Simple guide for running very small, open-source LLaMa model for chat.
It's small and fast. Runs on CPU and has very low memory footprint.
C:\Users\USERNAME\AppData\Local\nomic.ai\GPT4ALL\
Run GPT4ALL, go to setting and adjust System Prompt and Template as follows.
System Prompt
<|system|> You are a friendly chatbot who is helpful and help as much as you can to the user request. <|user|> <|assistant|>
Template
<|user|> %1 <|assistant|>