Change loaded mode to correct on that this model card refers to

Currently the base distilbert version that this sentiment analysis model is based on is loaded in the model card. New users that want to try this model out will get random results for sentiment analysis, because the base version is not fine tuned for this task.

README.md

@@ -141,8 +141,8 @@ Example of single-label classification:
 import torch
 from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
 
-tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased")
-model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased")
+tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
+model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
 
 inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
 with torch.no_grad():