Update Dockerfile

Dockerfile

@@ -1,6 +1,6 @@
 FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04
-
 ENV DEBIAN_FRONTEND=noninteractive
+
 RUN apt-get update && \
     apt-get upgrade -y && \
     apt-get install -y --no-install-recommends ca-certificates \
@@ -30,9 +30,7 @@ RUN useradd -m -u 1000 ${USER}
 USER ${USER}
 ENV HOME=/home/${USER} \
     PATH=${HOME}/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:${PATH} 
-    
 WORKDIR ${HOME}/app
-
     
 RUN curl https://pyenv.run | bash
 ENV PATH=${HOME}/.pyenv/shims:${HOME}/.pyenv/bin:${PATH}
@@ -42,13 +40,13 @@ RUN pyenv install ${PYTHON_VERSION} && \
     pyenv rehash && \
     pip install --no-cache-dir -U pip setuptools wheel && \
     pip install "huggingface-hub" "hf-transfer" "gradio[oauth]>=4.28.0" "gradio_huggingfacehub_search==0.0.7" "APScheduler"
-
+    
 COPY --chown=1000 . ${HOME}/app
+
 RUN git clone https://github.com/ollama/ollama.git \
     git clone https://github.com/ggerganov/llama.cpp \
-    pip install -r llama.cpp/requirements.txt \
+    pip install -r llama.cpp/requirements.txt
 COPY groups_merged.txt ${HOME}/app/llama.cpp/.
-
     
 ENV PYTHONPATH=${HOME}/app \
     PYTHONUNBUFFERED=1 \
@@ -64,7 +62,6 @@ ENV PYTHONPATH=${HOME}/app \
     NVIDIA_DRIVER_CAPABILITIES=compute,utility \
     NVIDIA_VISIBLE_DEVICES=all \
     OLLAMA_HOST=0.0.0.0
-    
 
 # EXPOSE 11434
 ENTRYPOINT /bin/sh start.sh