vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'ggerganov:master' into master

Browse source
This commit is contained in:
Michael Podvitskiy 2024-02-08 09:32:39 +01:00 • committed by GitHub
commit 0495811c9c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 9 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
CMakeLists.txt
View file

@ -850,7 +850,9 @@ endif()
set(ARCH_FLAGS "") set(ARCH_FLAGS "")
if ((${CMAKE_SYSTEM_PROCESSOR} MATCHES "arm") OR (${CMAKE_SYSTEM_PROCESSOR} MATCHES "aarch64") OR ("${CMAKE_GENERATOR_PLATFORM_LWR}" MATCHES "arm64")) if (CMAKE_OSX_ARCHITECTURES STREQUAL "arm64" OR CMAKE_GENERATOR_PLATFORM_LWR STREQUAL "arm64" OR
(NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_GENERATOR_PLATFORM_LWR AND
CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm.*|ARM64)$"))
message(STATUS "ARM detected") message(STATUS "ARM detected")
if (MSVC) if (MSVC)
add_compile_definitions(__ARM_NEON) add_compile_definitions(__ARM_NEON)
@ -876,7 +878,9 @@ if ((${CMAKE_SYSTEM_PROCESSOR} MATCHES "arm") OR (${CMAKE_SYSTEM_PROCESSOR} MATC
list(APPEND ARCH_FLAGS -mno-unaligned-access) list(APPEND ARCH_FLAGS -mno-unaligned-access)
endif() endif()
endif() endif()
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "^(x86_64|i686|AMD64)$" OR "${CMAKE_GENERATOR_PLATFORM_LWR}" MATCHES "^(x86_64|i686|amd64|x64)$" ) elseif (CMAKE_OSX_ARCHITECTURES STREQUAL "x86_64" OR CMAKE_GENERATOR_PLATFORM_LWR MATCHES "^(x86_64|i686|amd64|x64|win32)$" OR
(NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_GENERATOR_PLATFORM_LWR AND
CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|i686|AMD64)$"))
message(STATUS "x86 detected") message(STATUS "x86 detected")
if (MSVC) if (MSVC)
# instruction set detection for MSVC only # instruction set detection for MSVC only

3
README.md
View file

@ -150,6 +150,7 @@ Unless otherwise noted these projects are open-source with permissive licensing:
- [ollama/ollama](https://github.com/ollama/ollama) - [ollama/ollama](https://github.com/ollama/ollama)
- [oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui) (AGPL) - [oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui) (AGPL)
- [psugihara/FreeChat](https://github.com/psugihara/FreeChat) - [psugihara/FreeChat](https://github.com/psugihara/FreeChat)
- [cztomsik/ava](https://github.com/cztomsik/ava) (MIT)
- [ptsochantaris/emeltal](https://github.com/ptsochantaris/emeltal) - [ptsochantaris/emeltal](https://github.com/ptsochantaris/emeltal)
- [pythops/tenere](https://github.com/pythops/tenere) (AGPL) - [pythops/tenere](https://github.com/pythops/tenere) (AGPL)
- [semperai/amica](https://github.com/semperai/amica) - [semperai/amica](https://github.com/semperai/amica)
@ -679,7 +680,7 @@ python3 -m pip install -r requirements.txt
python3 convert.py models/mymodel/ python3 convert.py models/mymodel/
# [Optional] for models using BPE tokenizers # [Optional] for models using BPE tokenizers
python convert.py models/mymodel/ --vocabtype bpe python convert.py models/mymodel/ --vocab-type bpe
# quantize the model to 4-bits (using Q4_K_M method) # quantize the model to 4-bits (using Q4_K_M method)
./quantize ./models/mymodel/ggml-model-f16.gguf ./models/mymodel/ggml-model-Q4_K_M.gguf Q4_K_M ./quantize ./models/mymodel/ggml-model-f16.gguf ./models/mymodel/ggml-model-Q4_K_M.gguf Q4_K_M

2
tests/.gitignore vendored
View file

@ -1,3 +1,3 @@
* *
!*.* !*.*
test-c.o *.o