cturan/llama.cpp

miroir de https://github.com/cturan/llama.cpp

Auteur	SHA1 Message	Date
Marcus Dunn	5be6c803fa llama : remove token functions with `context` args in favor of `model` (#3720)	il y a 2 ans
Herman Semenov	f439e506e8 ggml : fix rope + llama minor optimizations (#3560)	il y a 2 ans
staviq	1a159553f9 tokenizer : special token handling (#3538)	il y a 2 ans
slaren	16bc66d947 llama.cpp : split llama_context_params into model and context params (#3301)	il y a 2 ans
xaedes	0e76a8992c train : finetune LORA (#2632)	il y a 2 ans