up dockerfile

.dockerignore

@@ -0,0 +1,21 @@
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env/
+venv/
+.env
+.venv
+pip-log.txt
+pip-delete-this-directory.txt
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.log
+.pytest_cache/
+.python-version 

Dockerfile

@@ -0,0 +1,33 @@
+# Use NVIDIA CUDA base image
+FROM nvidia/cuda:11.8.0-runtime-ubuntu22.04
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    python3 \
+    python3-pip \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first to leverage Docker cache
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip3 install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application
+COPY . .
+
+# Create model directory
+RUN mkdir -p /app/model/medical_llama_3b
+
+# Expose port
+EXPOSE 7860
+
+# Set environment variables
+ENV MODEL_PATH=/app/model/medical_llama_3b
+
+# Command to run the application
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"] 

requirements.txt

@@ -0,0 +1,9 @@
+fastapi==0.104.1
+uvicorn==0.24.0
+torch==2.1.0
+transformers==4.34.1
+datasets==2.14.5
+pydantic==2.4.2
+python-multipart==0.0.6
+huggingface-hub==0.17.3
+accelerate==0.24.1