centomila

joined 11 months ago
[โ€“] [email protected] 1 points 11 months ago
[โ€“] [email protected] 1 points 11 months ago

Next time, I will ask here before asking ChatGPT :D

[โ€“] [email protected] 1 points 11 months ago (1 children)

Perfect timing. I quit just today :D

Just installed with docker with this and it works great. https://github.com/AmruthPillai/Reactive-Resume/blob/main/tools/compose/simple.yml

After inserting a key created on https://platform.openai.com/api-keys , I tried the GPT functionality, but I always receive an error in a toast notification

404 This is a chat model and not supported in the v1/completions endpoint. Did you mean to use v1/chat/completions?

Also, does it utilize GPT-3.5 or GPT-4

 

Hello, beautiful people of this community! As a newcomer, I'm eager to learn from your experiences. I'm facing a challenge in accessing my home server from my iOS device and am looking for alternative solutions or different approaches:

  • Internet Constraints: I'm using Fastweb in Italy, which unfortunately does not provide a public IP.
  • Server Setup: My home server is an old laptop running Ubuntu Server 23.10.
  • Music Management: Jellyfin as docker is my go-to for managing my music collection.
  • Current VPN Solution: I've implemented ZeroTier on the server and ZeroTier One on my iPhone.

The Challenge

While the current setup with ZeroTier does function, it's not without its issues. Every time I switch from WiFi to 4G/LTE, I have to manually open ZeroTier One, disconnect, and reconnect. This is a repetitive and often frustrating process.

Moreover, without this manual reconnection, no client seems capable of connecting to the server, despite the VPN icon being displayed on my phone's top bar. Both Finamp and Substreamer have failed in this aspect.

Are there any alternative solutions to ZeroTier that might work better with my setup? Or perhaps a different approach to this problem that I haven't considered? I would greatly appreciate any advice or insights you can provide!

[โ€“] [email protected] 1 points 11 months ago

I recommend LMSTUDIO (https://lmstudio.ai/).

It allows you to manage and download models from Hugging Face, and suggests models compatible with your machine. Additionally, it can initiate a local HTTP server that functions similarly to OpenAI's API."