671B parameters! Well, it doesn't look like I'll be running that locally.
Deepseek R1-0528
131–140 of 264 posts
Re: Deepseek R1-0528
#132671B parameters! Well, it doesn't look like I'll be running that locally.
there is a small community of people that do indeed run this locally. typically on CPU/RAM (lots and lots of RAM), insofar as that's cheaper than GPU(s).
Re: Deepseek R1-0528
#133Deepseek seems to be one of the few LLMs that run on a iPod Touch because of the older version of ios.
... What?
Re: Deepseek R1-0528
#134What use cases are people using local LLMs for? Have you created any practical tools that actually increase your efficiency? I've been experimenting a bit but find it hard to get inspiration for useful applications
Anyone who does not want to leak their data? I am actually surprised that people are ok with trusting their secrets to a random foreign company.
Re: Deepseek R1-0528
#135Earlier quoted context omitted.
>overly tuning models just to specific test already published tests, rather than focusing on making them generalize. I think you just described SATs and other standardized tests
SAT has a correlation to IQ of 0.82 to 0.86 and I do think IQ is very useful in judging intelligence. https://gwern.net/doc/iq/high/smpy/2004-frey.pdf
It's a useful diagnostic when used in a battery of diagnostic tests of cognitive function, but to the point of this thread: it is notoriously not a good ranking mechanism.
Re: Deepseek R1-0528
#136Deepseek seems to be one of the few LLMs that run on a iPod Touch because of the older version of ios.
Hey! You! You can't just say that and not explain. Come back.
Re: Deepseek R1-0528
#137Earlier quoted context omitted.
But where's the source? I just see a binary blob, what makes it open source?
The weights are the source. It isn't as though something was compiled into weights. They're trained directly. But I know what you mean, it would be more open to have the training pipeline and souce dataset available.
The weights seem much more like a binary to me, the training pipeline the compiler, and the training dataset the source.
Re: Deepseek R1-0528
#138What use cases are people using local LLMs for? Have you created any practical tools that actually increase your efficiency? I've been experimenting a bit but find it hard to get inspiration for useful applications
I have a signal tracer that evaluates unusual trading volumes. Given those signals, my local agent receives news items through API to make an assessment what happens. This helps me tremendously. If I would do this through a remote app, I'd have to spend a several dollars per day. So I have this on existing hardware.
Thank you, this is a great example!
Re: Deepseek R1-0528
#139What use cases are people using local LLMs for? Have you created any practical tools that actually increase your efficiency? I've been experimenting a bit but find it hard to get inspiration for useful applications
Anyone who does not want to leak their data? I am actually surprised that people are ok with trusting their secrets to a random foreign company.
But what do you do with these secrets? Like tagging emails, summarizing documents?
Re: Deepseek R1-0528
#140Earlier quoted context omitted.
it's got more 'source' than whatever OpenAI provides for their models.
No it doesn't, it has exactly the same source, zero. It has more downloadable binary.
That’s the ‘source’ for what the model spits out though, if not the source for what spits out the model.