In a continuous endeavor to optimize user experience, we’re thrilled to announce that our app now seamlessly integrates with the llama.cpp API, starting from version 1.1.4.
By adopting the llama.cpp API, our goal is to offer our users an enhanced chat experience, tapping into the deep capabilities this tool provides.
Llama.cpp is a port of Llama in C/C++, which makes it possible to run Llama 2 locally using 4-bit integer quantization on Macs. However, Llama.cpp also has support for Linux/Windows.
Github Repo: https://github.com/ggerganov/llama.cpp
The API that YourChat depends: https://github.com/ggerganov/llama.cpp/tree/master/examples/server
August 17, 2023