feat: we successfully have the installer working for windows!

Models are downloaded at runtime instead of build.

patches/llama-cpp-sys-2/llama.cpp/cmake/llama.pc.in

@@ -0,0 +1,10 @@
+prefix=@CMAKE_INSTALL_PREFIX@
+exec_prefix=@CMAKE_INSTALL_PREFIX@
+libdir=@CMAKE_INSTALL_FULL_LIBDIR@
+includedir=@CMAKE_INSTALL_FULL_INCLUDEDIR@
+
+Name: llama
+Description: Port of Facebook's LLaMA model in C/C++
+Version: @LLAMA_INSTALL_VERSION@
+Libs: -L${libdir} -lggml -lggml-base -lllama
+Cflags: -I${includedir}