This is the v1.0 release of LlamaChat, which allows you to run LLaMA-compatible model files in a native macOS chat-style app.

LlamaChat currently supports models from:

• The original LLaMA project: https://github.com/facebookresearch/llama
• Stanford's Alpaca: https://github.com/tatsu-lab/stanford_alpaca
• NomicAI's GPT4All: https://github.com/nomic-ai/gpt4all

LlamaChat supports models in both the raw PyTorch checkpoint format (.pth) as well as the .ggml format, since LlamaChat is powered by the ggml and llama.cpp and llama.swift libraries.

Features

• Import .pth and .ggml models with support for pre-converting .pth files directly within the app. Note that some manual intervention may be necessary in the case of outdated .ggml model files; please see the llama.cpp repository for more.
• Chat with LLaMA-compatible models in a native macOS chat-style interface. Messages are stored between sessions.
• Support for fun Llama and Alpaca avatars to make the chat experience more fun ✌️
• Inspect and debug model context including raw tokens.
• Clear model context and chat history on demand.