Upload Dockerfile

Dockerfile

@@ -0,0 +1,68 @@
+# ════════════════════════════════════════════════════════════
+#  Qwen AI Chatbot — Docker Image for HuggingFace Spaces CPU
+#  Base: Python 3.11 slim | Port: 7860
+# ════════════════════════════════════════════════════════════
+
+FROM python:3.11-slim
+
+# System dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    git \
+    ffmpeg \
+    libsm6 \
+    libxext6 \
+    libgl1-mesa-glx \
+    build-essential \
+    curl \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create non-root user (required by HF Spaces)
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+WORKDIR /home/user/app
+
+# Install PyTorch CPU first (avoids downloading CUDA version)
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir \
+    torch==2.4.1+cpu \
+    torchvision==0.19.1+cpu \
+    torchaudio==2.4.1+cpu \
+    --extra-index-url https://download.pytorch.org/whl/cpu
+
+# Install other Python dependencies
+COPY --chown=user requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY --chown=user . .
+
+# Create necessary directories
+RUN mkdir -p uploads static
+
+# Pre-download the model during build (optional — comment out to download at runtime)
+# This adds ~2GB to image size but avoids cold-start download time
+# RUN python -c "from transformers import AutoModelForCausalLM, AutoTokenizer; \
+#     AutoTokenizer.from_pretrained('Qwen/Qwen3.5-0.8B', trust_remote_code=True); \
+#     AutoModelForCausalLM.from_pretrained('Qwen/Qwen3.5-0.8B', torch_dtype='float16', trust_remote_code=True)"
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1 \
+    TRANSFORMERS_CACHE=/home/user/.cache/huggingface \
+    HF_HOME=/home/user/.cache/huggingface \
+    TOKENIZERS_PARALLELISM=false \
+    OMP_NUM_THREADS=4 \
+    MKL_NUM_THREADS=4
+
+# Expose port (HF Spaces requires 7860)
+EXPOSE 7860
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=30s --start-period=120s --retries=3 \
+    CMD curl -f http://localhost:7860/api/info || exit 1
+
+# Launch server
+CMD ["python", "app.py"]