llama.cpp

Author	SHA1	Message	Date
Jay Krell	9b80f683f9	Merge `c2201a9a83` into `7c9e54e55e`	2 years ago
beiller	129c7d1ea8	Add repetition penalty (#20 ) * Adding repeat penalization * Update utils.h * Update utils.cpp * Numeric fix Should probably still scale by temp even if penalized * Update comments, more proper application I see that numbers can go negative so a fix from a referenced commit * Minor formatting --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2 years ago
Jay Krell	636d56818a	Port to Visual C++. - Combined nmake/Unix Makefile. - _alloca instead of variable size array. - Cast void* to char* for math. - C++20 for designated initializers. It builds. I haven't run it yet.	2 years ago
Georgi Gerganov	7d9ed7b25f	Bump memory buffer	2 years ago
Georgi Gerganov	007a8f6f45	Support all LLaMA models + change Q4_0 quantization storage	2 years ago
Georgi Gerganov	70bc0b8b15	Fix a bug in the rope calculation	2 years ago
Georgi Gerganov	319cdb3e1f	Final touches	2 years ago
Georgi Gerganov	26c0846629	Initial release	2 years ago