 Suaj Carrot
|
7392f1cd2c
Improved quantize script (#222)
|
%!s(int64=2) %!d(string=hai) anos |
 tjohnman
|
ad5fd5b60c
Make prompt randomization optional. (#300)
|
%!s(int64=2) %!d(string=hai) anos |
|
tjohnman
|
368d0c8a9e
Respect the maximum number of tokens in interactive. (#298)
|
%!s(int64=2) %!d(string=hai) anos |
 slaren
|
50fae10d03
Add --ignore-eos parameter (#181)
|
%!s(int64=2) %!d(string=hai) anos |
 Qingyou Meng
|
084e2f0ec0
interactive mode: print '\n' in sigint_handler, this flush stdout thus ensure color reset. (#283)
|
%!s(int64=2) %!d(string=hai) anos |
 Erik Scholz
|
0b366e7357
Command line switch to use F16 for memory_k and memory_v (refactor of #154) (#294)
|
%!s(int64=2) %!d(string=hai) anos |
 Georgi Gerganov
|
160bfb217d
Update hot topics to mention Alpaca support
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
c494ed5b94
Fix off-by-one bug (#115)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
c1c7026b47
Fix python stuff (#109)
|
%!s(int64=2) %!d(string=hai) anos |
 qunash
|
467b149761
Refactoring `convert-pth-to-ggml.py`: more concise and readable (#109)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
70f01cb863
Drop trailing new line from file prompts (#80)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
a4e63b73df
Add instruction for using Alpaca (#240)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
9e1707218a
Add "--instruct" argument for usage with Alpaca (#240)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
22213a17b5
Change RMSNorm eps to 1e-6 (#173)
|
%!s(int64=2) %!d(string=hai) anos |
 Ronsor
|
d7def1a752
Warn user if a context size greater than 2048 tokens is specified (#274)
|
%!s(int64=2) %!d(string=hai) anos |
 Pavol Rusnak
|
6f61c18ec9
Fix typo in readme
|
%!s(int64=2) %!d(string=hai) anos |
|
Pavol Rusnak
|
1e5a6d088d
Add note about Python 3.11 to readme
|
%!s(int64=2) %!d(string=hai) anos |
|
Pavol Rusnak
|
554b541521
Add memory/disk requirements to readme
|
%!s(int64=2) %!d(string=hai) anos |
 Alex Nguyen
|
d3f202d57b
Remove unused code since n_vocab is model.hparams.n_vocab (#262)
|
%!s(int64=2) %!d(string=hai) anos |
 Justin Suess
|
e03e359730
fixed warning with std::ignore about unused function result (#151)
|
%!s(int64=2) %!d(string=hai) anos |
 Gary Linscott
|
a81d0c2a17
Fix n^2 loop in tokenization (#254)
|
%!s(int64=2) %!d(string=hai) anos |
 anzz1
|
b2de7f18df
CI Improvements (#230)
|
%!s(int64=2) %!d(string=hai) anos |
 Niklas Korz
|
a292747893
Nix flake (#40)
|
%!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 |
|
Georgi Gerganov
|
4f54609110
Default to 4 threads (#243)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
e81b9c81c1
Update Contributing section
|
%!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 |
 mmyjona
|
6b0df5ccf3
add ptread link to fix cmake build under linux (#114)
|
%!s(int64=2) %!d(string=hai) anos |
 Bernat Vadell
|
2af23d3043
🚀 Dockerize llamacpp (#132)
|
%!s(int64=2) %!d(string=hai) anos |
 Matvey Soloviev
|
904d2a8d6a
Q4_1 quantization (#193)
|
%!s(int64=2) %!d(string=hai) anos |
