chatgpt-web VS llama.cpp

Wow, this is almost as good as chatgpt-web [0], and it works offline and is free. Amazing.

In case anyone here hasn't used chatgpt-web, I recommend trying it out. With the new GPT-4 models you can chat for way cheaper than paying for ChatGPT Plus, and you can also switch back to the older (non-nerfed) GPT-4 models that can still actually code.

[0]: https://github.com/Niek/chatgpt-web

Came across this: https://github.com/Niek/chatgpt-web

I tried asking AutoGPT to do it, but it spins its wheels. It can't even seem to access the folder, and I'm not running it in a docker. So I've given up on trying to code it myself. https://niek.github.io/chatgpt-web/ is basically what I need, but with GPT4, since 3.5 is already free.

And if you wanna just try it out they have it up on https://niek.github.io/chatgpt-web/

Basically, with API, you pay per message. You can just enable it and try it out on a front-end like https://niek.github.io/chatgpt-web/ .

Looks great! I have something very similar:

https://github.com/Niek/chatgpt-web

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