llama.cpp.git - llama.cpp

Age	Commit message (Expand)	Author
2023-03-24	Support calling mlock() on loaded model data on Linux and macOS (#453)	comex
2023-03-24	Add embedding mode with arg flag. Currently working (#282)	Luciano
2023-03-22	Don't force immediate interactive without `-i` (#354)	tjohnman
2023-03-22	Introduce C-style API (#370)	Georgi Gerganov
2023-03-21	We could use std::unordered_map over std::map (#305)	Fabio R. Sluzala
2023-03-21	Compute perplexity over prompt (#270)	Gary Linscott
2023-03-21	cmdline option for custom amount of model parts (--n_parts N) (#348)	anzz1
2023-03-21	Change default repeat_penalty to 1.0	Georgi Gerganov
2023-03-21	Add tokenizer test + revert to C++11 (#355)	Georgi Gerganov
2023-03-20	move file magic/version to header, print expected version (#319)	Mack Straight
2023-03-20	sentencepiece bpe compatible tokenizer (#252)	Mack Straight
2023-03-19	Support for multiple reverse prompts. (#299)	tjohnman
2023-03-19	Make prompt randomization optional. (#300)	tjohnman
2023-03-19	Add --ignore-eos parameter (#181)	slaren
2023-03-19	Command line switch to use F16 for memory_k and memory_v (refactor of #154) (...	Erik Scholz
2023-03-19	Add "--instruct" argument for usage with Alpaca (#240)	Georgi Gerganov
2023-03-17	Default to 4 threads (#243)	Georgi Gerganov
2023-03-17	Don't tell users to use a bad number of threads (#243)	Stephan Walter
2023-03-15	added ctx_size parameter (#148)	Justin Suess
2023-03-12	Add interactive mode (#61)	Matvey Soloviev
2023-03-12	Add back top_k (#56)	beiller
2023-03-12	Add repetition penalty (#20)	beiller
2023-03-10	Fix a bug in the rope calculation	Georgi Gerganov
2023-03-10	Final touches	Georgi Gerganov
2023-03-10	Initial release	Georgi Gerganov