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/talk-llama/CMakeLists.txt

@@ -0,0 +1,10 @@
+if (WHISPER_SUPPORT_SDL2)
+    # talk-llama
+    set(TARGET talk-llama)
+
+    add_executable(${TARGET} talk-llama.cpp llama.cpp)
+
+    include(DefaultTargetOptions)
+
+    target_link_libraries(${TARGET} PRIVATE common common-sdl whisper ${SDL2_LIBRARIES} ${CMAKE_THREAD_LIBS_INIT})
+endif ()