tjohnman
tjohnman
The editor text area keeps focus even when you switch to the display tab, resulting in accidental code modification while trying to input keystrokes into the emulator.
I haven't found a consistent pattern to reproduce this, but sometimes the model will continue outputting text even after it has printed the reverse prompt. If colors are enabled, they...
As per https://github.com/ggerganov/llama.cpp/blob/da5303c1ea68aa19db829c634f1e10d08d409680/main.cpp#L1066 the EOS flag in interactive mode simply causes `is_interacting` to switch on, and so it serves as a way to end the current series of tokens and...
This fixes bug #292 as suggested [here](https://github.com/ggerganov/llama.cpp/issues/292#issuecomment-1476318351).
In interactive mode, every time the model has to respond to user input it has an increasingly reduced token budget, eventually generating only a few words before stopping. The token...
Sometimes we might want to use a reverse prompt but we want to let the model generate tokens right after the initial prompt. So we don't force user input mode...
### Describe the bug Sometimes the config dictionary does not contain some keys that are assumed to be in it, and the script crashes due to KeyError. ### Affected versions...
### Describe the bug Yin-Yang does not start. ### Affected versions - Yin-Yang version: I tried building master and beta from source. I also tried the 3.2.4 release package. ###...
If you have something like this in PHP code: `$variable .= "stuff {\n ";` atom-auto-indent will think we're actually opening a pair of braces and indent the lines following this...
Your shell script examples use /bin/sh as the interpreter but use bash equality checks, which break the script right from the get-go. You also mention our .emacs file right at...