Change the llama-cli flags

Explanation:
-cnv : conversation mode
--chat-template : apply the chatglm4 chat template
-p : when in conversation mode the prompt becomes the system prompt

README.md

@@ -34,7 +34,7 @@ cmake --build build -- -j
 After installation, you can start the GLM-Edge Chat model using the following command:
 
 ```shell
-llama-cli -m <path>/model.gguf -p "<|user|>\nhi<|assistant|>\n" -ngl 999
+llama-cli -m <path>/model.gguf -cnv --chat-template chatglm4 -p "You are a helpful AI assistant." -ngl 999
 ```
 
 In the command-line interface, you can interact with the model by entering your requests, and the model will provide the