owlninjam commited on
Commit
145da04
·
verified ·
1 Parent(s): f460721

Create Dockerfile

Browse files
Files changed (1) hide show
  1. Dockerfile +34 -0
Dockerfile ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:3.10-slim
2
+
3
+ WORKDIR /app
4
+
5
+ # Install system dependencies
6
+ RUN apt-get update && apt-get install -y \
7
+ wget \
8
+ curl \
9
+ && rm -rf /var/lib/apt/lists/*
10
+
11
+ # Install llama-cpp-python with prebuilt CPU wheel
12
+ RUN pip install --no-cache-dir \
13
+ --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu \
14
+ llama-cpp-python==0.2.24
15
+
16
+ # Copy and install remaining Python dependencies
17
+ COPY requirements.txt .
18
+ RUN pip install --no-cache-dir --upgrade pip && \
19
+ pip install --no-cache-dir -r requirements.txt
20
+
21
+ # Download the Zephyr Quiklang model (Q4_K_M)
22
+ RUN wget --progress=bar:force:noscroll -O zephyr-quiklang-3b-4k.Q4_K_M.gguf \
23
+ https://huggingface.co/TheBloke/zephyr-quiklang-3b-4K-GGUF/resolve/main/zephyr-quiklang-3b-4k.Q4_K_M.gguf
24
+
25
+ # Copy app files
26
+ COPY api.py .
27
+ COPY app.py .
28
+
29
+ EXPOSE 7860
30
+
31
+ HEALTHCHECK --interval=30s --timeout=30s --start-period=300s --retries=3 \
32
+ CMD curl --fail http://localhost:7860/_stcore/health || exit 1
33
+
34
+ CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0", "--server.headless=true"]