Update main.py

main.py

@@ -40,7 +40,7 @@ def predict(image_url: str = Query(...), prompt: str = Query(...)):
         return_tensors="pt",
     ).to(model.device)
     with torch.no_grad():
-        generated_ids = model.generate(**inputs, max_new_tokens=512)
+        generated_ids = model.generate(**inputs, max_new_tokens=128)
     generated_ids_trimmed = [out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
     output_texts = processor.batch_decode(
         generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False