 Xuan Son Nguyen
|
96952e7181
llama : fix `llama_chat_format_single` for mistral (#8657)
|
hai 1 ano |
 Georgi Gerganov
|
6af51c0d96
main : print error on empty input (#8456)
|
hai 1 ano |
|
Xuan Son Nguyen
|
a38b884c6c
cli: add EOT when user hit Ctrl+C (#8296)
|
hai 1 ano |
 fairydreaming
|
807b0c49ff
Inference support for T5 and FLAN-T5 model families (#5763)
|
hai 1 ano |
|
Xuan Son Nguyen
|
9ef0780062
Fix new line issue with chat template, disable template when in-prefix/suffix is set (#8203)
|
hai 1 ano |
|
Xuan Son Nguyen
|
72272b83a3
fix code typo in llama-cli (#8198)
|
hai 1 ano |
|
Xuan Son Nguyen
|
48e6b92cc3
Add chat template support for llama-cli (#8068)
|
hai 1 ano |
|
Georgi Gerganov
|
1442677f92
common : refactor cli arg parsing (#7675)
|
hai 1 ano |
 Brian
|
d298382ad9
main: replace --no-special with --special (#7534)
|
hai 1 ano |
 Justine Tunney
|
00c6390793
main : don't print special tokens with --grammar (#6923)
|
hai 1 ano |
|
Georgi Gerganov
|
fbf777d2b9
main : minor (#7462)
|
hai 1 ano |
|
Georgi Gerganov
|
6ff13987ad
common : normalize naming style (#7462)
|
hai 1 ano |
 Olivier Chafik
|
e402de364b
`grammars`: fix resampling logic regression (#7424)
|
hai 1 ano |
|
Justine Tunney
|
4e3880978f
Fix memory bug in grammar parser (#7194)
|
hai 1 ano |
 HanishKVC
|
f89fe2732c
Main+: optionally allow special tokens from user in interactive mode (#7097)
|
hai 1 ano |
 Dawid Potocki
|
83330d8cd6
main : add --conversation / -cnv flag (#7108)
|
hai 1 ano |
 RhinoDevel
|
3af34c1d1b
main : update log text (EOS to EOG) (#7104)
|
hai 1 ano |
 l3utterfly
|
8d608a81b7
main : fix off by one error for context shift (#6921)
|
hai 1 ano |
 Daniel Bevenius
|
5539e6fdd1
main : fix typo in comment in main.cpp (#6985)
|
hai 1 ano |
 Johannes Gäßler
|
28103f4832
Server: fix seed for multiple slots (#6835)
|
hai 1 ano |
 Pedro Cuenca
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
hai 1 ano |
 Jared Van Bortel
|
1b67731e18
BERT tokenizer fixes (#6498)
|
hai 1 ano |
 Jan Boon
|
beea6e1b16
llama : save and restore kv cache for single seq id (#6341)
|
hai 1 ano |
|
Georgi Gerganov
|
05b06210c9
llama : more consistent names of count variables (#5994)
|
hai 1 ano |
 DAN™
|
5a51cc1bb4
main : support special tokens as reverse/anti prompt (#5847)
|
hai 1 ano |
|
Georgi Gerganov
|
bf08e00643
llama : refactor k-shift implementation + KV defragmentation (#5691)
|
hai 1 ano |
|
Jared Van Bortel
|
89febfed93
examples : do not assume BOS when shifting context (#5622)
|
hai 1 ano |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
hai 1 ano |
|
Georgi Gerganov
|
85910c5b30
main : ctrl+C print timing in non-interactive mode (#3873)
|
hai 1 ano |
 Michael Klimenko
|
52bb63c708
refactor : switch to emplace_back to avoid extra object (#5291)
|
hai 1 ano |
