• 0 Posts
  • 4 Comments
Joined 8 months ago
cake
Cake day: June 30th, 2025

help-circle

  • Unless someone has released something new while I haven’t been paying attention, all the gen AIs are essentially frozen. Your use of them can’t impact the actual weights inside of the model.

    If it seems like it’s remember things is because of the actual input of the LLM is larger than the input you will usually give it.

    For instance lets say the max input for a particular LLM is 9096 tokens. The first part of that will be instructions from the owners of the LLM to prevent their model from being used for things they don’t like. Lets say the first 2000 tokens. That leaves 7k or so for a conversation that will be ‘remembered’.

    Now if someone was really savvy, they’d have the model generate summaries of the conversation and stick them into another chunk of memory, maybe another 2000 tokens worth, that way it will seem to remember more than just the current thread. That would leave you with 5000 tokens to have a running conversation.


  • Here’s mine, no judging for how I set the ip

    name: jellyfin
    services:
        jellyfin:
            container_name: jellyfin.live
            networks:
                mynet:
                    ipv4_address: 192.168.5.3
            ports:
                - 8096:8096
            volumes:
                - jellyfin-config:/config
                - jellyfin-cache:/cache
                - type: bind
                  source: /mnt
                  target: /Media Disk 1
                - type: bind
                  source: /mnt
                  target: /Media Disk 2
                - type: bind
                  source: /mnt
                  target: /Media Disk 3
            environment:
                - HEALTHCHECK_URL=192.168.5.3
            restart: unless-stopped
            deploy:
                resources:
                    reservations:
                        devices:
                            - driver: nvidia
                              count: all
                              capabilities:
                                  - gpu
            image: jellyfin/jellyfin:latest
    networks:
        mynet:
            external: true
            name: mynet
    volumes:
        jellyfin-config:
            external: true
            name: jellyfin-config
        jellyfin-cache:
            external: true
            name: jellyfin-cache
    
    

    The section on the GPU looks like yours. I had to do something to get it working, but it’s been forever.