A chat interface based on llama.cpp for running Alpaca models. Entirely self-hosted, no API keys needed. Fits on 4GB of RAM and runs on the CPU.
- SvelteKit frontend
- MongoDB for storing chat history & parameters
- FastAPI + beanie for the API, wrapping calls to
llama.cpp
demo.webm
Currently only the 7B, 713B and 30B alpaca models are supported. If you have existing weights from another project you can add them to the serge_weights volume using docker cp.
llama will just crash if you don't have enough available memory for your model.
- 7B requires about 4.5GB of free RAM
- 13B requires about 12GB free
- 30B requires about 20GB free
Currently Serge requires a CPU compatible with AVX2 instructions. Try lscpu | grep avx2 in a shell, and if this returns nothing then your CPU is incompatible for now.
Feel free to join the discord if you need help with the setup: Discord
Serge is always open for contributions! If you catch a bug or have a feature idea, feel free to open an issue or a PR.
If you want to run Serge in development mode (with hot-module reloading for svelte & autoreload for FastAPI) you can do so like this:
git clone https://github.com/nsarrazin/serge.git
DOCKER_BUILDKIT=1 docker compose -f docker-compose.dev.yml up -d --build
You can test the production image with
DOCKER_BUILDKIT=1 docker compose up -d --build
- Front-end to interface with the API
- Pass model parameters when creating a chat
- Manager for model files
- Support for other models
- LangChain integration
- User profiles & authentication
And a lot more!