Recently made a post about the 35b MOE. Now the dense 27b variant has been released.


you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 4 months ago (11 children)

Thank you!!! This is awesome!

When using llama.cpp, does it pass your prompts through a web server to process? Any privacy concerns?

Sounds like I’m looking at a few grand to run something decent. I’ll need to do more research before I commit to that big of a purchase, but your machine sounds nice!

Are there any small models you recommend that can run on 16GB DDR4 and an i7? No dedicated graphics card with separate VRAM. Maybe I’ll just experiment with something v small first.

Thanks again!

  • source
  • parent
  • hideshow 11 child comments
  • [+] 5 points 4 months ago* (last edited 4 months ago) (6 children)
  • [–] 2 points 4 months ago (5 children)

    Thanks. I don’t understand web UI enough. Thought it had to be hosted somewhere. I’ll try it out.

    I just want to use it for general web search, data processing and maybe some light automation. In the beginning I just wanna understand how it all works and how to set it up so small model is fine.

  • source
  • parent
  • hideshow 5 child comments
  • [+] 3 points 4 months ago* (last edited 4 months ago) (4 children)
  • [–] 2 points 4 months ago (2 children)

    Are you running llama.cpp via Docker or you compiled on your machine?

  • source
  • parent
  • hideshow 2 child comments
  • [–] 1 point 4 months ago

    Got it. I’ve built simple webpages and opened those files in my browser to preview them, but didn’t know those would connect to anything.

    I’ll check out Jan and Llama and see which works for me.

    Thanks!!

  • source
  • parent
  • [–] 4 points 4 months ago (3 children)

    You would be surprised by the smaller 7-12B LLMs. Give them tools and they can work well

  • source
  • parent
  • hideshow 3 child comments
  • [–] 1 point 4 months ago (2 children)

    Thanks! I imagine you can create and pull tools from somewhere. Where is a good place to find prebuilt tools?

  • source
  • parent
  • hideshow 2 child comments