local_llama VS llama.cpp

I work with AWS daily, terraform, Python and java creating and maintaining enterprise solutions. I have played with sagemaker but it is so expensive I hate to leave it up for longer than a day. I downloaded and created a chat with your docs (entirely in airplane mode) here point being that I’ve hosted models both locally and in the cloud. But just ended up sticking to API calls as it’s so cheap

I posted the speed of mine in the readme https://github.com/jlonge4/local_llama

I would like to use this tool https://github.com/jlonge4/gpt_chatwithPDF/blob/main/gpt_chat_api.py but unfortunately the local version (https://github.com/jlonge4/local_llama) is bound to the CPU and thus quiet slow. Is there any way i could get textgenwebui working with the above stated tool?

This is what you want https://github.com/jlonge4/local_llama it’s fully offline with no third parties, but the setup is a bit involved

Or try this https://github.com/jlonge4/local_llama

Code here if interested

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

Have just done this recently for local chat with pdf feature in https://recurse.chat. (It's a macOS app that has built-in llama.cpp server and local vector database)

Running an embedding server locally is pretty straightforward:

- Get llama.cpp release binary: https://github.com/ggerganov/llama.cpp/releases

Ah, thanks for this! I can't edit my parent comment that you replied to any longer unfortunately.

As I said, I only compared the contributors graphs [0] and checked for overlaps. But those apparently only go back about year and only list at most 100 contributors ranked by number of commits.

[0]: https://github.com/ollama/ollama/graphs/contributors and https://github.com/ggerganov/llama.cpp/graphs/contributors