Thiago Padilha

Thanks. I thought it was responsibility of terminfo to deal with color numbers outside the range. In my xterm-256color terminfo `set_a_foreground` is defined as `\E[%?%p1%{8}%

> How hard would it be to add a mode where it could stay running and be ready to accept more text piped to standard input? #278 implements a way...

> I wouldn't go as far to assume: [Statista: Global market share held by operating systems for desktop PCs, January 2023](https://www.statista.com/statistics/218089/global-market-share-of-windows-7/) Windows 74.14% , macOS 15.33% , Linux 2.91% ,...

> This is essentially what fork() does anyway, but instead of duplicating the whole process (and incurring a performance penalty), only the model would be duplicated instead. Fork is very...

@anzz1 I'm also interested in the tcp_server functionality, which is why I'm rebasing and using it on my private fork (Not doing any updates though, so you can consider it...

> Could we load LoRA with llama.cpp? Some languages are not well supported in original llama, but may be provided via LoRA. Yes, you just need to use the script...

Here's a comparison with GPT 3.5:  I tried to raise "temp" to 0.7 to match that of GPT 3.5 but it resulted in a worse solution (even though the...

> How does this PR tie into the current active refactor here https://github.com/ggerganov/llama.cpp/pull/77 ? I was not aware of that PR, I should have searched it first. The only reason...

> Not my call, but you could review the other PR with your insight :) I had a quick look and it seems that the goal in #77 is to...

Closing in favor of #278