Update app.py

app.py

@@ -23,9 +23,13 @@ def greet(image, prompt):
     
     
     # # model = PeftModel(base_model, "/folders").to(device)
-    inputs = processor(prompt, image, return_tensors="pt")
-    output = model.generate(**inputs, max_new_tokens=20)
-    return output
+    model_inputs = processor(text=prompt, images=image, return_tensors="pt")
+    input_len = model_inputs["input_ids"].shape[-1]
+    with torch.inference_mode():
+        generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
+        generation = generation[0][input_len:]
+        decoded = processor.decode(generation, skip_special_tokens=True)
+    return decoded
 
 demo = gr.Interface(fn=greet, inputs=[gr.Image(label="Upload image", sources=['upload', 'webcam'], type="pil"), gr.Text()], outputs="text")
 demo.launch(share=True)