Marcus Dunn 5be6c803fa llama : remove token functions with `context` args in favor of `model` (#3720) 2 år sedan
..
CMakeLists.txt 70c29da118 common : fix mirostat state when using multiple sequences (#3543) 2 år sedan
common.cpp 5be6c803fa llama : remove token functions with `context` args in favor of `model` (#3720) 2 år sedan
common.h d1031cf49c sampling : refactor init to use llama_sampling_params (#3696) 2 år sedan
console.cpp 3aefaab9e5 check C++ code with -Wmissing-declarations (#3184) 2 år sedan
console.h 6381d4e110 gguf : new file format with flexible meta data (beta) (#2398) 2 år sedan
grammar-parser.cpp f439e506e8 ggml : fix rope + llama minor optimizations (#3560) 2 år sedan
grammar-parser.h 6381d4e110 gguf : new file format with flexible meta data (beta) (#2398) 2 år sedan
log.h 0e89203b51 speculative : add tree-based sampling example (#3624) 2 år sedan
sampling.cpp 5be6c803fa llama : remove token functions with `context` args in favor of `model` (#3720) 2 år sedan
sampling.h d1031cf49c sampling : refactor init to use llama_sampling_params (#3696) 2 år sedan
stb_image.h 370359e5ba examples: support LLaVA v1.5 (multimodal model) (#3436) 2 år sedan
train.cpp 5be6c803fa llama : remove token functions with `context` args in favor of `model` (#3720) 2 år sedan
train.h 0e76a8992c train : finetune LORA (#2632) 2 år sedan