Hacker News Reader

Does this really need to be a fork of llama.cpp? It seems like there's no real changes to the code.

It reworks the interactive mode into a chat interface, which -if my code was cleaner- could have just been a pull request.

"Clean Code, Horrible Performance" :)

There is an interactive mode in llama.cpp

https://github.com/ggerganov/llama.cpp/blob/master/main.cpp#...

EDIT: I see now you are saying you re-worked the existing interactive mode. I still think your changes could be a PR into the original repo

Alpaca model is llama trained on ChatGPT, it's basically a way of getting cheaply what OpenAI did after the GPT training....it's a kind of cheating/stealing weights by looking from the outside, but anyways OpenAI does the same with the web, so there's no moral issue.

> cheating/stealing weights by looking from the outside

What do you mean by this? Can you please elaborate.

Reply on news.ycombinator.com