| .. |
|
CMakeLists.txt
|
381efbf480
llava : expose as a shared library for downstream projects (#3613)
|
il y a 2 ans |
|
base64.hpp
|
381efbf480
llava : expose as a shared library for downstream projects (#3613)
|
il y a 2 ans |
|
build-info.cpp.in
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
il y a 2 ans |
|
common.cpp
|
2833a6f63c
ggml-cuda : fix f16 mul mat (#3961)
|
il y a 2 ans |
|
common.h
|
8f961abdc4
speculative : change default p_accept to 0.5 + CLI args (#3919)
|
il y a 2 ans |
|
console.cpp
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
il y a 2 ans |
|
console.h
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
il y a 2 ans |
|
grammar-parser.cpp
|
f439e506e8
ggml : fix rope + llama minor optimizations (#3560)
|
il y a 2 ans |
|
grammar-parser.h
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
il y a 2 ans |
|
log.h
|
a2758d08e4
log : make generating separate log files optional (#3787)
|
il y a 2 ans |
|
sampling.cpp
|
e75dfdd31b
sampling : null grammar field after reset (#3885)
|
il y a 2 ans |
|
sampling.h
|
238657db23
samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841)
|
il y a 2 ans |
|
stb_image.h
|
370359e5ba
examples: support LLaVA v1.5 (multimodal model) (#3436)
|
il y a 2 ans |
|
train.cpp
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
il y a 2 ans |
|
train.h
|
4760e7cc0b
sync : ggml (backend v2) (#3912)
|
il y a 2 ans |
Georgi Gerganov
4760e7cc0b
sync : ggml (backend v2) (#3912)