Earlier quoted context omitted.
I really don't like that these models can be branded as Deepseek R1.
Well, Deepseek trained them?
? Alexander is not Aristotle?!
Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
101–110 of 162 posts
Re: Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
#102Re: Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
#103Earlier quoted context omitted.
You have my curiosity. Like what and how did you find it?
Ask about Xi Jinping in all the ways you can imagine (jokes, bad habits, failures, embarrassing facts, ...). Compare the responses to other well known politicians, use the same prompt in a fresh conversation with a different name. Ask about the political system of china and its flaws. Compare the sentiment of the responses with answers about other political systems. You might get some critical answers, but the sentim…
[dead]
Re: Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
#104Earlier quoted context omitted.
Ask about Xi Jinping in all the ways you can imagine (jokes, bad habits, failures, embarrassing facts, ...). Compare the responses to other well known politicians, use the same prompt in a fresh conversation with a different name. Ask about the political system of china and its flaws. Compare the sentiment of the responses with answers about other political systems. You might get some critical answers, but the sentim…
Could it be just a bias inside the selected training material?
Feel free to call propaganda a bias if you like. But if it walks like a duck, quacks like a duck, ...
Re: Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
#105Really there needs to be a product based off of LLMs similar to Alexa or Google home where instead of connecting to the cloud it’s a locally run LLM. I don’t know why one doesn’t exist yet or why no one is working on this
Wouldn't it be due to price? Quality LLMs are expensive, so the real question is can you make a product cheap enough to still have margins and a useful enough LLM that people would buy?
Re: Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
#106Earlier quoted context omitted.
Ask about Xi Jinping in all the ways you can imagine (jokes, bad habits, failures, embarrassing facts, ...). Compare the responses to other well known politicians, use the same prompt in a fresh conversation with a different name. Ask about the political system of china and its flaws. Compare the sentiment of the responses with answers about other political systems. You might get some critical answers, but the sentim…
Could it be just a bias inside the selected training material?
Btw, the propaganda is specific towards china. If you ask about other authoritarian countries and politicians, it behaves unbiased.
Re: Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
#107When can I "apt-get install" all this fancy new AI stuff?
Not apt-get per se, but most of the infra components underlying the "AI stuff" can be `conda install`-ed.
No thank you. I spent months trying to find the source of mysterious segfaults on my system, that magically disappeared once I moved away from conda.
Sorry for not being more specific, but at this point I just lost faith in this package manager.
Re: Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
#108Earlier quoted context omitted.
Could it be just a bias inside the selected training material?
Feel free to call propaganda a bias if you like. But if it walks like a duck, quacks like a duck, ...
This is HN: my focus is technical (here specifically), maybe "technical" in world assessment and future prediction (in other pages).
I.e.: I am just trying to understand the facts.
Re: Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
#109[dead]
Re: Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5
#110Earlier quoted context omitted.
Or a couple of 12GB 3060s.
Some of us also worry about energy consumption
They idle at pretty low wattages, and since the bulk of the TDP is rated for raster workloads you usually won't see them running at full-power on compute workloads.
My 300w 3070ti doesn't really exceed 100w during inference workloads. Boot up a 1440p video game and it's a different story altogether, but for inference and transcoding those 3060s are some of the most power efficient options on the consumer market.