Update README.md

README.md

@@ -301,11 +301,19 @@ llm = Llama(
   n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
 )
 
+prompt = "Tell me about AI"
+
 output = llm(
-  "what is life?", # Prompt
-  max_tokens=10,  # Generate up to 512 tokens
+  f'''[INST] <<SYS>>
+You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
+<</SYS>>
+{prompt}[/INST]
+
+''', # Prompt
+  max_tokens=100,  # Generate up to 512 tokens
   stop=["</s>"],   # Example stop token - not necessarily correct for this specific model! Please check before using.
   echo=True ,       # Whether to echo the prompt
   temperature=0.001
 )
+
 ```