Create Dockerfile

Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.10-slim
+
+# Install system dependencies needed to compile llama.cpp
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    python3-dev \
+    wget \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Optimize build configurations specifically for standard CPU execution
+ENV LLAMA_GGML_BACKEND=cpu
+RUN pip install --no-cache-dir "llama-cpp-python[server]"
+
+# Download the optimal Q4_K_M variant directly from the waddie repo
+RUN wget -O model.gguf "https://huggingface.co/waddie/mini-2.0-GGUF/resolve/main/mini-2.0-Q4_K_M.gguf"
+
+# Expose the default port for Hugging Face Spaces
+EXPOSE 7860
+
+# Run the API server with 2 context threads to play nice with the shared CPU limits
+CMD ["python3", "-m", "llama_cpp.server", \
+     "--model", "model.gguf", \
+     "--host", "0.0.0.0", \
+     "--port", "7860", \
+     "--n_threads", "2"]