Artefact2

Which GGUF is right for me? (Opinionated)

Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggerganov/llama.cpp#5962

In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.

llama.cpp feature matrix

See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix

rafaqz

#=
This julia script converts fortran 90 code into julia.
It uses naive regex replacements to do as much as possible,
but the output WILL need further cleanup.

Known conversion problems such as GOTO are commented and marked with FIXME

Most variable declaration lines are entirely deleted, which may or
may not be useful. 

mimikadze

# Start with export LC_ALL=C && mc on OSX
[skin]
    description = Solarized (mostly) dark skin for Midnight Commander.
    256colors = true

[Lines]
    horiz = ─
    vert = │
    lefttop = ┌
    righttop = ┐