llama_any_server/README.md

llama.any server

This is a server for the llama.any protocol.

Clients

• llama.any: (CLI) https://gitlab.com/niansa/llama_any
• llama.nds: (GUI) https://gitlab.com/niansa/llama_nds

Building and use

1. Install a recent version of boost asio and CMake, as well as a recent C++ compiler
2. Obtain the gpt4all unfiltered llama model
3. Use CMake to configure and build the project
4. Enjoy!