Spaces:
Runtime error
Runtime error
Create Dockerfile
Browse files- Dockerfile +19 -0
Dockerfile
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
FROM nvidia/cuda:12.1.0-runtime-ubuntu20.04
|
2 |
+
|
3 |
+
# System packages
|
4 |
+
RUN apt-get update && apt-get install -y git python3 python3-pip && rm -rf /var/lib/apt/lists/*
|
5 |
+
|
6 |
+
# Python packages
|
7 |
+
RUN pip3 install vllm accelerate
|
8 |
+
|
9 |
+
# Download Mistral model from Hugging Face
|
10 |
+
RUN mkdir /app
|
11 |
+
WORKDIR /app
|
12 |
+
RUN git lfs install
|
13 |
+
RUN git clone https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 model
|
14 |
+
|
15 |
+
# Expose port for API
|
16 |
+
EXPOSE 8000
|
17 |
+
|
18 |
+
# Run vLLM API server
|
19 |
+
CMD ["python3", "-m", "vllm.entrypoints.openai.api_server", "--model", "/app/model"]
|