Re:The Coming of Local LLMs
by syntaxing on Tuesday April 11, 2023 @12:54PM
(#35527823)
Super curious how you did this! Doesn’t 30B model require a hefty computer to run locally (assuming you’re tuning a non-quantized version)
[ Parent
| on HN ]
Not at all. Even a Raspberry Pi would do - you only need ~6GiB RAM for a 4-bit quantized LLaMA model (though it's gonna be quite slow). A decent modern desktop machine would do just fine, no need for anything extra fancy.
What I'm wondering is how they fed the documents, as all those LLMs have limitations on the input sizes.
>~6GiB RAM
That's for the 7B model. The 30B model needs 24GB quantized (or 64GB for the unquantized model).
I've seen reports that it wrecks RPi SD cards in short order though, so beware...
> What I'm wondering is how they fed the documents, as all those LLMs have limitations on the input sizes.
It's like file hashing at scale, you don't have to read the whole stream for every file, just the first 1024/2048 bytes (or first few paragraphs).
(This works for classification and sorting, less so for summarization.)