Upload README.md

README.md

@@ -7,7 +7,9 @@ license: mit
 model_creator: Nobody.png
 model_name: Yi 34B GiftedConvo Llama
 model_type: llama
-prompt_template: '{prompt}
+prompt_template: 'USER: {prompt}
+
+  ASSISTANT:
 
   '
 quantized_by: TheBloke
@@ -71,10 +73,11 @@ Here is an incomplete list of clients and libraries that are known to support GG
 <!-- repositories-available end -->
 
 <!-- prompt-template start -->
-## Prompt template: Unknown
+## Prompt template: User-Assistant
 
 ```
-{prompt}
+USER: {prompt}
+ASSISTANT:
 
 ```
 
@@ -200,7 +203,7 @@ Windows Command Line users: You can set the environment variable by running `set
 Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
 
 ```shell
-./main -ngl 32 -m yi-34b-giftedconvo-merged.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
+./main -ngl 32 -m yi-34b-giftedconvo-merged.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "USER: {prompt}\nASSISTANT:"
 ```
 
 Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.