Create Dockerfile

Dockerfile

@@ -0,0 +1,29 @@
+# Use a lightweight base image with Python
+FROM python:3.10-slim
+
+# Install wget to download the model
+RUN apt-get update && apt-get install -y wget && rm -rf /var/lib/apt/lists/*
+
+# Set working directory
+WORKDIR /app
+
+# Install llama-cpp-python with pre-built CPU wheels
+RUN pip install --no-cache-dir \
+    "llama-cpp-python[server] @ https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.90/llama_cpp_python-0.2.90-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl"
+
+# Download the Qwen 2.5 Coder GGUF model
+RUN wget https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/resolve/main/qwen2.5-coder-7b-instruct-q4_k_m.gguf
+
+# Expose the port HF Spaces expects (7860)
+EXPOSE 7860
+
+# Run the server
+# --n_threads 2 (HF Free tier has 2 vCPUs)
+# --host 0.0.0.0 --port 7860 (Required for HF)
+CMD ["python3", "-m", "llama_cpp.server", \
+     "--model", "qwen2.5-coder-7b-instruct-q4_k_m.gguf", \
+     "--host", "0.0.0.0", \
+     "--port", "7860", \
+     "--n_threads", "2", \
+     "--n_gpu_layers", "0", \
+     "--n_ctx", "4096"]