Upload README.md

README.md

@@ -5,16 +5,9 @@ license: llama2
 model_creator: Xwin-LM
 model_name: Xwin-LM 70B V0.1
 model_type: llama
-prompt_template: 'Below is an instruction that describes a task. Write a response
-  that appropriately completes the request.
-
-
-  ### Instruction:
-
-  {prompt}
-
-
-  ### Response:
+prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
+  The assistant gives helpful, detailed, and polite answers to the user''s questions.
+  USER: {prompt} ASSISTANT:
 
   '
 quantized_by: TheBloke
@@ -63,15 +56,10 @@ It is also now supported by continuous batching server [vLLM](https://github.com
 <!-- repositories-available end -->
 
 <!-- prompt-template start -->
-## Prompt template: Alpaca
+## Prompt template: Vicuna
 
 ```
-Below is an instruction that describes a task. Write a response that appropriately completes the request.
-
-### Instruction:
-{prompt}
-
-### Response:
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
 
 ```
 
@@ -161,12 +149,7 @@ 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'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
-
-### Instruction:
-{prompt}
-
-### Response:
+prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
 
 '''