Update handler.py

handler.py

@@ -14,7 +14,7 @@ class EndpointHandler():
             device_map="cuda:0",  # or "mps" if on Apple Silicon
             attn_implementation="flash_attention_2" if is_flash_attn_2_available() else None,
         ).eval()
-        self.processor = ColQwen2Processor.from_pretrained(path, max_num_visual_tokens=8192) # temporary
+        self.processor = ColQwen2Processor.from_pretrained(path) #, max_num_visual_tokens=8192) # temporary
         # self.model = torch.compile(self.model)
         print(f"Model and processor loaded {'with' if is_flash_attn_2_available() else 'without'} FA2")