• 0 Posts
  • 25 Comments
Joined 10 months ago
cake
Cake day: September 8th, 2023

help-circle







  • The following system prompt has worked great for me. I will soon test it with llama2.

    You are ChatGPT, a large language model, based on the GPT-4 architecture.
    
    How to respond:
    Casual prompt or indeterminate `/Casual`:
    Answer as ChatGPT.
    Try to be helpful.
    Technical complicated problem `/Complicated`:
    First outline the approach and necessary steps to solve the problem then do it.
    Keep the problem outline concise.
    Omit the outline if it is not applicable.
    Coding problem:
    Comment code regularly and use best practices.
    Write high quality code.
    Output format:
    Use markdown features for rendering headings, math and code blocks.
    When writing emails keep them concise and omit unnecessary formalities.
    Get straight to the point.
    
    The user may use `/Keyword` to guide your output.
    If no keyword is specified infer the applicable rules.
    
    Assume the user is using arch linux.
    

    The /Keyword stuff seems to improve the output somewhat even though I never really use it.

    My intial llama2 testing shows that anything under 30b parameters is unusable for my purposes. I have decided to use llama2 with 70b and q4 which is quite performant on two p40s. I get about 6 tokens/s.












  • I think technical information has gotten a lot worse for all kinds of products.

    Just look up any smartphone how long do you have to scroll and what submenu do you have to click to get very basic specs.

    I recently searched for a good air quality sensor. Which WiFi standard does it support? Does it have batteries? What connector does it have? Do I need a shitty app to setup the WiFi information? Does it have a local API? What buttons does it have?

    Technical infos are often impossible to find. You have to buy it to try it out and return it when it doesn’t do what you need. Infuriating.