cturan/llama.cpp

spogulis no https://github.com/cturan/llama.cpp

Autors	SHA1 Ziņojums	Datums
Daniel Bevenius	930f907d3e export-lora : use LLAMA_FILE_MAGIC_GGLA (#4894)	2 gadi atpakaļ
Georgi Gerganov	afefa319f1 ggml : change ggml_scale to take a float instead of tensor (#4573)	2 gadi atpakaļ
Georgi Gerganov	4760e7cc0b sync : ggml (backend v2) (#3912)	2 gadi atpakaļ
xaedes	0e76a8992c train : finetune LORA (#2632)	2 gadi atpakaļ