 Nigel Bosch
|
a2ca4e9de9
Handle null rope scaling value (#2793)
|
%!s(int64=2) %!d(string=hai) anos |
 klosax
|
2ba83c8685
Fix spm whitespaces (#2806)
|
%!s(int64=2) %!d(string=hai) anos |
 lon
|
bae5c5f679
examples : skip unnecessary external lib in server README.md how-to (#2804)
|
%!s(int64=2) %!d(string=hai) anos |
 Marcus Dunn
|
232caf3c15
llama : fix struct decl (#2790)
|
%!s(int64=2) %!d(string=hai) anos |
 Kawrakow
|
d046dcee08
Faster perplexity computation (#2786)
|
%!s(int64=2) %!d(string=hai) anos |
 Matt Pulver
|
c82742ac9c
llama : add llama_beam_search() (#2267)
|
%!s(int64=2) %!d(string=hai) anos |
|
Nigel Bosch
|
28b2c996ca
convert.py : Get rope scale from HuggingFace models (#2772)
|
%!s(int64=2) %!d(string=hai) anos |
 slaren
|
154725c543
llama-bench : add model sizes (#2771)
|
%!s(int64=2) %!d(string=hai) anos |
|
slaren
|
12e2e33a97
convert.py : export rope freq_base when converting CodeLlama from an HF model (#2773)
|
%!s(int64=2) %!d(string=hai) anos |
 Jhen-Jie Hong
|
29674ab4e8
server : display token probabilities in the UI (#2489)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
5439a0ab57
ci : pip install gguf in editable mode (#2782)
|
%!s(int64=2) %!d(string=hai) anos |
 M. Yusuf Sarıgöz
|
8194cd8772
gguf : export objects to user code (#2780)
|
%!s(int64=2) %!d(string=hai) anos |
 Henri Vasserman
|
6bbc598a63
ROCm Port (#1087)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
3f460a2b72
cuda : add RoPE kernel for mode == 2 (NeoX) (#2760)
|
%!s(int64=2) %!d(string=hai) anos |
|
M. Yusuf Sarıgöz
|
87e3733f24
gguf : make gguf pip-installable
|
%!s(int64=2) %!d(string=hai) anos |
 Shouzheng Liu
|
b91ad7f461
ggml-alloc : enlarge size of parse_seq (#2776)
|
%!s(int64=2) %!d(string=hai) anos |
|
Marcus Dunn
|
2e5f70a25f
Added `enum` to `llama_token_get_type` return type (#2774)
|
%!s(int64=2) %!d(string=hai) anos |
|
slaren
|
d0f77b1353
convert.py : try to determine n_ctx automatically for CodeLlama (#2770)
|
%!s(int64=2) %!d(string=hai) anos |
|
slaren
|
0d3094f0c7
gguf : add rope_freq_base parameter for CodeLlama (#2769)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
01f2224682
falcon : write file type
|
%!s(int64=2) %!d(string=hai) anos |
|
Shouzheng Liu
|
38b16dfca6
metal : bug-fix when enable ggml-alloc (#2757)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
8f8c28e89c
convert : auto-determine model name based on dir + scripts update
|
%!s(int64=2) %!d(string=hai) anos |
 Kerfuffle
|
7694adda8d
Fix for main example getting stuck when -n -2 and --interactive (#2767)
|
%!s(int64=2) %!d(string=hai) anos |
|
slaren
|
fea95c682d
fix convert.py for codellama, add llama 34B to the list of recognized models (#2768)
|
%!s(int64=2) %!d(string=hai) anos |
 DannyDaemonic
|
ef955fbd23
Tag release with build number (#2732)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
d67777c202
metal : add Q8_0 support (#2763)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
c3e53b421a
llama : escape all U+2581 in a string (#2750)
|
%!s(int64=2) %!d(string=hai) anos |
 Evan Jones
|
6e91a1b070
llama : fix grammar sometimes generating null char (#2756)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
44d5462b5c
readme : fix link
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
c7868b0753
minor : fix trailing whitespace
|
%!s(int64=2) %!d(string=hai) anos |
