276e5b7811
Unmap the file in llama_free
1 year ago
d68c5dc435
Make mmap_file static
1 year ago
64bde3ffd4
Fix ggml_init_params in quantize
1 year ago
c03ae8dca1
Add mmap support for model files
1 year ago
3bcc129ba8
cmake : properly invoke CTest ( #629 )
1 year ago
a4755cf288
Remove unused variable ( #607 )
...
* It seems some new warning were added recently that exposed this. I wrote the code that included this unused variable originally and it is indeed not needed.
1 year ago
1f0414feec
make : fix darwin f16c flags check ( #615 )
...
...there was no check. ported upstream from https://github.com/zanussbaum/gpt4all.cpp/pull/2 (I dont see any clean path for upstream patches)
1 year ago
77efdf5a50
ggml : fix NEON signs ( close #620 , #622 )
1 year ago
ed3c680bcd
Fix GGML_F32Cx8_STORE in AVX without F16C path ( #619 )
1 year ago
9cbc404ba6
ci : re-enable AVX512 testing (Windows-MSVC) ( #584 )
...
* CI: Re-enable AVX512 testing (Windows-MSVC)
Now with 100% less base64 encoding
* plain __cpuid is enough here
1 year ago
b51c717d5c
ggml : init time on first ggml_init() call
1 year ago
0ba76c1e73
llama : fix compile warnings when reading the vocab
1 year ago
cea1c85948
ggml : add ARM_NEON dequantize_row_q4_1()
1 year ago
f202ada131
ggml : add ARM_NEON quantize_row_q4_1()
1 year ago
3b44d30d9b
ggml : add ARM_NEON ggml_vec_dot_q4_1()
1 year ago
61cbfff5c9
rename convert_ggml_to_pth.py -> convert-ggml-to-pth.py ( #600 )
...
to match filenames of other converters
1 year ago
d9ad104440
Create chat-13B.bat ( #592 )
...
* Create chat-13B.bat
Same script than chat-13B.sh, but for windows users.
Tested and working on windows 10/11 v 22H2
* Apply suggestions from code review
---------
Co-authored-by: anzz1 <anzz1@live.com>
1 year ago
b467702b87
readme : fix typos
1 year ago
516d88e75c
readme : add GPT4All instructions ( close #588 )
1 year ago
53635c081c
py : add GPT4All conversion script
...
For now: copy-paste
Too much time for me to deduplicate the python code
1 year ago
41318d708e
llama : use the same threshold for OpenBLAS and ggml thread limiting ( #577 )
1 year ago
a6956b25a1
add example of re-act pattern ( #583 )
...
* add example of re-act pattern
* spelling...
* fixed whitespace in reverse prompt issue
1 year ago
83df5639eb
Fix GCC warning about binary literal ( #595 )
...
0b10101010 -> 0xAA /* 0b10101010 */
1 year ago
a5c42c4b13
Fix typo in llama.h ( #593 )
1 year ago
5a5f8b1501
Enable Fused-Multiply-Add (FMA) and F16C/CVT16 vector extensions on MSVC ( #375 )
...
* Enable Fused-Multiply-Add (FMA) instructions on MSVC
__FMA__ macro does not exist in MSVC
* Enable F16C/CVT16 vector extensions on MSVC
__F16C__ macro does not exist in MSVC, but is implied with AVX2/AVX512
* MSVC cvt intrinsics
* Add __SSE3__ macro for MSVC too because why not
even though it's not currently used for anything when AVX is defined
1 year ago
f1217055ea
CI: fix subdirectory path globbing ( #546 )
...
- Changes in subdirectories will now be detecter properly
- (Windows-MSVC) AVX512 tests temporarily disabled
1 year ago
7f4c5c6651
llama : fix linkage with mingw ( #551 )
...
* Revert 7e53955#542 )
Still needs to be fixed properly
* Fix linking on mingw32
1 year ago
2a98bc18ea
ggml : add AVX2 implementation of quantize_row_q4_1 ( #515 )
...
