Situation - You run a discord server for alt right and weirdly obsessed about the military dudes. You have a secret clearance. Do you -

[ ] Share secret intel with people who have no need to see or know about it

[ ] Do nothing

Note: There are no political or military reasons to share this info, only ego boosting yourself. 30 seconds on the clock.

oh freaking awesome, this looks amazing! Thank you so much for this!

Time to start self hosting these for my friends

For most of you suggesting hosting a repository - yes but,

Host forgejo. Just host the git mirror. It comes with a package repo out of the box. Then you have the source code and the docker images

Generally there are not LLMs that do this, but you start building up a workflow. You speak, one service reads in the audio and translates it to text. Then you feed that into an LLM, it responds in text, and you have another service translate that into audio.

Home Assistant is the easiest way to get them all put together.

https://www.home-assistant.io/integrations/assist_pipeline

Edit agree with others below. Use the apps that are made for it.

• Whisper for STT
• Any hosted LLM can work, text-generation-webui or tabbyapi
• I use xttsv2 for TTS

This post is written as if there’s only one “community”. Why does there need to be a primary? I’m here and I’m happy. If I have questions I search online or ask here, same as any other community

Wow I feel so safe now. Like Sony wrapped me up in their arms and swaddled me. Thank you papa sony

Seconded with Matrix. All I’m wanting for it is for someone to make a Discord/Revolt UI frontend for Matrix 2.0 and it’ll be a drop in replacement

Oh yeah, critical component. And vram, in fact I would only consider LLMs on a 3000+ card right now, they require quite a bit of vram

NVidia is great in a server, drivers are a pain but do-able. I have a 3000 series that I use regularly and pass into my kubernetes cluster. NVidia on a gaming rig linux is fine, but there is more overhead with the drivers.

AMD is great in gaming servers, but doesn’t have CUDA, so it’s not as useful in a server environment in my experience - if you’re thinking of doing CUDA workloads like hosting LLMs.

1060 will be a noticeable step in Jellyfin

DNS is of course the preferred approach

I wouldn’t worry about mounting your nfs shares directly to those host unless you need to. Compose has an operator similar to k8s that lets docker itself manage the shares, which is insanely useful if you lose your host. Then you don’t have to have piles of scripts to mount them.

https://stackoverflow.com/questions/45282608/how-to-directly-mount-nfs-share-volume-in-container-using-docker-compose-v3

version: "3.2"

services:
  rsyslog:
    image: jumanjiman/rsyslog
    ports:
      - "514:514"
      - "514:514/udp"
    volumes:
      - type: volume
        source: example
        target: /nfs
        volume:
          nocopy: true
volumes:
  example:
    driver_opts:
      type: "nfs"
      o: "addr=10.40.0.199,nolock,soft,rw"
      device: ":/docker/example"

So early game these trains mostly run empty. A good example is steel production. Out in Dune Desert it starts with Steel beams, Steel Pipes, and Encased Steel Beams. Each one gets a train car by default (makes sorting soooo much easier, and you don’t limit yourself to belts). However I stick with 10 because those grow. As steel grows, each one needs 2 train cars, then beams and pipes may need 3. Then all of a sudden you realize you might actually need two separate trains running around. Sure you can add another train on, but that only temporarily solves the problem. When you get into the thousands of beams/pipes per minute you start getting into needing longer trains.

Oh yeah! It looks different from the side, my brain went right to AT-AT lol

Is that an AT-AT in the background?

LLMs use a ton of VRAM, the more VRAM you have the better.

If you just need an API, then TabbyAPI is pretty great.

If you need a full UI, then Oogabooga’s TextGenration WebUI is a good place to start

Thank you, I didn’t know if people would find it useful, but I hoped some would

That’s my favorite way to play! Working collaboratively can be a lot of fun (but of course nothing wrong with going it solo either). Have fun playing it! If you’re interested, I wrote up a multiplayer “guide” that is totally optional but may help prevent arguments in the future.

Satisfactory isn’t about timing or how fast you do things, it’s about having fun and coming up with interesting ways to solve problems. I personally like to maximize everything, so for me I like to calculate out what is the max output this node can give me, and I’ll spend DAYS just building out that one factory. Other people like to just burn through and unlock things as fast as they can.

If you’re goofing around right now, then have fun and remain efficient! But I hope you aren’t seriously worried about not being “good” at satisfactory. There is no good or bad, just building a sick factory that destroys the planet. If you’re having fun, (and by fun I mean it should also feel like work lol), then you’re “good” at the game :)

Hey nice to see it’s structurally sound now!