8 points

Thought that said cbatGPT

permalink
report
reply
11 points

Please keep us updated with all future inconsequential misinterpretations.

-Management

permalink
report
parent
reply
3 points

Dear Management,

I was just brushing my teeth without my glasses on, anf out of the corner of my eye it sorta looked like Versace.

Hope this helps, Facebones

permalink
report
parent
reply
10 points
*

Fun fact: you can download llama3, an llm model made by meta (which is surprisingly good for its size), and it’s only 4.7gb. A dvd can store 4.7 gb of data, meaning you could in theory have an llm on a DVD.

Model link

CC BY-NC-SA 4.0

permalink
report
reply
44 points
*

Technically possible with a small enough model to work from. It’s going to be pretty shit, but “working”.

Now, if we were to go further down in scale, I’m curious how/if a 700MB CD version would work.

Or how many 1.44MB floppies you would need for the actual program and smallest viable model.

permalink
report
reply
12 points

Might be a dvd. 70b ollama llm is like 1.5GB. So you could save many models on one dvd.

permalink
report
parent
reply
5 points

It does have the label DVD-R

permalink
report
parent
reply
8 points

70b model taking 1.5GB? So 0.02 bit per parameter?

Are you sure you’re not thinking of a heavily quantised and compressed 7b model or something? Ollama llama3 70b is 40GB from what i can find, that’s a lot of DVDs

permalink
report
parent
reply
7 points

Less than half of a BDXL though! The dream still breathes

permalink
report
parent
reply
9 points

Ah yes probably the Smaler version, your right. Still, a very good llm better than gpt 3

permalink
report
parent
reply
5 points

For some reason, triple layer writable blu-ray exists. 100GB each

https://www.verbatim.com/prod/optical-media/blu-ray/bd-r-xl-tl/bd-r-xl-tl/

permalink
report
parent
reply
8 points

It is a DVD, can faintly see DVD+R on the left side

permalink
report
parent
reply
8 points
*

Maybe not all that LLM, https://en.wikipedia.org/wiki/ELIZA

permalink
report
parent
reply
16 points

squints

That says , “PHILLIPS DVD+R”

So we’re looking at a 4.7GB model, or just a hair under the tiniest, most incredibly optimized implementation of <INSERT_MODEL_NAME_HERE>

permalink
report
parent
reply
13 points

llama 3 8b, phi 3 mini, Mistral, moondream 2, neural chat, starling, code llama, llama 2 uncensored, and llava would fit.

permalink
report
parent
reply
1 point

Just interested in the topic did you 🔨 offline privately?

permalink
report
parent
reply
7 points

ELIZA was pretty impressive for the 1960s, as a chatbot for psychology.

permalink
report
parent
reply
3 points

pkzip c:\chatgpt*.* a:\chatgpt.zip -&

permalink
report
parent
reply
4 points

yes i guess it would be a funny experiment for just a local model

permalink
report
parent
reply
4 points

Seems legit

permalink
report
reply
7 points
permalink
report
reply

Memes

!memes@lemmy.ml

Create post

Rules:

  1. Be civil and nice.
  2. Try not to excessively repost, as a rule of thumb, wait at least 2 months to do it if you have to.

Community stats

  • 8.1K

    Monthly active users

  • 6.2K

    Posts

  • 43K

    Comments