model, mtmd: fix gguf conversion for audio/vision mmproj (#21309)

* fix gguf conversion for audio/vision mmproj

* fix test

gguf-py/gguf/gguf_writer.py

@@ -799,6 +799,7 @@ class GGUFWriter:
     def add_shared_kv_layers(self, value: int) -> None:
         self.add_uint32(Keys.Attention.SHARED_KV_LAYERS.format(arch=self.arch), value)
 
+    # if input is array, true means SWA and false means full_attention for each layer
     def add_sliding_window_pattern(self, value: int | Sequence[bool]) -> None:
         key = Keys.Attention.SLIDING_WINDOW_PATTERN.format(arch=self.arch)
         if isinstance(value, int):