Use the right tokenizer

As its a finetune of the Google Flan T5 Small model, the tokenizer its the same, so there isn't really a reason to use the base model repo tokenizer when you can just use the one of your own model as its like a duplicate one

README.md

@@ -24,7 +24,7 @@ pip install transformers
 ```python
 from transformers import T5Tokenizer, T5ForConditionalGeneration
 
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-small")
+tokenizer = T5Tokenizer.from_pretrained("roborovski/superprompt-v1")
 model = T5ForConditionalGeneration.from_pretrained("roborovski/superprompt-v1", device_map="auto")
 
 input_text = "Expand the following prompt to add more detail: A storefront with 'Text to Image' written on it."