Update Dockerfile

Dockerfile

@@ -74,7 +74,7 @@ COPY groups_merged.txt llama.cpp/.
 WORKDIR ${APPDIR}/llama.cpp
 RUN git pull
 RUN python -m pip install -r requirements.txt
-RUN GGML_CUDA=1 make -j llama-quantize
+RUN GGML_CUDA=1 LLAMA_CUDA=1 make -j llama-quantize
     
 ENV PYTHONUNBUFFERED=1 \
     HF_HUB_ENABLE_HF_TRANSFER=1 \
@@ -92,6 +92,6 @@ ENV PYTHONUNBUFFERED=1 \
 
 WORKDIR ${APPDIR}
 # EXPOSE map[11434/tcp:{}]
-RUN ollama serve --verbose & sleep 5
+RUN ollama serve & sleep 5
 # RUN . .venv/bin/activate
-ENTRYPOINT python app.py --verbose
+ENTRYPOINT python app.py