Update Dockerfile

Dockerfile

@@ -1,4 +1,4 @@
-FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04
+FROM nvidia/cuda:12.4.1-cudnn-devel-ubuntu22.04
 ENV DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get update && \
@@ -31,7 +31,10 @@ USER ${USER}
 ENV HOME=/home/${USER} \
     PATH=${HOME}/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:${PATH} 
 WORKDIR ${HOME}/app
-    
+
+COPY --from=ollama/ollama:0.1.49-rc13 /go/src/github.com/ollama/ollama/ollama /bin/ollama
+
+ENV NVIDIA_VISIBLE_DEVICES=all
 RUN curl https://pyenv.run | bash
 ENV PATH=${HOME}/.pyenv/shims:${HOME}/.pyenv/bin:${PATH}
 ARG PYTHON_VERSION=3.10.13
@@ -39,11 +42,10 @@ RUN pyenv install ${PYTHON_VERSION} && \
     pyenv global ${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"
+    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
+ 
 RUN git clone https://github.com/ggerganov/llama.cpp
 RUN pip install -r llama.cpp/requirements.txt
 COPY groups_merged.txt ${HOME}/app/llama.cpp/.
@@ -63,6 +65,5 @@ ENV PYTHONPATH=${HOME}/app \
     NVIDIA_VISIBLE_DEVICES=all \
     OLLAMA_HOST=0.0.0.0
 
-# EXPOSE 11434
-ENTRYPOINT /bin/sh start.sh
-
+# EXPOSE map[11434/tcp:{}]
+ENTRYPOINT /bin/sh start.sh