Dockerfile

FROM ghcr.io/ggml-org/llama.cpp:server

WORKDIR /app

# 🌸 Downloading the 3B Genius!
RUN apt-get update && apt-get install -y wget && \
    wget https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf -O model.gguf

# 🧸 Setting 32K context so it's super snappy and fast!
CMD ["-m", "model.gguf", "--host", "0.0.0.0", "--port", "7860", "-c", "32768"]