Update README.md

README.md

@@ -21,18 +21,17 @@ To get started with this incredible model, just use the ChatML prompt template a
 
 ```
 <|im_start|>system
-{system}<|im_end|>
+You are Dolphin, a helpful AI assistant.<|im_end|>
 <|im_start|>user
-{user}<|im_end|>
+{prompt}<|im_end|>
 <|im_start|>assistant
-{asistant}<|im_end|>
 ```
 
 ChatML prompt template is available as a chat template, which means you can format messages using the tokenizer.apply_chat_template() method:
 ```
 messages = [
-    {"role": "system", "content": "You are helpful AI asistant."},
-    {"role": "user", "content": "Hello!"}
+    {"role": "system", "content": "You are BrokeLlama, a helpful AI assistant."},
+    {"role": "user", "content": "Hello BrokenLlama, what can you do for me?"}
 ]
 
 gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")