 Georgi Gerganov
|
6b0a7420d0
llama : KV cache view API + better KV cache management (#4170)
|
2 years ago |
 Seb C
|
881800d1f0
main : Add ChatML functionality to main example (#4046)
|
2 years ago |
 Kerfuffle
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
2 years ago |
|
Georgi Gerganov
|
8f961abdc4
speculative : change default p_accept to 0.5 + CLI args (#3919)
|
2 years ago |
|
Georgi Gerganov
|
05816027d6
common : YAYF (yet another YARN fix) (#3925)
|
2 years ago |
 cebtenzzre
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
2 years ago |
|
cebtenzzre
|
898aeca90a
llama : implement YaRN RoPE scaling (#2268)
|
2 years ago |
 bandoti
|
0e40806c1c
common : allow caller to handle help/argument exceptions (#3715)
|
2 years ago |
|
Georgi Gerganov
|
d1031cf49c
sampling : refactor init to use llama_sampling_params (#3696)
|
2 years ago |
|
Georgi Gerganov
|
0e89203b51
speculative : add tree-based sampling example (#3624)
|
2 years ago |
 staviq
|
1a159553f9
tokenizer : special token handling (#3538)
|
2 years ago |
 M. Yusuf Sarıgöz
|
370359e5ba
examples: support LLaVA v1.5 (multimodal model) (#3436)
|
2 years ago |
|
Kerfuffle
|
70c29da118
common : fix mirostat state when using multiple sequences (#3543)
|
2 years ago |
 pudepiedj
|
a8777ad84e
parallel : add option to load external prompt file (#3416)
|
2 years ago |
 vvhg1
|
c97f01c362
infill : add new example + extend server API (#3296)
|
2 years ago |
 slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
2 years ago |
 xaedes
|
0e76a8992c
train : finetune LORA (#2632)
|
2 years ago |
|
Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
2 years ago |
|
Cebtenzzre
|
51a7cf5c6e
examples : fix RoPE defaults to match PR #3240 (#3315)
|
2 years ago |
|
Cebtenzzre
|
8781013ef6
make : restore build-info.h dependency for several targets (#3205)
|
2 years ago |
|
Cebtenzzre
|
e6616cf0db
examples : add compiler version and target to build info (#2998)
|
2 years ago |
|
Cebtenzzre
|
80291a1d02
common : do not use GNU zero-length __VA_ARGS__ extension (#3195)
|
2 years ago |
 Roland
|
2d770505a8
llama : remove mtest (#3177)
|
2 years ago |
 FK
|
84e723653c
speculative: add --n-gpu-layers-draft option (#3063)
|
2 years ago |
|
Cebtenzzre
|
00d62adb79
fix some warnings from gcc and clang-tidy (#3038)
|
2 years ago |
|
Georgi Gerganov
|
e36ecdccc8
build : on Mac OS enable Metal by default (#2901)
|
2 years ago |
|
Georgi Gerganov
|
47068e5170
speculative : PoC for speeding-up inference via speculative sampling (#2926)
|
2 years ago |
|
staviq
|
8341a25957
main : log file (#2748)
|
2 years ago |
 Johannes Gäßler
|
6b73ef1201
YAML result logging + preset script (#2657)
|
2 years ago |
|
Georgi Gerganov
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
2 years ago |
