th/chapter3/4.mdx b/chapters/th/chapter3/4.mdx
index 3587608dc..88c369042 100644
--- a/chapters/th/chapter3/4.mdx
+++ b/chapters/th/chapter3/4.mdx
@@ -15,7 +15,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/th/chapter6/2.mdx b/chapters/th/chapter6/2.mdx
index efb9c9bee..b28293a63 100644
--- a/chapters/th/chapter6/2.mdx
+++ b/chapters/th/chapter6/2.mdx
@@ -42,7 +42,7 @@
 from datasets import load_dataset
 
 # This can take a few minutes to load, so grab a coffee or tea while you wait!
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 คุณสามารถเช็คดูข้อมูลส่วนที่ใช้เทรนได้โดยรันโค้ดข้างล่างนี้ เพื่อจะได้ดูว่าในชุดข้อมูลมีคอลัมน์อะไรบ้าง
diff --git a/chapters/th/chapter6/8.mdx b/chapters/th/chapter6/8.mdx
index 767da8acb..a6c8ed4ce 100644
--- a/chapters/th/chapter6/8.mdx
+++ b/chapters/th/chapter6/8.mdx
@@ -46,7 +46,7 @@ library นี้ ประกอบด้วยส่วนหลักคื
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/vi/chapter3/2.mdx b/chapters/vi/chapter3/2.mdx
index c316c264a..14b4306b9 100644
--- a/chapters/vi/chapter3/2.mdx
+++ b/chapters/vi/chapter3/2.mdx
@@ -92,7 +92,7 @@ Thư viện 🤗 Datasets cung cấp một lệnh rất đơn giản để tải
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/vi/chapter3/3.mdx b/chapters/vi/chapter3/3.mdx
index 7c8c4faf5..e64651118 100644
--- a/chapters/vi/chapter3/3.mdx
+++ b/chapters/vi/chapter3/3.mdx
@@ -19,7 +19,7 @@ Các ví dụ mã bên dưới giả sử bạn đã thực hiện các ví dụ
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/vi/chapter3/3_tf.mdx b/chapters/vi/chapter3/3_tf.mdx
index f048d0270..c403906e0 100644
--- a/chapters/vi/chapter3/3_tf.mdx
+++ b/chapters/vi/chapter3/3_tf.mdx
@@ -18,7 +18,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/vi/chapter3/4.mdx b/chapters/vi/chapter3/4.mdx
index 2429da9b7..75aead653 100644
--- a/chapters/vi/chapter3/4.mdx
+++ b/chapters/vi/chapter3/4.mdx
@@ -15,7 +15,7 @@ Bây giờ chúng ta sẽ xem cách đạt được kết quả tương tự nh
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/vi/chapter5/6.mdx b/chapters/vi/chapter5/6.mdx
index a65c03252..455ac0e2b 100644
--- a/chapters/vi/chapter5/6.mdx
+++ b/chapters/vi/chapter5/6.mdx
@@ -114,7 +114,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/vi/chapter5/8.mdx b/chapters/vi/chapter5/8.mdx
index 5303d1f5e..72a88e61d 100644
--- a/chapters/vi/chapter5/8.mdx
+++ b/chapters/vi/chapter5/8.mdx
@@ -41,7 +41,7 @@ Tuy nhiên, trước khi tiếp tục, hãy kiểm tra những gì bạn đã h
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 Đâu là một trong số những câu lệnh sẽ tạo ra một tập mẫu ngẫu nhiên 50 phần tử từ `dataset`?
@@ -140,7 +140,7 @@ dataset = load_dataset("glue", "mrpc", split="train")
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/vi/chapter6/2.mdx b/chapters/vi/chapter6/2.mdx
index ee264bfc9..77ea512e3 100644
--- a/chapters/vi/chapter6/2.mdx
+++ b/chapters/vi/chapter6/2.mdx
@@ -24,7 +24,7 @@ Thư viện [🤗 Datasets](https://github.com/huggingface/datasets) có thể g
 from datasets import load_dataset
 
