remove cache_examples from launch

removed cache_examples from launch, true by default on huggingface, see: https://gradio.app/docs/

inference/gradio/infer.py

@@ -60,7 +60,7 @@ class GradioInfer:
                              article=self.article,
                              examples=example_inputs,
                              enable_queue=True)
-        iface.launch(share=True,cache_examples=True)
+        iface.launch()
 
 
 if __name__ == '__main__':