chore: updated CMAKE_ARGS, added --verbose for troubleshooting and updated model download link

Dockerfile

@@ -10,11 +10,11 @@ RUN apt-get update && \
     curl
 
 RUN pip install -U pip setuptools wheel && \
-    CMAKE_ARGS="-DLLAMA_OPENBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python[server]
+    CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" FORCE_CMAKE=1 pip install --verbose llama-cpp-python[server]
 
 # Download model
 RUN mkdir model && \
-    curl -L https://huggingface.co/TheBloke/orca_mini_v3_13B-GGML/resolve/main/orca_mini_v3_13b.ggmlv3.q5_K_S.bin -o model/ggmlv3-model.bin
+    curl -L https://huggingface.co/TheBloke/orca_mini_v3_13B-GGML/resolve/main/orca_mini_v3_13b.ggmlv3.q6_K.bin -o model/ggmlv3-model.bin
 
 COPY ./start_server.sh ./start_server.sh
 

README.md

@@ -8,3 +8,5 @@ pinned: false
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+https://limcheekin-test.hf.space/v1/