 # Quá trình này có thể mất một vài phút để tải, vì vậy hãy lấy cà phê hoặc trà trong khi chờ đợi!
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 Chúng ta có thể xem xét phần tách huấn luyện để xem ta có quyền truy cập vào những cột nào:
diff --git a/chapters/vi/chapter6/8.mdx b/chapters/vi/chapter6/8.mdx
index 9e5e9a242..f089a5d36 100644
--- a/chapters/vi/chapter6/8.mdx
+++ b/chapters/vi/chapter6/8.mdx
@@ -41,7 +41,7 @@ Bạn có thể tìm được toàn bộ danh sách các khối tại [đây](ht
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/vi/chapter7/7.mdx b/chapters/vi/chapter7/7.mdx
index 7766d7009..853d83782 100644
--- a/chapters/vi/chapter7/7.mdx
+++ b/chapters/vi/chapter7/7.mdx
@@ -46,7 +46,7 @@ Như thường lệ, chúng ta có thể tải xuống và lưu bộ dữ liệu
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("squad")
+raw_datasets = load_dataset("rajpurkar/squad")
 ```
 
 Sau đó, chúng ta có thể xem xét đối tượng này để tìm hiểu thêm về tập dữ liệu SQuAD:
diff --git a/chapters/vi/chapter8/4.mdx b/chapters/vi/chapter8/4.mdx
index 24fd86e4e..262ac117f 100644
--- a/chapters/vi/chapter8/4.mdx
+++ b/chapters/vi/chapter8/4.mdx
@@ -31,7 +31,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -108,7 +108,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -300,7 +300,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -426,7 +426,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -631,7 +631,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/vi/chapter8/4_tf.mdx b/chapters/vi/chapter8/4_tf.mdx
index c7b6b1e5d..becdf69ea 100644
--- a/chapters/vi/chapter8/4_tf.mdx
+++ b/chapters/vi/chapter8/4_tf.mdx
@@ -27,7 +27,7 @@ from transformers import (
     TFAutoModelForSequenceClassification,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/zh-CN/chapter3/2.mdx b/chapters/zh-CN/chapter3/2.mdx
index 2ae86ef09..4e6745254 100644
--- a/chapters/zh-CN/chapter3/2.mdx
+++ b/chapters/zh-CN/chapter3/2.mdx
@@ -98,7 +98,7 @@ model.train_on_batch(batch, labels)
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/zh-CN/chapter3/3.mdx b/chapters/zh-CN/chapter3/3.mdx
index 2cb66e663..de19f5d28 100644
--- a/chapters/zh-CN/chapter3/3.mdx
+++ b/chapters/zh-CN/chapter3/3.mdx
@@ -19,7 +19,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/zh-CN/chapter3/3_tf.mdx b/chapters/zh-CN/chapter3/3_tf.mdx
index 4c93fb6d5..94253ee94 100644
--- a/chapters/zh-CN/chapter3/3_tf.mdx
+++ b/chapters/zh-CN/chapter3/3_tf.mdx
@@ -18,7 +18,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/zh-CN/chapter3/4.mdx b/chapters/zh-CN/chapter3/4.mdx
index 8fdb7653e..78b19ce0f 100644
--- a/chapters/zh-CN/chapter3/4.mdx
+++ b/chapters/zh-CN/chapter3/4.mdx
@@ -15,7 +15,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/zh-CN/chapter5/6.mdx b/chapters/zh-CN/chapter5/6.mdx
index 91bc56229..26626a58a 100644
--- a/chapters/zh-CN/chapter5/6.mdx
+++ b/chapters/zh-CN/chapter5/6.mdx
@@ -103,7 +103,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in :\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in :\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect,even by Web browser,please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/zh-CN/chapter5/8.mdx b/chapters/zh-CN/chapter5/8.mdx
index c3cf162ad..7a52d5cfb 100644
--- a/chapters/zh-CN/chapter5/8.mdx
+++ b/chapters/zh-CN/chapter5/8.mdx
@@ -36,7 +36,7 @@
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 以下哪个命令可以从 `dataset` 中生成 50 个元素的随机样本？
@@ -122,7 +122,7 @@ dataset = load_dataset("glue", "mrpc", split="train")
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/zh-CN/chapter6/2.mdx b/chapters/zh-CN/chapter6/2.mdx
index 96727b31e..68693d132 100644
--- a/chapters/zh-CN/chapter6/2.mdx
+++ b/chapters/zh-CN/chapter6/2.mdx
@@ -23,7 +23,7 @@
 from datasets import load_dataset
 
 # 加载这个可能需要几分钟的时间,你可以趁此喝杯咖啡或茶!
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 我们可以查看训练集部分来看我们可以使用哪些列：
diff --git a/chapters/zh-CN/chapter6/8.mdx b/chapters/zh-CN/chapter6/8.mdx
index b8b940001..21efba8ab 100644
--- a/chapters/zh-CN/chapter6/8.mdx
+++ b/chapters/zh-CN/chapter6/8.mdx
@@ -43,7 +43,7 @@
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/zh-CN/chapter7/7.mdx b/chapters/zh-CN/chapter7/7.mdx
index 220530c0e..5d95bb776 100644
--- a/chapters/zh-CN/chapter7/7.mdx
+++ b/chapters/zh-CN/chapter7/7.mdx
@@ -46,7 +46,7 @@
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("squad")
+raw_datasets = load_dataset("rajpurkar/squad")
 ```
 
