Dockerfile

FROM ubuntu:24.04
 
RUN apt-get update && apt-get install -y \
    python3 python3-pip \
    curl wget tar \
    && rm -rf /var/lib/apt/lists/*
 
WORKDIR /app
 
# ---- download precompiled llama.cpp ----
RUN wget -O llama.tar.gz https://github.com/ggml-org/llama.cpp/releases/download/b9310/llama-b9310-bin-ubuntu-x64.tar.gz && \
    mkdir llama && \
    tar -xzf llama.tar.gz -C llama --strip-components=1 && \
    rm llama.tar.gz
 
COPY requirements.txt .
RUN pip3 install --no-cache-dir --break-system-packages -r requirements.txt
 
# ---- bake model into image so container starts instantly ----
RUN python3 -c "\
from huggingface_hub import hf_hub_download; \
hf_hub_download(repo_id='LiquidAI/LFM2.5-350M-GGUF', filename='LFM2.5-350M-Q8_0.gguf')"
 
COPY . .
 
EXPOSE 7860
CMD ["python3", "app.py"]