 k.h.lai
|
30e70334f7
llava-cli: fix base64 prompt (#7248)
|
hai 1 ano |
 Justine Tunney
|
4e3880978f
Fix memory bug in grammar parser (#7194)
|
hai 1 ano |
 cpumaxx
|
ffe666572f
llava-cli : multiple images (#6969)
|
hai 1 ano |
|
Justine Tunney
|
89b0bf0d5d
llava : use logger in llava-cli (#6797)
|
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 |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
hai 1 ano |
 John
|
aa23412989
llava : support v1.6 (#5267)
|
hai 1 ano |
 Xiao-Yong Jin
|
0ef46da632
llava-cli : always tokenize special tokens (#5382)
|
hai 1 ano |
|
John
|
6db2b41a76
llava : support for Yi-VL and fix for mobileVLM (#5093)
|
%!s(int64=2) %!d(string=hai) anos |
 Justine Tunney
|
36e5a08b20
llava-cli : don't crash if --image flag is invalid (#4835)
|
%!s(int64=2) %!d(string=hai) anos |
|
Justine Tunney
|
4af4801566
llava-cli : refactor to use sampling library (#4669)
|
%!s(int64=2) %!d(string=hai) anos |
 Kerfuffle
|
91f6499393
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
|
%!s(int64=2) %!d(string=hai) anos |
 Matthew Tejo
|
54b4df8886
Use params when loading models in llava-cli (#3976)
|
%!s(int64=2) %!d(string=hai) anos |
 Damian Stewart
|
381efbf480
llava : expose as a shared library for downstream projects (#3613)
|
%!s(int64=2) %!d(string=hai) anos |
