Update Getting Started code as previous version doesn't work anymore (#4)

- Update Getting Started code as previous version doesn't work anymore (f7d1a692f0b87d3c75ada8e02e7dbd3c94fe7434)


Co-authored-by: Ankit Sharma <celex@users.noreply.huggingface.co>

README.md

@@ -24,10 +24,10 @@ Preprocessing, training and implementation details can be found in the [personaG
 ```python
 from transformers import GPT2Tokenizer, GPT2LMHeadModel
 import torch
-tokenizer = AutoTokenizer.from_pretrained("af1tang/personaGPT")
-model = AutoModelForCausalLM.from_pretrained("af1tang/personaGPT")
+tokenizer = GPT2Tokenizer.from_pretrained("af1tang/personaGPT")
+model = GPT2LMHeadModel.from_pretrained("af1tang/personaGPT")
 if torch.cuda.is_available():
-	model = model.cuda()
+    model = model.cuda()
 ## utility functions ##
 flatten = lambda l: [item for sublist in l for item in sublist]