Torrent-Tracker-Platforms VS llama.cpp

In that case, I would shop around different codebases before doing anything else (I’m a big Gazelle fan myself, but everyone I’ve ever worked with says learning PHP is a pain, which makes me a bit hesitant). HDVinnie has a good list here: https://github.com/HDVinnie/Torrent-Tracker-Platforms

https://github.com/HDVinnie/Torrent-Tracker-Platforms currently the easiest to deploy is UNIT3D,

Lazy or unskilled web administrators Most trackers use pre-made software. https://github.com/HDVinnie/Torrent-Tracker-Platforms

This project is for fun. Figured it would be a nice addition to my other three tracker related repos. https://github.com/HDVinnie/Private-Trackers-Spreadsheet https://github.com/HDVinnie/Torrent-Tracker-Platforms https://github.com/HDInnovations/UNIT3D-Community-Edition

Check out this github for links to the different tracker platforms that have been developed.

"Not so good update. We couldn't get money into the account quick enough (only had 11 days) and lost the domain, I've filled out the form that's currently at the sites address but no response yet. because of the license for the sites code we can't change the domain without paying at templateshares.net but the staff are never there any more so that's never going to happen. the only other option is to migrate the site to a new code base (https://github.com/HDVinnie/Torrent-Tracker-Platforms) which I don't have the skill to do and R [name removed] doesn't have the time to do so we are stuck in a pretty bad spot right now."

if you can compile stuff, then looking at llama.cpp (what ollama uses) is also interesting: https://github.com/ggerganov/llama.cpp

the server is here: https://github.com/ggerganov/llama.cpp/tree/master/examples/...

And you can search for any GGUF on huggingface

Yes, Metal seems to allow a maximum of 1/2 of the RAM for one process, and 3/4 of the RAM allocated to the GPU overall. There’s a kernel hack to fix it, but that comes with the usual system integrity caveats. https://github.com/ggerganov/llama.cpp/discussions/2182

For anyone interested in exploring this, llama.cpp has an example implementation here:

https://github.com/ggerganov/llama.cpp/tree/master/examples/...

Getting started with LLMs can be intimidating. In this tutorial we will show you how to fine-tune a large language model using LoRA, facilitated by tools like llama.cpp and KitOps.

well https://github.com/ggerganov/llama.cpp/issues/6849