 我们可以查看这个 `raw_datasets` 对象来了解关于 SQuAD 数据集的更多信息：
diff --git a/chapters/zh-TW/chapter3/2.mdx b/chapters/zh-TW/chapter3/2.mdx
index 4cc8f883d..96c90451d 100644
--- a/chapters/zh-TW/chapter3/2.mdx
+++ b/chapters/zh-TW/chapter3/2.mdx
@@ -92,7 +92,7 @@ model.train_on_batch(batch, labels)
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 raw_datasets
 ```
 
diff --git a/chapters/zh-TW/chapter3/3.mdx b/chapters/zh-TW/chapter3/3.mdx
index c2d37016f..18bf824de 100644
--- a/chapters/zh-TW/chapter3/3.mdx
+++ b/chapters/zh-TW/chapter3/3.mdx
@@ -19,7 +19,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/zh-TW/chapter3/3_tf.mdx b/chapters/zh-TW/chapter3/3_tf.mdx
index 6423977ec..8160da4f1 100644
--- a/chapters/zh-TW/chapter3/3_tf.mdx
+++ b/chapters/zh-TW/chapter3/3_tf.mdx
@@ -18,7 +18,7 @@ from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 import numpy as np
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/zh-TW/chapter3/4.mdx b/chapters/zh-TW/chapter3/4.mdx
index 9134b8ffd..7f479fba7 100644
--- a/chapters/zh-TW/chapter3/4.mdx
+++ b/chapters/zh-TW/chapter3/4.mdx
@@ -15,7 +15,7 @@
 from datasets import load_dataset
 from transformers import AutoTokenizer, DataCollatorWithPadding
 
-raw_datasets = load_dataset("glue", "mrpc")
+raw_datasets = load_dataset("nyu-mll/glue", "mrpc")
 checkpoint = "bert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(checkpoint)
 
diff --git a/chapters/zh-TW/chapter5/6.mdx b/chapters/zh-TW/chapter5/6.mdx
index b62dc59fd..1b0bef93a 100644
--- a/chapters/zh-TW/chapter5/6.mdx
+++ b/chapters/zh-TW/chapter5/6.mdx
@@ -112,7 +112,7 @@ df["comments"][0].tolist()
 ```
 
 ```python out
-['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)',
+['the bug code locate in ：\r\n    if data_args.task_name is not None:\r\n        # Downloading and loading a dataset from the hub.\r\n        datasets = load_dataset("nyu-mll/glue", data_args.task_name, cache_dir=model_args.cache_dir)',
  'Hi @jinec,\r\n\r\nFrom time to time we get this kind of `ConnectionError` coming from the github.com website: https://raw.githubusercontent.com\r\n\r\nNormally, it should work if you wait a little and then retry.\r\n\r\nCould you please confirm if the problem persists?',
  'cannot connect，even by Web browser，please check that  there is some  problems。',
  'I can access https://raw.githubusercontent.com/huggingface/datasets/1.7.0/datasets/glue/glue.py without problem...']
diff --git a/chapters/zh-TW/chapter5/8.mdx b/chapters/zh-TW/chapter5/8.mdx
index b6c62af5e..d592c6f0c 100644
--- a/chapters/zh-TW/chapter5/8.mdx
+++ b/chapters/zh-TW/chapter5/8.mdx
@@ -36,7 +36,7 @@
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("glue", "mrpc", split="train")
+dataset = load_dataset("nyu-mll/glue", "mrpc", split="train")
 ```
 
