niansa/libjustlm
1
0
Fork 0
mirror of https://gitlab.com/niansa/libjustlm.git synced 2025-03-06 20:49:17 +01:00
Code Releases Activity
Super easy to use library for doing LLaMA/GPT-J stuff!
103 commits 1 branch 6 tags 544 KiB
C++ 87.3%
CMake 12.5%
C 0.2%
Find a file
niansa a0ec6f8a11 Fixed . being used instead of ${DIRECTORY} in llama.cpp.cmake
2023-05-17 19:01:08 +00:00
gptj Properly implemented MPT 2023-05-15 14:46:19 +02:00
include Minor MPT improvements 2023-05-16 23:35:42 +02:00
llama.cpp-alibi@03ceb39c1e Properly implemented MPT 2023-05-15 14:46:19 +02:00
llama.cpp-mainline@0e018fe008 Load implemenations as shared objects 2023-05-16 19:10:05 +00:00
mpt MPT works now! 2023-05-17 09:33:16 +02:00
.gitignore Initial commit 2023-03-30 07:03:33 -05:00
.gitmodules Load implemenations as shared objects 2023-05-16 19:10:05 +00:00
CMakeLists.txt Load implemenations as shared objects 2023-05-16 19:10:05 +00:00
dlhandle.hpp Load implemenations as shared objects 2023-05-16 19:10:05 +00:00
g4a-common.cpp Updated MPT implementation 2023-05-16 23:49:43 +02:00
g4a-common.hpp Updated MPT implementation 2023-05-16 23:49:43 +02:00
gptj.cpp Load implemenations as shared objects 2023-05-16 19:10:05 +00:00
justlm.cpp Load implemenations as shared objects 2023-05-16 19:10:05 +00:00
justlm_gptj.hpp Minor improvements on EOS handling 2023-05-17 10:51:20 +02:00
justlm_llama.hpp Minor improvements on EOS handling 2023-05-17 10:51:20 +02:00
justlm_mpt.hpp Minor improvements on EOS handling 2023-05-17 10:51:20 +02:00
justlm_pool.cpp Added missing co_await 2023-05-05 00:28:04 +02:00
LICENSE Add LICENSE 2023-04-28 16:08:19 +00:00
llama.cpp Load implemenations as shared objects 2023-05-16 19:10:05 +00:00
llama.cpp.cmake Fixed . being used instead of ${DIRECTORY} in llama.cpp.cmake 2023-05-17 19:01:08 +00:00
mpt.cpp Load implemenations as shared objects 2023-05-16 19:10:05 +00:00
pybind.cpp Load implemenations as shared objects 2023-05-16 19:10:05 +00:00
README.md MPT works now! 2023-05-17 09:33:16 +02:00

README.md

JustLM

Super easy to use library for doing LLaMA/GPT-J/MPT stuff!

Overview

This library implements an easy to use interface to LLaMa, GPT-J and MPT, with optional Python bindings.

Context scrolling is automatic and supports a top window bar.

Additionally, "pooling" is implemented to support keeping x inference instances in RAM and automatically moving least recently used ones to disk, ready for retrieval.

Documentation

Literally, just read the 2 header files in include/! The interface couldn't be simpler.

Credits

Thanks to Georgi Gerganov (ggerganov) for having written ggml and llama.cpp C libraries, which are both extremely important parts of this project! Also thanks to Nomic AI for having heavily helped me drive this project forward.