Spaces:

oki602960
/

llama-cpp-python

Paused

Update Dockerfile

0dad949 verified 4 months ago

733 Bytes

FROM python:3.10-slim

# Install curl
RUN apt-get update && apt-get install -y \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Install PRE-COMPILED llama-cpp-python for CPU (Very Fast)
RUN pip install llama-cpp-python[server] --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
RUN pip install huggingface_hub

# Download Llama-3.2-3B-Instruct Q4_K_M model from bartowski
RUN huggingface-cli download bartowski/Llama-3.2-3B-Instruct-GGUF Llama-3.2-3B-Instruct-Q4_K_M.gguf --local-dir /app --local-dir-use-symlinks False

# Expose the API port
EXPOSE 7860

# Start the API server
CMD ["python3", "-m", "llama_cpp.server", "--model", "/app/Llama-3.2-3B-Instruct-Q4_K_M.gguf", "--host", "0.0.0.0", "--port", "7860"]

	FROM python:3.10-slim

	# Install curl
	RUN apt-get update && apt-get install -y \
	curl \
	&& rm -rf /var/lib/apt/lists/*

	# Install PRE-COMPILED llama-cpp-python for CPU (Very Fast)
	RUN pip install llama-cpp-python[server] --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
	RUN pip install huggingface_hub

	# Download Llama-3.2-3B-Instruct Q4_K_M model from bartowski
	RUN huggingface-cli download bartowski/Llama-3.2-3B-Instruct-GGUF Llama-3.2-3B-Instruct-Q4_K_M.gguf --local-dir /app --local-dir-use-symlinks False

	# Expose the API port
	EXPOSE 7860

	# Start the API server
	CMD ["python3", "-m", "llama_cpp.server", "--model", "/app/Llama-3.2-3B-Instruct-Q4_K_M.gguf", "--host", "0.0.0.0", "--port", "7860"]