Update README.md

README.md

@@ -32,8 +32,6 @@ app before April 12, 2023.
 
 supervised finetune on sequence of 5120 conversation dataset
 
-
-
 ## Model Details
 
 - **Developed by:** [Open-Assistant Contributors](https://open-assistant.io/) and [iKala](https://ikala.ai/)
@@ -46,11 +44,11 @@ supervised finetune on sequence of 5120 conversation dataset
 ## Prompting
 
 Two special tokens are used to mark the beginning of user and assistant turns:
-`<|prompter|>` and `<|assistant|>`. Each turn ends with a `<|endoftext|>` token.
+`<|prompter|>` and `<|assistant|>`. Each turn ends with a `</s>` token.
 
 Input prompt example:
 ```
-<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
+<|prompter|>What is a meme, and what's the history behind this word?</s><|assistant|>
 ```
 The input ends with the `<|assistant|>` token to signal that the model should 
 start generating the assistant reply.