Super easy to use library for doing LLaMA/GPT-J stuff!
Go to file
niansa 1a04a0e6d9 Updated llama.cpp-mainline 2023-12-25 16:55:30 +01:00
gptj Fixed compile errors because of previous commit 2023-05-31 20:22:18 +02:00
include Updated llama.cpp-mainline 2023-10-04 22:13:48 +02:00
llama.cpp-alibi@03ceb39c1e Properly implemented MPT 2023-05-15 14:46:19 +02:00
llama.cpp-mainline@b9f47952ff Updated llama.cpp-mainline 2023-12-25 16:55:30 +01:00
mpt Fixed compile errors because of previous commit 2023-05-31 20:22:18 +02:00
.gitignore Initial commit 2023-03-30 07:03:33 -05:00
.gitmodules Improved llama.cpp version naming scheme 2023-05-20 16:53:03 +02:00
CMakeLists.txt Check for correct magic value in llama 2023-08-31 17:57:56 +02:00
LICENSE Add LICENSE 2023-04-28 16:08:19 +00:00
README.md MPT works now! 2023-05-17 09:33:16 +02:00
dlhandle.hpp Minor improvemens in CMakeFiles and dlhandle 2023-05-18 22:32:06 +02:00
g4a_common.cpp Renamed llama-mainline to llama_old 2023-05-19 15:57:17 +02:00
g4a_common.hpp Renamed llama-mainline to llama_old 2023-05-19 15:57:17 +02:00
gptj.cpp Fixed file type detection 2023-05-19 17:45:32 +02:00
justlm.cpp Fixed file type detection 2023-05-19 17:45:32 +02:00
justlm_gptj.hpp Fixed exception if pre_tick is nullptr 2023-08-31 18:07:42 +02:00
justlm_llama.hpp Updated llama.cpp-mainline 2023-11-09 12:51:53 +01:00
justlm_mpt.hpp Fixed exception if pre_tick is nullptr 2023-08-31 18:07:42 +02:00
justlm_pool.cpp Added missing co_await 2023-05-05 00:28:04 +02:00
llama.cpp Check for correct magic value in llama 2023-08-31 17:57:56 +02:00
llama.cpp.cmake Updated llama.cpp-mainline 2023-11-09 12:51:53 +01:00
mpt.cpp Fixed file type detection 2023-05-19 17:45:32 +02:00
msvc_compat_unistd.h add msvc support -polyfill unistd 2023-05-31 19:56:40 +02:00
pybind.cpp Added python bindings for grammar 2023-09-05 09:27:45 +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.