readme updated

README.md

@@ -18,8 +18,13 @@ Model architecture is similar to bert-medium (8 layers, 8 heads, and 512 hidden
 The details can be found at this paper: 
 https://arxiv.org/...
 
-The following code segment can be used for initializing the tokenizer, example max length (514) can be changed:
+The following code can be used for model loading and tokenization, example max length (514) can be changed:
 ```
+	model = AutoModel.from_pretrained([model_path])
+	#for sequence classification:
+	#model = AutoModelForSequenceClassification.from_pretrained([model_path], num_labels=[num_classes])
+
+	tokenizer = ByT5Tokenizer.from_pretrained("google/byt5-small")
 	tokenizer = PreTrainedTokenizerFast(tokenizer_file=[file_path])
 	tokenizer.mask_token = "[MASK]"
 	tokenizer.cls_token = "[CLS]"