I really wish when people say stuff like this, I don’t have to resort to simply believe what they say at face value because they provide something like a fucking link or an article I can read to back up what they say.
I really wish when people say stuff like this, I don’t have to resort to simply believe what they say at face value because they provide something like a fucking link or an article I can read to back up what they say.
It abstracts away llama.cpp in a way that, frankly, leaves a lot of performance and quality on the table.
OP, do you have any telemetry you can show us comparing the performance difference between what you setup on this guide and an Ollama setup? Otherwise, at face value, I’m going to assume this is another thing on the internet i have to assume is uncorroborated bullshit. Apologies for sounding rude.
I don’t like some things about the devs. I won’t rant, but I especially don’t like the hint they’re cooking up something commercial.
This concerns me. Please provide links for us to read here about this. I would like any excuse to uninstall Ollama. Thank you!
deleted by creator
I’m self hosting Vaultwarden and my home server got killed by the hurricane, yet I can still access my passwords just fine on the app because it stores them locally encrypted on my phone from the last time it synced. I just can’t update or change anything until I can bring everything back on.
So, host your own shit you cowards, it’ll be fine.
Yeah, either secure copy (SCP) or rsync are the ways to do this securely.
Why not use this and select whatever LLM to leverage as a RAG? It literally allows you to self host the model and select any model for both chat and RAG analysis. I have it set to Hermes3 8B for chat and a 1.3B Llama3 as the RAG.
You don’t even need a GPU, i can run Ollama Open-WebUI on my CPU with an 8B model fast af
Never heard of either one of these sites. What are they for?
Correct, all VPN applications override the DNS server of any system it’s installed on.
pip is legit trash when trying to update modules
$1/month isn’t bad though.
I just heard some of their tracks and I feel like it wasn’t a huge loss not being able to hear a Duran Duran or Depeche Mode wannabe band while I’m murdering hookers in GTA6
What is the point of this when the OG Jellyfin has an android app?
Agreed, but their entire fab process was stolen via corporate espionage and is not a novel design in any way.
Toss OpenWRT into the trash and install OPNSense instead.
No, you really shouldn’t listen to critics, including myself. You should commit to your vision of your game, since it’s your art. Everything I said is for a game i want, not for a game you want to make
Realistic graphics do not do your wonderful game any favors, I recommend deliberately forcing an overlay filter of some kind that cannot be adjusted, such as a film grain or 90’s VHS signal.
What game engine did you use? Animations look rigid like a 90’s Pixar film, textures look like shit, lighting looks bad. If you stayed with a unique consistent non-realistic theme, such as a 90’s PS1 game aesthetic, it would look better and people would forgive the shitty looks.
There are only two CVEs related to Tuya and both are related to only one of their camera products. Their protocol has yet to be exploited. If there are zero days, then this is the case for literally everything and your statement is useless.
Again, please post something for us all to read, or all this stuff you are saying here is worthless nonsense.