top | item 37958680

(no title)

wrigglingworm | 2 years ago

>But even NorthPole’s 224 megabytes of RAM are not enough for large language models, such as those used by the chatbot ChatGPT, which take up several thousand megabytes of data even in their most stripped-down versions.

Is that right?

discuss

order

Ukv|2 years ago

At a glance, the supplementary materials from IBM's paper claim even less:

> NorthPole's core array includes 192 MB of flexible memory (768KB of unified memory per core). Assigning 2/3rd of this memory to parameters, such as weights and biases, provides 128MB for network storage.

https://www.science.org/doi/suppl/10.1126/science.adh1174/su...

My understanding is that this is a small energy-efficient chip for edge computing, like to stuff in an IoT device. Way too little memory to expect to run any recent language models, but could maybe do some basic object detection in a doorbell camera, for example.

The article's author seems to believe 224 megabytes is a huge amount of memory, and is a few orders of magnitude too low on the ChatGPT estimate too.

dartos|2 years ago

Yeah. 224 MB is nothing.

Small LLMs that have been quantized to optimize for space still sit at 4-9 gigs

hadlock|2 years ago

I would expect LLM hardware to routinely support between 32 and 512GB memory in the Very Near Future. 1-4TB by the end of the decade. Custom hardware for GPT and LLM technology only started being developed in earnest in September 2022

wrigglingworm|2 years ago

I thought the article was mixing up MB and GB at first. Is that the size of the LLM with no training data? Is there any value in that?

loufe|2 years ago

That's not true, there are some very pruned (and relatively dumb) LLMs which go under a gig.