| .. |
|
CMakeLists.txt
|
70c29da118
common : fix mirostat state when using multiple sequences (#3543)
|
2 lat temu |
|
common.cpp
|
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
|
2 lat temu |
|
common.h
|
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
|
2 lat temu |
|
console.cpp
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
2 lat temu |
|
console.h
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 lat temu |
|
grammar-parser.cpp
|
f439e506e8
ggml : fix rope + llama minor optimizations (#3560)
|
2 lat temu |
|
grammar-parser.h
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
2 lat temu |
|
log.h
|
a2758d08e4
log : make generating separate log files optional (#3787)
|
2 lat temu |
|
sampling.cpp
|
e75dfdd31b
sampling : null grammar field after reset (#3885)
|
2 lat temu |
|
sampling.h
|
238657db23
samplers : Min-P sampler implementation [alternative to Top P/Top K] (#3841)
|
2 lat temu |
|
stb_image.h
|
370359e5ba
examples: support LLaVA v1.5 (multimodal model) (#3436)
|
2 lat temu |
|
train.cpp
|
73bdcb395e
finetune : add -ngl parameter (#3762)
|
2 lat temu |
|
train.h
|
73bdcb395e
finetune : add -ngl parameter (#3762)
|
2 lat temu |
cebtenzzre
898aeca90a
llama : implement YaRN RoPE scaling (#2268)