Terrasque
- 0 Posts
- 32 Comments
I mean, I totally agree with you. But that also kinda ignores all the useful things a dog can be trained to do.
It’s less the calculations and more about memory bandwidth. To generate a token you need to go through all the model data, and that’s usually many many gigabytes. So the time it takes to read through in memory is usually longer than the compute time. GPUs have gb’s of RAM that’s many times faster than the CPU’s ram, which is the main reason it’s faster for llm’s.
Most tpu’s don’t have much ram, and especially cheap ones.
Reasonable smart… that works preferably be a 70b model, but maybe phi3-14b or llama3 8b could work. They’re rather impressive for their size.
For just the model, if one of the small ones work, you probably need 6+ gb VRAM. If 70b you need roughly 40gb.
And then for the context. Most models are optimized for around 4k to 8k tokens. One word is roughly 3-4 tokens. The VRAM needed for the context varies a bit, but is not trivial. For 4k I’d say right half a gig to a gig of VRAM.
As you go higher context size the VRAM requirement for that start to eclipse the model VRAM cost, and you will need specialized models to handle that big context without going off the rails.
So no, you’re not loading all the notes directly, and you won’t have a smart model.
For your hardware and use case… try phi3-mini with a RAG system as a start.
22·2 months agoI’m not saying it’s broken, but it has some design choices and functions that makes even Whatsapp a better choice for privacy minded people. Like rolling their own crypto and not having e2ee as default.
7·2 months agoSo you’re saying it’s already feature complete with most json libraries out there?
59·2 months agoYou realise there is no algorithm behind Lemmy, right?
Of course there is. Even “sort by newest” is an algorithm, and the default view is more complicated than that.
You aren’t being shoved controversial polarizing content subliminally here.
Neither are you on TikTok, unless you actively go looking for it
4·2 months agoI’ve seen Skype do that. It was a weird folder name, but gallery found it and displayed the images.
Which is how I noticed it in the first place
Hah as if. In the early 00s the mods were in maybe once or twice a day and there was tons of CP being posted.
Worst I saw was a little girl chopped into pieces, and a many -page discussion / argument if it should be sorted as CP or Necro porn. That was the old 4chan.
Even for 4chan that’s fucked up.
Oh, sweet summer child…
Yep, I usually make docker environments for cuda workloads because of these things. Much more reliable
Koboldcpp
I’m waiting for them to find a better spot on durability, weight /bulkiness and hardware like cameras.
They’re still too big and bulky for me, the other components are usually a bit behind, and the screen durability seems a bit too eeh still.
Which is to say, I’m interested in one, but they’re not there yet for me.
I gotta ask… were you around and actively using xmpp around that time?
Because I was. And xmpp struggling had nothing to do with Google
Yeah, it also has the effect that when starting up say a new postgres or web server is one simple command, a few seconds and a few mb of disk and ram, you do it more for smaller stuff.
Instead of setting up one nginx for multiple sites you run one nginx per site and have the settings for that as part of the site repository. Or when a service needs a DB, just start a new one just for that. And if that file analyzer ran in it’s own image instead of being part of the web service, you could scale that separately… oh, and it needs a redis instance and a rabbitmq server, that’s two more containers, that serves just that web service. And so on…
Things that were a huge hassle before, like separate mini vm’s for each sub-service, and unique sub-services for each service doesn’t just become practical but easy. You can define all the services and their relations in one file and docker will recreate the whole stack with all services with one command.
And then it also gets super easy to start more than one of them, for example for testing or if you have a different client. … which is how you easily reach a hundred instances running.
So instead of a service you have a service blueprint, which can be used in service stack blueprints, which allows you to set up complex systems relatively easily. With a granularity that would traditionally be insanity for anything other than huge, serious big-company deployments.
Nine. How much ram do they use? How much disk space? Try running 90, or 900. Currently, on my personal hobby kubernetes cluster, there’s 83 different instances running. Because of the low overhead, I can run even small tools in their own container, completely separate from the rest. If I run say… a postgresql server… spinning one up takes 90mb disk space for the image, and about 15 mb ram.
I worked at a company that did - among other things - hosting, and was using VM’s for easier management and separation between customers. I wasn’t directly involved in that part day to day, but was friend with the main guy there. It was tough to manage. He was experimenting with automatic creating and setting up new VM’s, stripping them for unused services and files, and having different sub-scripts for different services. This was way before docker, but already then admins were looking in that direction.
So aschually, docker is kinda made for people who runs things in VM’s, because that is exactly what they were looking for and duct taping things together for before docker came along.
Hilarious for a system which main point / feature is photo backup