C:\KKJ\>:idle: · @w84death
752 followers · 399 posts · Server fosstodon.org
Mario Alberto Chávez · @mario_chavez
51 followers · 45 posts · Server ruby.social

I just pushed changes to LLM Server, a Rack Ruby server that wraps llama.cpp binary to allow you to run LLM models via an API.
By default, it loads the model one in memory and executes it in interactive mode.

It works fine for Open Llama or Vicuna models but not for models like Orca. A non-interactive mode was introduced for them. It is fast for smaller models like Orcas's 3b.
I have been using quantized models from @thebloke
with success.

github.com/mariochavez/llm_ser

#ruby #LLM #llamacpp

Last updated 1 year ago

C:\KKJ\>:idle: · @w84death
718 followers · 338 posts · Server fosstodon.org

Real time Raspberry Pi AI saying hi!

#raspberrypi #llamacpp #selfhosting

Last updated 1 year ago

David Burela · @DavidBurela
154 followers · 24 posts · Server hachyderm.io

I've been working with to explore patterns that allows for running on or

I've found using a combination of & allows me to do this.
I've created a small example repo, that shows how to quickly get up and running with GPU support.

github.com/DavidBurela/edgellm

#llm #edgecompute #azure #openai #langchain #llamacpp

Last updated 1 year ago

In case you're wondering how the "run ChatGPT" at home race is going, here's a locally run, CPU-powered "13b q5_1 Vicuna" model on versus , , and itself.

"What are my first steps for teaching a newborn baby how to breakdance?"

#llamacpp #bard #bingchat #chatgpt #ai #llms

Last updated 1 year ago

onion · @onion
30 followers · 247 posts · Server mastodon.tal.org

Took a while to download the models but got up and running. No idea what to actually do with it.

#llamacpp #llama

Last updated 1 year ago

ダニエル · @bietiekay
31 followers · 55 posts · Server mas.to

ja richtig. Ohne Grafikkarte. Man braucht eigentlich nur github.com/antimatter15/alpaca und die in der readme angegebenen Models. Das 13B ist seit ein paar Stunden verfügbar und läuft bei mir mit mittelalterlicher Hardware „fast enough“. Auf moderner Hardware ist das praktisch schon unheimlich was man damit machen kann.... zuhause. Einfach so. Living the future.

#llamacpp #largelanguagemodel #alpacacpp

Last updated 1 year ago

ダニエル · @bietiekay
31 followers · 55 posts · Server mas.to

nagut, dann installier ich das halt mal.... diese Projektnamen, ich muss die ganze Zeit grinsen.... "npx dalai llama install 7B"

#alpacacpp #llamacpp #llama #dalai

Last updated 1 year ago