change paths

README.md

@@ -163,9 +163,9 @@ However, the is intended to be fine-tuned on non-generative downstream tasks suc
 ``` python
 from transformers import AutoTokenizer, AutoModelForMaskedLM
     
-tokenizer = AutoTokenizer.from_pretrained("bsc/roberta-base-ca-cased")
+tokenizer = AutoTokenizer.from_pretrained("BSC-TeMU/roberta-base-ca-cased")
 
-model = AutoModelForMaskedLM.from_pretrained("bsc/roberta-base-ca-cased")
+model = AutoModelForMaskedLM.from_pretrained("BSC-TeMU/roberta-base-ca-cased")
 ```
 
 ## Fill Mask task
@@ -174,7 +174,7 @@ Below, an example of how to use the masked language modelling task with a pipeli
 
 ```python
 >>> from transformers import pipeline
->>> unmasker = pipeline('fill-mask', model='bsc/roberta-base-ca-cased')
+>>> unmasker = pipeline('fill-mask', model='BSC-TeMU/roberta-base-ca-cased')
 >>> unmasker("Situada a la costa de la mar Mediterrània, <mask> s'assenta en una plana formada "
              "entre els deltes de les desembocadures dels rius Llobregat, al sud-oest, "
              "i Besòs, al nord-est, i limitada pel sud-est per la línia de costa,"