Bloefz

joined 2 months ago
[–] Bloefz@lemmy.world 1 points 1 month ago

Really? Wow I didn't realise there were still countries without gay marriage in Europe. Well except the Vatican maybe πŸ˜‚ but yeah if they respect them from other countries no idea

[–] Bloefz@lemmy.world 2 points 1 month ago* (last edited 1 month ago)

I'm sorry πŸ˜” I have two friends from Slovakia and they are really worried too. They don't live there anymore but they left before Fico.

But yes good point this could cause them leaving the EU. I doubt that they will push for that though. Because of subsidies. Same reason why Hungary doesn't consider leaving.

[–] Bloefz@lemmy.world 54 points 1 month ago (7 children)

And Hungary and Slovakia don't forget!

[–] Bloefz@lemmy.world 2 points 1 month ago* (last edited 1 month ago)

Meh he's a European citizen too. He's entitled to his opinion just as I am to mine.

And I agree with him. With the US pulling their nuclear umbrella away we need more deterrent against Russia so that they never consider attacking us.

I think we should have more strategic weapons though, not tactical. The type that you have just to never use. For tactical ones the barrier is lower to use them. Too low, IMO.

[–] Bloefz@lemmy.world 46 points 1 month ago* (last edited 1 month ago) (2 children)

The threat of trucks crashing into schools isn’t the only problem that the data center has brought. Local residents Joseph and Robin Williams told WWNO that they’ve noticed their tap water is frequently rust colored since Meta started building the data center, and they say their electricity frequently goes off for hours on end with no warning.

Wow you'd expect this in a third world country, not a place that should have standards πŸ™„ And is the richest in the world.

[–] Bloefz@lemmy.world 18 points 1 month ago

Gratitude for asking them to fully surrender to Putin's wishes??

[–] Bloefz@lemmy.world 1 points 1 month ago (1 children)

Thank you so much!! I have been putting it off because what I have works but a time will soon come when I'll want to test new models.

I'm looking for a server but not many parallel calls because I would like to use as much context as I can. When making space for e.g. 4 threads, the context is split and thus 4x as small. With llama 3.1 8b I managed to get 47104 context on the 16GB card (though actually using that much is pretty slow). That's with KV quant to 8b too. But sometimes I just need that much.

I've never tried the llama.cpp directly, thanks for the tip!

Kobold sounds good too but I have some scripts talking to it directly. I'll read up on that too see if it can do that. I don't have time now but I'll do it in the coming days. Thank you!

[–] Bloefz@lemmy.world 2 points 1 month ago* (last edited 1 month ago)

I don't think that's a problem. I live in Spain and speak Spanish daily with real people, many of them my friends. They'll correct me if needed, they often do. Though most are my own mistakes.

Don't forget people give wrong answers too. But people aren't available 24/7 to help me.

[–] Bloefz@lemmy.world 2 points 1 month ago (3 children)

Agreed. The way they just dumped support for my card in some update with some vague reason also irked me (we need a newer rocm they said but my card works fine with all current rocm versions)

Also the way they're now trying to sell cloud AI means their original local service is in competition to the product they sell.

I'm looking to use something new but I don't know what yet.

[–] Bloefz@lemmy.world 10 points 1 month ago (5 children)

I have one server with a cheap MI50 instinct. Those come for really cheap on eBay. And it's got really good memory bandwidth with HBM2. They worked ok with ollama until recently when they dropped support for some weird reason but a lot of other software still works fine. Also older models work fine on old ollama.

The other one runs an RTX 3060 12GB. I use this for models that only work on nvidia like whisper speech recognition.

I tend to use the same models for everything so I don't have the delay of loading the model. Mainly uncensored ones so it doesn't choke when someone says something slightly sexual. I'm in some very open communities so standard models are pretty useless with all their prudeness.

For frontend i use OpenWebUI and i also run stuff directly against the models like scripts.

[–] Bloefz@lemmy.world 6 points 1 month ago (4 children)

I mainly use it for Spanish which I have a basic proficiency in. It just accompanies me on my learning journey. It may be wrong sometime but not often. Like the other reply said, LLMs are good at languages, it's what they were originally designed for until people found out they could do more (but not quite as well).

And as for filtering, I just use it as a news feed sanitizer with a whole bunch of rules. It will miss things sometimes but it's also my ruleset that's not perfect. I often come across the unfiltered sources anyway and even if it misses something, it's only news. Nothing really important to me.

view more: next β€Ί