Update README.md

README.md

@@ -54,7 +54,7 @@ pipeline_tag: text-generation
 </div>
 
 <div style="display: flex; justify-content: center; align-items: center">
-  <p>* Llama-3-Instruct often fails to follow the few-shot templates.</p>
+  <p>* Llama-3-Instruct often fails to follow the few-shot templates. See <a href="https://huggingface.co/openchat/openchat-3.6-8b-20240522/discussions/6">example</a>.</p>
 </div>
 
 <div align="center">
@@ -87,13 +87,15 @@ curl http://localhost:18888/v1/chat/completions \
 
 ### Conversation templates
 
-💡 **Default Mode**: Best for coding, chat and general tasks
+💡 **Default Mode**: Best for coding, chat and general tasks.
+
+It's a modified version of the Llama 3 Instruct template, the only difference is role names, which are either `GPT4 Correct User` or `GPT4 Correct Assistant`
 
 ```
-GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:
+<|start_header_id|>GPT4 Correct User<|end_header_id|>\n\nHello<|eot_id|><|start_header_id|>GPT4 Correct Assistant<|end_header_id|>\n\nHi<|eot_id|><|start_header_id|>GPT4 Correct User<|end_header_id|>\n\nHow are you today?<|eot_id|><|start_header_id|>GPT4 Correct Assistant<|end_header_id|>\n\n
 ```
 
-⚠️ **Notice:** Remember to set `<|end_of_turn|>` as end of generation token.
+⚠️ **Notice:** Remember to set `<|eot_id|>` as end of generation token.
 
 The default template is also available as the integrated `tokenizer.chat_template`, which can be used instead of manually specifying the template: