I imagine that was part of it, but I doubt it’s the actual main reason. More of a post justification.
projectmoon
Keyoxide: aspe:keyoxide.org:MWU7IK7RMUTL3AP6U6UWCF4LHY
- 0 Posts
- 21 Comments
projectmoon@lemm.eeto
Technology@lemmy.world•Gov. Landry signs new drone defense law; first in nationEnglish
7·1 year agoOr if you just ignore federal courts, which seems to be the current fashion.
projectmoon@lemm.eeto
Lord Of The Rings Memes@lemmy.dbzer0.com•Once OP gets to Rivendell, howeverEnglish
8·2 years agoWhat is actually happening to the computer in the image?
projectmoon@lemm.eeto
Technology@lemmy.world•Google created a new AI model for talking to dolphinsEnglish
20·2 years agoThis is probably one of the best actual uses for something like generative AI. With enough data, they should be able to vectorize and translate dolphin language, assuming there is one.
projectmoon@lemm.eeto
Technology@lemmy.world•Thanks to Nvidia, there's a new generation of PCs coming, and they'll be running LinuxEnglish
29·2 years agoDon’t know about “always.” In recent years, like the past 10 years, definitely. But I remember a time when Nvidia was the only reasonable recommendation for a graphics card on Linux, because Radeon was so bad. This was before Wayland, and probably even before AMD bought ATI. And it was certainly long before the amdgpu drivers existed.
For stuff like that, it’s best to have an auto formatter like checkstyle or something.
Had a team lead that kept requesting nitpicky changes, going in a FULL CIRCLE about what we should change or not, to the point that changes would take weeks to get merged. Then he had the gall to say that changes were taking too long to be merged and that we couldn’t just leave code lying around in PRs.
Jesus fucking Christ.
There’s a reason that team imploded…
Stærsta þjóðin í heimi!
Skálmöld á Sauðárkróki? Hvenær ætla þau að koma?
projectmoon@lemm.eetoMicroblog Memes@lemmy.world•"Whoa, check out this squirrel!"English
8·2 years agoWell VTR is a roleplaying game. It’s similar to Vampire the Masquerade, but different setting and somewhat different mechanics. I guess it’s best explained as “nutrients.” Animal blood and blood from e.g. blood bags gives less Vitae (magic blood points resource) than blood harvested from living humans. And as the character becomes more powerful, eventually that “lesser” blood can’t actually give them Vitae.
The vampiric curse in VTR is explicitly stated to be supernatural, though, so there’s not a necessary scientific explanation for it. The curse imparts the Beast, which is the predator in all vampires.
projectmoon@lemm.eetoMicroblog Memes@lemmy.world•"Whoa, check out this squirrel!"English
17·2 years agoSome fiction has it. In vampire the requiem, low level vampires can survive on animal blood. But more powerful ones need human or even vampire blood.
projectmoon@lemm.eeto
Technology@lemmy.world•Intel says integrating RAM into Lunar Lake SoC was a mistake, might abandon desktop GPUs againEnglish
3·2 years agoWhere can I get a sub 400 AMD card with 26 GB of VRAM?
projectmoon@lemm.eeto
Technology@lemmy.world•What Ever Happened to MSN Messenger?English
31·2 years agoHave you tried Matrix?
LLMs are statistical word association machines. Or tokens more accurately. So if you tell it to not make mistakes, it’ll likely weight the output towards having validation, checks, etc. It might still produce silly output saying no mistakes were made despite having bugs or logic errors. But LLMs are just a tool! So use them for what they’re good at and can actually do, not what they themselves claim they can do lol.
projectmoon@lemm.eeto
Selfhosted@lemmy.world•Guide to Self Hosting LLMs Faster/Better than OllamaEnglish
1·2 years agoOpenWebUI connected tabbyUI’s OpenAI endpoint. I will try reducing temperature and seeing if that makes it more accurate.
projectmoon@lemm.eeto
Selfhosted@lemmy.world•Guide to Self Hosting LLMs Faster/Better than OllamaEnglish
1·2 years agoContext was set to anywhere between 8k and 16k. It was responding in English properly, and then about halfway to 3/4s of the way through a response, it would start outputting tokens in either a foreign language (Russian/Chinese in the case of Qwen 2.5) or things that don’t make sense (random code snippets, improperly formatted text). Sometimes the text was repeating as well. But I thought that might have been a template problem, because it seemed to be answering the question twice.
Otherwise, all settings are the defaults.
projectmoon@lemm.eeto
Selfhosted@lemmy.world•Guide to Self Hosting LLMs Faster/Better than OllamaEnglish
1·2 years agoI tried it with both Qwen 14b and Llama 3.1. Both were exl2 quants produced by bartowski.
projectmoon@lemm.eeto
Selfhosted@lemmy.world•Guide to Self Hosting LLMs Faster/Better than OllamaEnglish
3·2 years agoPerplexica works. It can understand ollama and custom OpenAI providers.



I know. I have NodeBB as a backup.