Working tokenizer and model download fix

Fix handler startup

Dockerfile

@@ -10,16 +10,13 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install --upgrade pip && \
     python3 -m pip install --upgrade -r /requirements.txt
 
-# Add source files
-COPY src /src
-
 # Setup for Option 2: Building the Image with the Model included
 ARG MODEL_NAME=""
 ARG TOKENIZER_NAME=""
 ARG BASE_PATH="/runpod-volume"
 ARG QUANTIZATION=""
-ARG MODEL_REVISION="main"
-ARG TOKENIZER_REVISION="main"
+ARG MODEL_REVISION=""
+ARG TOKENIZER_REVISION=""
 
 ENV MODEL_NAME=$MODEL_NAME \
     MODEL_REVISION=$REVISION \
@@ -33,14 +30,19 @@ ENV MODEL_NAME=$MODEL_NAME \
     HF_TRANSFER=1 
 
 ENV PYTHONPATH="/:/vllm-installation"
-    
+
+COPY builder/download_model.py /download_model.py
 RUN --mount=type=secret,id=HF_TOKEN,required=false \
     if [ -f /run/secrets/HF_TOKEN ]; then \
         export HF_TOKEN=$(cat /run/secrets/HF_TOKEN); \
     fi && \
     if [ -n "$MODEL_NAME" ]; then \
-        python3 /src/download_model.py; \
+        python3 /download_model.py; \
     fi
 
+# Add source files
+COPY src /src
+
+
 # Start the handler
-CMD ["python3", "/src/handler.py"]
+CMD ["python3", "/src/handler.py"]