Update app.py

app.py

@@ -18,7 +18,7 @@ def analyze(image, prompt):
         ]},
     ]
     # Process the messages using apply_chat_template
-    inputs = processor.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
+    inputs = processor.apply_chat_template(messages, tokenize=True, return_dict=True, return_tensors="pt", add_generation_prompt=True).to(model.device, dtype=torch.bfloat16)
     output_ids = model.generate(**inputs, max_new_tokens=512)
     response = processor.batch_decode(output_ids, skip_special_tokens=True)[0]
     model_reply = response.split(processor.tokenizer.eos_token)[0].split("model\n")[-1].strip()