* Add AVX2 implementation of quantize_row_q4_1
* Actually use AVX2
* Make quantize_row_q4_1 static
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 year ago
d0aaff571c
py : add temporary script to convert old ggml files to newer version ( #539 )
...
Co-authored-by: Jakub Horak <jakub.horak@ibawizard.net>
1 year ago
d0330fd783
py : add capabiliy to convert from ggml back to torch or hf format for further consumption/training/finetuning ( #403 )
1 year ago
99c5b27654
ggml : refactor quantized processing functions ( #509 )
...
* Refactor quantized processing functions
* ggml : minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 year ago
692ce3164e
py : removed unused `model` variable and verified that the code functions correctly with `vocab_only` setting. Also confirmed that the code works as expected after running with reduced memory usage due to deletion of no-longer-needed variable. ( #547 )
1 year ago
96f9c0506f
ci : make ctest verbose, hopefully we see what is wrong with the sanitizer
1 year ago
d502bc7c9d
tests : free llama context at the end of the test
1 year ago
436e561931
all : be more strict about converting float to double ( #458 )
...
* Be more strict about converting float to double
* Test equivalence of round, SILU implementations
Test module is commented out in CMakeLists.txt because the tests may
take a long time, depending on how much the compiler optimizes.
* Fix softmax in perplexity.cpp
* all : prefer float over double where appropriate
* perplexity : add <cmath>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 year ago
20e1e84884
deploy : add a Package.swift for SwiftPM support ( #393 )
...
* Add a Package.swift for SwiftPM support
* Swap from exclusions to allowlist
1 year ago
c1f885067c
ggml : introduce structs for the q4 data blocks ( #356 )
...
* Introduce structs for the q4 data blocks
* ggml : rename quant struct variables + fix ARM_NEON
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
1 year ago
e0670260fb
gitignore : add "embedding"
1 year ago
28ba975aea
Check the existence of f16_model_path_base in quantize.py ( #574 )
...
Co-authored-by: Jincheng Miao <jincheng.miao@gmail.com>
1 year ago
a6bdc47cba
Fix usage of F16C intrinsics in AVX code ( #563 )
...
* Fix usage of F16C intrinsics in AVX code when F16C is not defined
1 year ago
7b8dbcb78b
main.cpp fixes, refactoring ( #571 )
...
- main: entering empty line passes back control without new input in interactive/instruct modes
- instruct mode: keep prompt fix
- instruct mode: duplicate instruct prompt fix
- refactor: move common console code from main->common
1 year ago
4b8efff0e3
Add embedding example to Makefile ( #540 )
1 year ago
7e5395575a
Fix missing ggml link in cmake for examples/* on w64-mingw32 ( #542 )
1 year ago
34c1072e49
ci: add debug build to sanitizer build matrix ( #527 )
1 year ago
939ad2d3a5
Fix undefined variables in debug build, remove unused variables ( #531 )
1 year ago
8c2ec5e21d
Add support for linux/arm64 platform during Docker Builds ( #514 )
...
* Add support for linux/arm64 platform
* Add platform to versioned builds
1 year ago
b391579db9
Update README and comments for standalone perplexity tool ( #525 )
1 year ago
7a87d31f4f
[main] fix infinite generation (-n == -1) ( #523 )
1 year ago
348d6926ee
Add logo to README.md
1 year ago
33e35b8fe8
Exit from interactive mode if input stream is bad ( #491 )
...
Allow exiting the interactive prompt also with CTRL-D on Unix and CTRL-Z
on Windows.
1 year ago
Slaren
Stephan Walter
Casey Primozic
david raistrick
Georgi Gerganov
anzz1
Pavol Rusnak
Thérence
Maël Kerbiriou
Tobias Lütke
thement
Tai Duc Nguyen
DooWoong Lee (David)
Jed Fox
dotpy314
RJ Adriaansen
Marco Matthies
Erik Scholz
Juan Calderon-Perez
Harald Fernengel