 Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
1 سال پیش |
 Olivier Chafik
|
e402de364b
`grammars`: fix resampling logic regression (#7424)
|
1 سال پیش |
 Justine Tunney
|
4e3880978f
Fix memory bug in grammar parser (#7194)
|
1 سال پیش |
 HanishKVC
|
f89fe2732c
Main+: optionally allow special tokens from user in interactive mode (#7097)
|
1 سال پیش |
 Dawid Potocki
|
83330d8cd6
main : add --conversation / -cnv flag (#7108)
|
1 سال پیش |
 RhinoDevel
|
3af34c1d1b
main : update log text (EOS to EOG) (#7104)
|
1 سال پیش |
 l3utterfly
|
8d608a81b7
main : fix off by one error for context shift (#6921)
|
1 سال پیش |
 Daniel Bevenius
|
5539e6fdd1
main : fix typo in comment in main.cpp (#6985)
|
1 سال پیش |
 Johannes Gäßler
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
1 سال پیش |
 Pedro Cuenca
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
1 سال پیش |
 Jared Van Bortel
|
1b67731e18
BERT tokenizer fixes (#6498)
|
1 سال پیش |
 Jan Boon
|
beea6e1b16
llama : save and restore kv cache for single seq id (#6341)
|
1 سال پیش |
|
Georgi Gerganov
|
05b06210c9
llama : more consistent names of count variables (#5994)
|
1 سال پیش |
 DAN™
|
5a51cc1bb4
main : support special tokens as reverse/anti prompt (#5847)
|
1 سال پیش |
|
Georgi Gerganov
|
bf08e00643
llama : refactor k-shift implementation + KV defragmentation (#5691)
|
1 سال پیش |
|
Jared Van Bortel
|
89febfed93
examples : do not assume BOS when shifting context (#5622)
|
1 سال پیش |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
1 سال پیش |
|
Georgi Gerganov
|
85910c5b30
main : ctrl+C print timing in non-interactive mode (#3873)
|
1 سال پیش |
 Michael Klimenko
|
52bb63c708
refactor : switch to emplace_back to avoid extra object (#5291)
|
1 سال پیش |
 divinity76
|
813416991a
main : allow empty --prompt-cache file (#5176)
|
1 سال پیش |
 Yann Follet
|
722d33f34e
main : add parameter --no-display-prompt (#4541)
|
2 سال پیش |
|
Georgi Gerganov
|
7edefbd79c
main : better name for variable n_print (#4874)
|
2 سال پیش |
|
Georgi Gerganov
|
3ca63b4538
main : disable token count by default (#4874)
|
2 سال پیش |
 pudepiedj
|
43f76bf1c3
main : print total token count and tokens consumed so far (#4874)
|
2 سال پیش |
|
Georgi Gerganov
|
52531fdff8
main : add self-extend support (#4815)
|
2 سال پیش |
 MaggotHATE
|
52c8bc3cf3
sampling : custom samplers order (#4285)
|
2 سال پیش |
 Andrew Godfrey
|
8efa0f6ebe
main : pass LOG_TEE callback to llama.cpp log (#4033)
|
2 سال پیش |
 Seb C
|
881800d1f0
main : Add ChatML functionality to main example (#4046)
|
2 سال پیش |
 Kerfuffle
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
2 سال پیش |
 cebtenzzre
|
b12fa0d1c1
build : link against build info instead of compiling against it (#3879)
|
2 سال پیش |
