 pudepiedj
|
a8777ad84e
parallel : add option to load external prompt file (#3416)
|
2 anni fa |
 Jhen-Jie Hong
|
97af49fa39
server : reuse llama_sample_token common util (#3494)
|
2 anni fa |
 Kenvix ⭐
|
45eba9369f
build : use std::make_tuple() for compatibility with older GCC versions (#3488)
|
2 anni fa |
 staviq
|
acec9eaaa9
common : process escape sequences in reverse prompts (#3461)
|
2 anni fa |
 goerch
|
ff5a3f0c09
Work on the BPE tokenizer (#3252)
|
2 anni fa |
 vvhg1
|
c97f01c362
infill : add new example + extend server API (#3296)
|
2 anni fa |
 Cebtenzzre
|
bc39553c90
build : enable more non-default compiler warnings (#3200)
|
2 anni fa |
 slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
2 anni fa |
 xaedes
|
0e76a8992c
train : finetune LORA (#2632)
|
2 anni fa |
 Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
2 anni fa |
|
Cebtenzzre
|
a5661d7e71
llama : allow gguf RoPE keys to be overridden with defaults (#3240)
|
2 anni fa |
|
goerch
|
b08e75baea
Fixing the last deviations from sentencepiece indicated by test-tokenizer-1 (#3170)
|
2 anni fa |
|
Cebtenzzre
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
2 anni fa |
 Roland
|
2d770505a8
llama : remove mtest (#3177)
|
2 anni fa |
 FK
|
84e723653c
speculative: add --n-gpu-layers-draft option (#3063)
|
2 anni fa |
|
Cebtenzzre
|
00d62adb79
fix some warnings from gcc and clang-tidy (#3038)
|
2 anni fa |
|
Georgi Gerganov
|
c4f496648c
metal : fix kernel_norm (fixes Falcon on Metal) (#3057)
|
2 anni fa |
|
Cebtenzzre
|
de2fe892af
examples : replace fprintf to stdout with printf (#3017)
|
2 anni fa |
|
Georgi Gerganov
|
921772104b
speculative : add grammar support (#2991)
|
2 anni fa |
|
Georgi Gerganov
|
e36ecdccc8
build : on Mac OS enable Metal by default (#2901)
|
2 anni fa |
|
Georgi Gerganov
|
47068e5170
speculative : PoC for speeding-up inference via speculative sampling (#2926)
|
2 anni fa |
|
Georgi Gerganov
|
8f429fa511
perplexity : fix ETA by warming up the model with an empty run
|
2 anni fa |
|
Cebtenzzre
|
ef15649972
build : fix most gcc and clang warnings (#2861)
|
2 anni fa |
|
staviq
|
8341a25957
main : log file (#2748)
|
2 anni fa |
|
xaedes
|
44c117f41e
train : mem usage and other improvements (#2439)
|
2 anni fa |
 Johannes Gäßler
|
6b73ef1201
YAML result logging + preset script (#2657)
|
2 anni fa |
|
Georgi Gerganov
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
2 anni fa |
 Henri Vasserman
|
6bbc598a63
ROCm Port (#1087)
|
2 anni fa |
|
Georgi Gerganov
|
cf658adc83
llm : add Falcon support (#2717)
|
2 anni fa |
 Kawrakow
|
62959e740e
Strided perplexity (#2714)
|
2 anni fa |
