Upload 2 files

Dockerfile

@@ -0,0 +1,37 @@
+# Use official PyTorch image with CUDA 12.1 runtime
+FROM pytorch/pytorch:2.3.0-cuda12.1-cudnn8-runtime
+
+# Set working directory
+WORKDIR /app
+
+# Prevent Python from writing pyc files and buffering stdout/stderr
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    git \
+    && rm -rf /lib/apt/lists/*
+
+# Install python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application source code
+COPY gemma_code_llm/ ./gemma_code_llm/
+COPY static/ ./static/
+
+# Expose port
+EXPOSE 7860
+
+# Default environment variables
+ENV BASE_MODEL="google/gemma-3-1b-it"
+ENV ADAPTER_PATH="/app/outputs/gemma-code-lora"
+ENV QUANTIZATION="none"
+ENV DTYPE="auto"
+ENV TRUST_REMOTE_CODE="0"
+
+# Note: The adapter weights should be mounted at /app/outputs/gemma-code-lora or copied in.
+# Start FastAPI application
+CMD ["uvicorn", "gemma_code_llm.api:app", "--host", "0.0.0.0", "--port", "7860"]

requirements.txt

@@ -0,0 +1,10 @@
+torch>=2.3.0
+transformers>=4.51.0
+accelerate>=0.34.0
+peft>=0.12.0
+safetensors>=0.4.4
+fastapi>=0.115.0
+uvicorn[standard]>=0.30.0
+pydantic>=2.7.0
+bitsandbytes>=0.43.3
+