 以下哪個命令將從 `dataset` 中生成50個元素的隨機樣本?
@@ -122,7 +122,7 @@ dataset = load_dataset("glue", "mrpc", split="train")
 ```py
 from datasets import load_dataset
 
-dataset = load_dataset("allocine", streaming=True, split="train")
+dataset = load_dataset("tblard/allocine", streaming=True, split="train")
 dataset[0]
 ```
 
diff --git a/chapters/zh-TW/chapter6/2.mdx b/chapters/zh-TW/chapter6/2.mdx
index fd24bd1ab..0b12415b2 100644
--- a/chapters/zh-TW/chapter6/2.mdx
+++ b/chapters/zh-TW/chapter6/2.mdx
@@ -24,7 +24,7 @@
 from datasets import load_dataset
 
 # This can take a few minutes to load, so grab a coffee or tea while you wait!
-raw_datasets = load_dataset("code_search_net", "python")
+raw_datasets = load_dataset("code-search-net/code_search_net", "python")
 ```
 
 我們可以查看訓練集的部分，以查看我們數據集中有哪些列：
diff --git a/chapters/zh-TW/chapter6/8.mdx b/chapters/zh-TW/chapter6/8.mdx
index 2182b0da9..739391fe7 100644
--- a/chapters/zh-TW/chapter6/8.mdx
+++ b/chapters/zh-TW/chapter6/8.mdx
@@ -43,7 +43,7 @@
 ```python
 from datasets import load_dataset
 
-dataset = load_dataset("wikitext", name="wikitext-2-raw-v1", split="train")
+dataset = load_dataset("Salesforce/wikitext", name="wikitext-2-raw-v1", split="train")
 
 
 def get_training_corpus():
diff --git a/chapters/zh-TW/chapter7/7.mdx b/chapters/zh-TW/chapter7/7.mdx
index 8ad9ee93e..7c5f985fe 100644
--- a/chapters/zh-TW/chapter7/7.mdx
+++ b/chapters/zh-TW/chapter7/7.mdx
@@ -47,7 +47,7 @@
 ```py
 from datasets import load_dataset
 
-raw_datasets = load_dataset("squad")
+raw_datasets = load_dataset("rajpurkar/squad")
 ```
 
 然後我們可以查看這個對象以, 瞭解有關 SQuAD 數據集的更多信息:
diff --git a/chapters/zh-TW/chapter8/4.mdx b/chapters/zh-TW/chapter8/4.mdx
index c0c17f392..affafe970 100644
--- a/chapters/zh-TW/chapter8/4.mdx
+++ b/chapters/zh-TW/chapter8/4.mdx
@@ -30,7 +30,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -106,7 +106,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -297,7 +297,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -422,7 +422,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
@@ -626,7 +626,7 @@ from transformers import (
     Trainer,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
diff --git a/chapters/zh-TW/chapter8/4_tf.mdx b/chapters/zh-TW/chapter8/4_tf.mdx
index e6aa13c6b..f09c271f1 100644
--- a/chapters/zh-TW/chapter8/4_tf.mdx
+++ b/chapters/zh-TW/chapter8/4_tf.mdx
@@ -34,7 +34,7 @@ from transformers import (
     TFAutoModelForSequenceClassification,
 )
 
-raw_datasets = load_dataset("glue", "mnli")
+raw_datasets = load_dataset("nyu-mll/glue", "mnli")
 
 model_checkpoint = "distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)