add llama, remove

Dockerfile

@@ -10,14 +10,14 @@ RUN apt-get update && \
     pkg-config \
     curl cmake git
 
-RUN pip install -U pip setuptools wheel && \
-    CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" FORCE_CMAKE=1 pip install --verbose llama-cpp-python[server]
+# RUN pip install -U pip setuptools wheel && \
+#     CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" FORCE_CMAKE=1 pip install --verbose llama-cpp-python[server]
 
 
 RUN git clone https://github.com/ggerganov/llama.cpp.git llamacpp --depth 1 && \
     cd llamacpp && \
-    cmake -B build && \
-    cmake --build build --config Release main server && \
+    cmake -B build -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS && \
+    cmake --build build --config Release --target main server && \
     cp build/bin/* ~/
 
 # Download model