by run his own models he means locally running a text generation ai on his computer, because sending all that data to openai is a privacy nightmare, especially if you use it for sensitive stuff
But that’s still confusing because we already can. Yeah you might need a little bit more of hardware but… not that crazy. Plus some simpler models can be run with more normal hardware.
Max token windows are 4k for llama 2 tho there’s some fine tunes that push the context up further. Speed is limited by your budget mostly, you can stack GPUs and there are most models available (including the really expensive ones)
I’m just letting you know, If you want something easy, just use ChatGtp. I don’t find them overly expensive for what it is.
I’m trying to get to the point where I can locally run a (slow) LLM that I’ve fed my huge ebook collection too and can ask where to find info on $subject, getting title/page info back. The pdfs that are searchable aren’t too bad but finding a way to ocr the older TIFF scan pdfs and getting it to “see” graphs/images are areas I’m stuck on.
i hope you are joking because that’s a very much shitty idea. there are amazing password managers like bitwarden (open source, multi platform, externally audited) that do what you said 1000 times better. the unencrypted passwords never leave your device, and it can autocomplete them into fields
What do you mean by the second part of your comment?
by run his own models he means locally running a text generation ai on his computer, because sending all that data to openai is a privacy nightmare, especially if you use it for sensitive stuff
But that’s still confusing because we already can. Yeah you might need a little bit more of hardware but… not that crazy. Plus some simpler models can be run with more normal hardware.
Might not be easy to setup that is true.
For large context models the hardware is prohibitively expensive.
I personally use runpod. It doesn’t cost much even for the high end level stuff. Tbh the openai API is easier though and gives mostly better results.
I specifically said “large context” how many tokens can you get through before it goes insanely slow?
Max token windows are 4k for llama 2 tho there’s some fine tunes that push the context up further. Speed is limited by your budget mostly, you can stack GPUs and there are most models available (including the really expensive ones)
I’m just letting you know, If you want something easy, just use ChatGtp. I don’t find them overly expensive for what it is.
I can run 4bit quantised llama 70B on a pair of 3090s. Or rent gpu server time. It’s expensive but not prohibitive.
I’m trying to get to the point where I can locally run a (slow) LLM that I’ve fed my huge ebook collection too and can ask where to find info on $subject, getting title/page info back. The pdfs that are searchable aren’t too bad but finding a way to ocr the older TIFF scan pdfs and getting it to “see” graphs/images are areas I’m stuck on.
How many tokens can you run it for?
3k?Can’t recall exactly, and I’m getting hardwarestability issues.
you can, but things as good as chatgpt can’t be ran on local hardware yet. My main obstacle is language support other then english
I use chatgpt as my password manager.
“Hey robot please record this as the server admin password”
Then later i dont have to go looking, “hey bruv whats the server admin password?”
i hope you are joking because that’s a very much shitty idea. there are amazing password managers like bitwarden (open source, multi platform, externally audited) that do what you said 1000 times better. the unencrypted passwords never leave your device, and it can autocomplete them into fields
I was joking but i wouldnt be surprised if someone does.
phew, i was worried lmao