2 unstable releases

0.2.0 Aug 18, 2024
0.1.0 Aug 17, 2024

#495 in Machine learning

MIT/Apache

7MB
136K SLoC

C++ 83K SLoC // 0.1% comments C 34K SLoC // 0.1% comments CUDA 7.5K SLoC // 0.0% comments Metal Shading Language 5K SLoC // 0.0% comments GLSL 3.5K SLoC // 0.0% comments Objective-C 2.5K SLoC // 0.0% comments Rust 319 SLoC // 0.1% comments Python 41 SLoC // 0.3% comments

localllm

qwen2 model lib by llama.cpp

set LLAMA_LIB="llama.lib ggml.lib common.lib dir"

llama.lib ggml.lib common.lib from https://github.com/hjiayz/build-llama.cpp

example model https://hf-mirror.com/Qwen/Qwen2-1.5B-Instruct-GGUF/blob/main/qwen2-1_5b-instruct-q2_k.gguf

Dependencies

~3.5–6.5MB
~112K SLoC