Adam Treat 8c4b8f215f Fix gptj to have lower memory requirements for kv cache and add versioning to the internal state to smoothly handle such a fix in the future.		2023-05-08 17:23:02 -04:00
..
llama.cpp@03ceb39c1e	Update to the alibi version that Zach made.	2023-05-08 12:27:01 -04:00
CMakeLists.txt	Scaffolding for the mpt <-> ggml project.	2023-05-08 12:21:30 -04:00
gptj.cpp	Fix gptj to have lower memory requirements for kv cache and add versioning to the internal state to smoothly handle such a fix in the future.	2023-05-08 17:23:02 -04:00
gptj.h	Persistent state for gpt-j models too.	2023-05-05 10:00:17 -04:00
llamamodel.cpp	First attempt at providing a persistent chat list experience.	2023-05-04 15:31:41 -04:00
llamamodel.h	First attempt at providing a persistent chat list experience.	2023-05-04 15:31:41 -04:00
llmodel_c.cpp	feat: load model	2023-05-08 12:21:30 -04:00
llmodel_c.h	feat: load model	2023-05-08 12:21:30 -04:00
llmodel.h	include <cstdint> in llmodel.h	2023-05-04 20:36:19 -04:00
mpt.cpp	Match Helly's impl of kv cache.	2023-05-08 12:21:30 -04:00
mpt.h	Scaffolding for the mpt <-> ggml project.	2023-05-08 12:21:30 -04:00
utils.cpp	Move the backend code into own subdirectory and make it a shared library. Begin fleshing out the C api wrapper that bindings can use.	2023-04-26 08:22:38 -04:00
utils.h	Move the backend code into own subdirectory and make it a shared library. Begin fleshing out the C api wrapper that bindings can use.	2023-04-26 08:22:38 -04:00