Update app.py

app.py

@@ -3,6 +3,7 @@ from transformers import AutoModelForCausalLM, AutoProcessor, GenerationConfig
 from PIL import Image
 import torch
 import spaces
+import pprint
 
 # Load the processor and model
 processor = AutoProcessor.from_pretrained(
@@ -34,15 +35,16 @@ def process_image_and_text(image, text):
     # Generate output
     output = model.generate_from_batch(
         inputs,
-        GenerationConfig(max_new_tokens=200, stop_strings="<|endoftext|>"),
+        GenerationConfig(max_new_tokens=1024, stop_strings="<|endoftext|>"),
         tokenizer=processor.tokenizer
     )
 
     # Only get generated tokens; decode them to text
     generated_tokens = output[0, inputs['input_ids'].size(1):]
     generated_text = processor.tokenizer.decode(generated_tokens, skip_special_tokens=True)
+    pretty_text = pprint.pp(generated_text)
 
-    return generated_text
+    return pretty_text
 
 def chatbot(image, text, history):
     if image is None: