Deploy Polyglot backend with quantized models

Dockerfile

@@ -28,12 +28,14 @@ COPY preload_models.py .
 ENV HF_HOME=/app/.cache
 ENV TRANSFORMERS_CACHE=/app/.cache
 ENV NLTK_DATA=/app/nltk_data
+ENV NUMBA_CACHE_DIR=/app/.cache/numba
 ENV PYTHONPATH=/app
 ENV PORT=7860
 
 # Create cache directories
 RUN mkdir -p $HF_HOME && chmod -R 777 $HF_HOME
 RUN mkdir -p $NLTK_DATA && chmod -R 777 $NLTK_DATA
+RUN mkdir -p $NUMBA_CACHE_DIR && chmod -R 777 $NUMBA_CACHE_DIR
 
 # Create data directories for learning service
 RUN mkdir -p /app/data/learning/users && chmod -R 777 /app/data