Upload README.md

README.md

@@ -11,7 +11,7 @@ model_creator: Open-Orca
 model_name: OpenOrca x OpenChat - Preview2 - 13B
 model_type: llama
 pipeline_tag: text-generation
-prompt_template: 'user: {prompt}<|end_of_turn|>assistant:
+prompt_template: 'GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
 
   '
 quantized_by: TheBloke
@@ -60,10 +60,10 @@ It is also now supported by continuous batching server [vLLM](https://github.com
 <!-- repositories-available end -->
 
 <!-- prompt-template start -->
-## Prompt template: openchat llama2 v1
+## Prompt template: OpenChat
 
 ```
-user: {prompt}<|end_of_turn|>assistant:
+GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
 
 ```
 
@@ -153,7 +153,7 @@ model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
 
 prompt = "Tell me about AI"
-prompt_template=f'''user: {prompt}<|end_of_turn|>assistant:
+prompt_template=f'''GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
 
 '''