Inicio Explorar Axuda
Iniciar sesión
cturan
/
llama.cpp
réplica de https://github.com/cturan/llama.cpp
1
0
Fork 0
Ficheiros Incidencias 0 Wiki
Árbore: 6724ef1657
Ramas Etiquetas
llama.cpp
/
examples
/
llama.swiftui
Georgi Gerganov 0e18b2e7d0 llama.swiftui : add tinyllama 1.1B F16 %!s(int64=2) %!d(string=hai) anos
..
llama.cpp.swift 6ff39b129d llama.swiftui : add more models %!s(int64=2) %!d(string=hai) anos
llama.swiftui 0e18b2e7d0 llama.swiftui : add tinyllama 1.1B F16 %!s(int64=2) %!d(string=hai) anos
llama.swiftui.xcodeproj 800a489e4a llama.swiftui : add bench functionality (#4483) %!s(int64=2) %!d(string=hai) anos
.gitignore 800a489e4a llama.swiftui : add bench functionality (#4483) %!s(int64=2) %!d(string=hai) anos
README.md bb03290c17 examples : iOS example with swift ui (#4159) %!s(int64=2) %!d(string=hai) anos

README.md

llama.swiftui

Local inference of llama.cpp on an iPhone. So far I only tested with starcoder 1B model, but it can most likely handle 7B models as well.

https://github.com/bachittle/llama.cpp/assets/39804642/e290827a-4edb-4093-9642-2a5e399ec545