Update Dockerfile to use app_v4 with background model loading

Dockerfile

@@ -1,5 +1,5 @@
 # OpenELM API Docker Configuration
-# Includes all dependencies including SentencePiece for tokenizer support
+# Version 4: Background model loading to prevent timeout
 
 FROM python:3.10-slim
 
@@ -10,7 +10,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     pkg-config \
     && rm -rf /var/lib/apt/lists/*
 
-# Install SentencePiece (required for LlamaTokenizer)
+# Install SentencePiece (required for tokenizer)
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libsentencepiece-dev \
     && rm -rf /var/lib/apt/lists/*
@@ -43,5 +43,5 @@ COPY --chown=user . /app
 # Expose the API port
 EXPOSE 8000 7860
 
-# Set default command with extended timeout for model loading
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000", "--timeout-keep-alive", "120"]
+# Set default command - NOW USING app_v4 which has background loading!
+CMD ["uvicorn", "app_v4:app", "--host", "0.0.0.0", "--port", "8000", "--timeout-keep-alive", "120", "--log-level", "info"]