alpaca-electron VS llama.cpp

I sympathize. There are some efforts here and there but it's not something that resonates with the enthusiast crowd much. An abandoned example here: ItsPi3141/alpaca-electron

Look up troublechute on youtube. Or alpaca electron

I recently tried alpaca electron with the 7b model. I am surprised how well this runs on my own hardware with very little CPU and RAM consumption.

Here's alpaca running in electron. Not exactly one click but close.

https://github.com/ItsPi3141/alpaca-electron

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