Update README.md

README.md

@@ -28,13 +28,24 @@ More precisely, it was pretrained with the Masked language modeling (MLM) object
 This way, the model learns an inner representation of 100 languages that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the XLM-RoBERTa model as inputs.
 
 
-Here is how to use this model to get the features of a given text in PyTorch:
+**Here is how to use this model using pipeline in transformers:**
+
+```py
+from transformers import pipeline
+
+pipe = pipeline("token-classification", model="tejakota/finetuned-xlm-roberta",aggregation_strategy="simple")
+result = pipe("David is going to New York tomorrow")
+print(result)
+```
+
+
+**Here is how to use this model to get the features of a given text in PyTorch:**
 
 ```python
 from transformers import AutoTokenizer, AutoModelForMaskedLM
 
-tokenizer = AutoTokenizer.from_pretrained('xlm-roberta-base')
-model = AutoModelForMaskedLM.from_pretrained("xlm-roberta-base")
+tokenizer = AutoTokenizer.from_pretrained('tejakota/finetuned-xlm-roberta')
+model = AutoModelForMaskedLM.from_pretrained("tejakota/finetuned-xlm-roberta")
 
 # prepare input
 text = "Replace me by any text you'd like."