What is the state of the art self hosted AI for conversation? Anything decent?

Reply to this note

Please Login to reply.

Discussion

I haven't tried myself yet... but it seems that Llama2 is the "current thing" for self hosted AI, I enjoyed this video showing how to install everything locally: https://www.youtube.com/watch?v=k2FHUP0krqg

Saw the video and found it very interesting although still needs to be more reliable. I wonder if with more tokens gets more accurate. Will check more of his vídeos. Thanks!

Waiting for a post or podcast on the findings. 📝

Want to do an in depth review of possibilities :)

"In depth" sounds like a lot of work 😂

But yeah some of these days I'll try to install something. I'm interested in the idea of having a private AI assistant/tool.

fuck you

Ollama is really fucking good and very easy to set up

Noted! Will investigate! Any other AI worth having locally? Maybe Dall-e style?

Asking for models or tools?

For tools check out secondbrain.sh, serge.chat, faraday.dev.

For models Wizard-Vicuna-Uncensored is very good at question answering and ehartford/based gives amusing conversations.

To me this is the most interesting llama related project right now:

https://github.com/ggerganov/llama.cpp

Very easy to setup:

1. git clone the project and setup it

https://github.com/ggerganov/llama.cpp#get-the-code

2. Select your LLaMA2 model already quantizated from here: https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/tree/main

3. ./main -m ./models/your_downloaded_model.bin -n 128

Have to test it. Thank you Desobediente. Question, do you know how much space it uses?