 Gary Linscott
|
a81d0c2a17
Fix n^2 loop in tokenization (#254)
|
%!s(int64=2) %!d(string=hai) anos |
 thement
|
c9f670a177
Implement non-greedy tokenizer that tries to maximize token lengths (#242)
|
%!s(int64=2) %!d(string=hai) anos |
 Stephan Walter
|
367946c668
Don't tell users to use a bad number of threads (#243)
|
%!s(int64=2) %!d(string=hai) anos |
 Matvey Soloviev
|
904d2a8d6a
Q4_1 quantization (#193)
|
%!s(int64=2) %!d(string=hai) anos |
 Justin Suess
|
2d64715ad4
added ctx_size parameter (#148)
|
%!s(int64=2) %!d(string=hai) anos |
 Thomas Klausner
|
41be0a3b3d
Add NetBSD support. (#90)
|
%!s(int64=2) %!d(string=hai) anos |
|
Matvey Soloviev
|
96ea727f47
Add interactive mode (#61)
|
%!s(int64=2) %!d(string=hai) anos |
 Ben Garney
|
f385f8dee8
Allow using prompt files (#59)
|
%!s(int64=2) %!d(string=hai) anos |
 beiller
|
02f0c6fe7f
Add back top_k (#56)
|
%!s(int64=2) %!d(string=hai) anos |
 Sebastián A
|
eb062bb012
Windows fixes (#31)
|
%!s(int64=2) %!d(string=hai) anos |
|
beiller
|
129c7d1ea8
Add repetition penalty (#20)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
007a8f6f45
Support all LLaMA models + change Q4_0 quantization storage
|
%!s(int64=2) %!d(string=hai) anos |
 Jean-Michaël Celerier
|
9dcf4dba45
Add missing headers for memcpy and assert (#3)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
70bc0b8b15
Fix a bug in the rope calculation
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
319cdb3e1f
Final touches
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
26c0846629
Initial release
|
%!s(int64=2) %!d(string=hai) anos |
