Reduced URL

chapters/en/chapter7/2.mdx

@@ -188,7 +188,7 @@ model_checkpoint = "bert-base-cased"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
 ```
 
-You can replace the `model_checkpoint` with any other model you prefer from the [Hub](https://huggingface.co/models), or with a local folder in which you've saved a pretrained model and a tokenizer. The only constraint is that the tokenizer needs to be backed by the 🤗 Tokenizers library, so there's a "fast" version available. You can see all the architectures that come with a fast version in [this big table](https://huggingface.co/docs/transformers/index#supported-models-and-frameworks), and to check that the `tokenizer` object you're using is indeed backed by 🤗 Tokenizers you can look at its `is_fast` attribute:
+You can replace the `model_checkpoint` with any other model you prefer from the [Hub](https://huggingface.co/models), or with a local folder in which you've saved a pretrained model and a tokenizer. The only constraint is that the tokenizer needs to be backed by the 🤗 Tokenizers library, so there's a "fast" version available. You can see all the architectures that come with a fast version in [this big table](https://huggingface.co/transformers/#supported-models-and-frameworks), and to check that the `tokenizer` object you're using is indeed backed by 🤗 Tokenizers you can look at its `is_fast` attribute:
 
 ```py
 tokenizer.is_fast