Update Dockerfile

Dockerfile

@@ -5,7 +5,8 @@ FROM python:3.10-slim
 ENV HF_HOME=/tmp \
     XDG_CACHE_HOME=/tmp \
     TRANSFORMERS_CACHE=/tmp \
-    PYTHONUNBUFFERED=1
+    PYTHONUNBUFFERED=1 \
+    PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:32
 
 # Install system dependencies
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -17,6 +18,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libblas-dev \
     liblapack-dev \
     gfortran \
+    wget \
  && apt-get clean \
  && rm -rf /var/lib/apt/lists/*
 
@@ -25,13 +27,28 @@ WORKDIR /app
 
 # Copy requirements first for better caching
 COPY requirements.txt .
+
+# Install dependencies with specific versions
 RUN pip install --no-cache-dir -r requirements.txt
 
+# Pre-download model to avoid timeout during startup
+RUN python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('Qwen/Qwen2.5-1.5B-Instruct', use_fast=True)"
+
 # Copy the application code
 COPY . .
 
+# Increase timeout for model loading
+ENV FLASK_RUN_PORT=7860 \
+    TRANSFORMERS_OFFLINE=0 \
+    HF_HUB_DISABLE_TELEMETRY=1 \
+    OMP_NUM_THREADS=4
+
 # Expose port (for local or HF Spaces)
 EXPOSE 7860
 
-# Start the Flask app
-CMD ["python", "app.py"]
+# Use a shell script to start with proper memory management
+RUN echo '#!/bin/bash\necho "Starting application with memory monitoring"\nexec python app.py' > /app/start.sh && \
+    chmod +x /app/start.sh
+
+# Start the Flask app with the script
+CMD ["/app/start.sh"]