Create modeling_audio_only_thinker.py

modeling_audio_only_thinker.py

@@ -0,0 +1,11 @@
+from transformers import Qwen2_5OmniThinkerForConditionalGeneration
+
+class AudioOnlyThinker(Qwen2_5OmniThinkerForConditionalGeneration):
+    def __init__(self, config):
+        super().__init__(config)
+        self.visual = None
+        if hasattr(self.config, "vision_config"):
+            del self.config.vision_config
+
+    def forward(self, *args, pixel_values=None, pixel_values_videos=None, **kwargs):
+        return super().forward(*args, pixel_values=None, pixel_values_videos=None, **kwargs)