Update usage

README.md

@@ -58,7 +58,7 @@ You can use this model directly with a pipeline for masked language modeling:
 
 ```python
 >>> from transformers import pipeline
->>> unmasker = pipeline('fill-mask', model='fralbert-base')
+>>> unmasker = pipeline('fill-mask', model='qwant/fralbert-base')
 >>> unmasker("Bonjour Je suis un model [MASK] .")
 ```
 
@@ -66,8 +66,8 @@ Here is how to use this model to get the features of a given text in PyTorch:
 
 ```python
 from transformers import AlbertTokenizer, AlbertModel
-tokenizer = AlbertTokenizer.from_pretrained('fralbert-base')
-model = AlbertModel.from_pretrained("fralbert-base")
+tokenizer = AlbertTokenizer.from_pretrained('qwant/fralbert-base')
+model = AlbertModel.from_pretrained("qwant/fralbert-base")
 text = "Remplacez-moi par le texte en français que vous souhaitez."
 encoded_input = tokenizer(text, return_tensors='pt')
 output = model(**encoded_input)
@@ -77,8 +77,8 @@ and in TensorFlow:
 
 ```python
 from transformers import AlbertTokenizer, TFAlbertModel
-tokenizer = AlbertTokenizer.from_pretrained('fralbert-base')
-model = TFAlbertModel.from_pretrained("fralbert-base")
+tokenizer = AlbertTokenizer.from_pretrained('qwant/fralbert-base')
+model = TFAlbertModel.from_pretrained("qwant/fralbert-base")
 text = "Remplacez-moi par le texte en français que vous souhaitez."
 encoded_input = tokenizer(text, return_tensors='tf')
 output = model(encoded_input)
@@ -133,4 +133,6 @@ When fine-tuned on downstream tasks, the ALBERT models achieve the following res
   address   = {Online},
   month     = sep,
 }
-```
+```
+
+Link to the paper: [PDF](https://hal.archives-ouvertes.fr/hal-03336060)