talk-llama : add new example + sync ggml from llama.cpp (#664)

* talk-llama : talk with LLaMA AI

* talk.llama : disable EOS token

* talk-llama : add README instructions

* ggml : fix build in debug

examples/CMakeLists.txt

@@ -63,4 +63,5 @@ else()
     add_subdirectory(command)
     add_subdirectory(bench)
     add_subdirectory(talk)
+    add_subdirectory(talk-llama)
 endif()