Pi
Pi
> Inno Setup installer is a really simple thing. > And it allows to use any folder plus other things. Oh thanks for telling me that. I'll look into it....
The context size is set to max (2048) already
> is 2048 a hard limit with llama.cpp? or is that a function of the model? Yes, 2048 seems to be the hard limit. It allows you to make context...
> Are you planning on implementing context? By "context," I mean compressing previous messages and placing them in the prompt like GPT3/4's `createChatCompletion`. In theory, I could do that. But...
> I haven't tried this yet but it might help increasing prompt size by compressing the prompt. > > https://github.com/yasyf/compress-gpt I'll take a look at how it works later. If...
Yes. This project is open sourced, but technically all llama models are not. They're for research purposes only and cannot be monetized.
Temp is probably too high (0.8), iirc vicuna likes 0.3. it will be fixed when I add settings.
Yes that's a known issue with llama.cpp itself. I will try to implement a temporary fix for it soon.
I will consider changing the name to llama. I won't try to add support for all ggml versions since llama.cpp itself doesn't support the old one. I don't want to...
I support this issue! I need to be able to use Alpaca 30B and Alpaca Native 13B on my computer!!