Spaces:
Paused
Paused
Create Dockerfile
Browse files- Dockerfile +19 -0
Dockerfile
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM python:3.10-slim
|
| 2 |
+
|
| 3 |
+
# Install necessary packages
|
| 4 |
+
RUN apt-get update && apt-get install -y \
|
| 5 |
+
build-essential \
|
| 6 |
+
curl \
|
| 7 |
+
&& rm -rf /var/lib/apt/lists/*
|
| 8 |
+
|
| 9 |
+
# Install llama-cpp-python server and huggingface-cli
|
| 10 |
+
RUN pip install llama-cpp-python[server] huggingface_hub
|
| 11 |
+
|
| 12 |
+
# Download Llama-3.2-3B-Instruct Q4_K_M model from bartowski
|
| 13 |
+
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
|
| 14 |
+
|
| 15 |
+
# Expose the API port
|
| 16 |
+
EXPOSE 7860
|
| 17 |
+
|
| 18 |
+
# Start the API server
|
| 19 |
+
CMD ["python3", "-m", "llama_cpp.server", "--model", "/app/Llama-3.2-3B-Instruct-Q4_K_M.gguf", "--host", "0.0.0.0", "--port", "7860"]
|