Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 
 from transformers import AutoProcessor, LlavaForConditionalGeneration
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, TextIteratorStreamer
 
 from threading import Thread
 import re
@@ -38,6 +38,7 @@ def bot_streaming(message, history):
   if image is None:
       gr.Error("You need to upload an image for LLaVA to work.")
   prompt=f"<|start_header_id|>user<|end_header_id|>\n\n<image>\n{message['text']}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
+  print(f"prompt: {prompt}")
   image = Image.open(image).convert("RGB")
   inputs = processor(prompt, image, return_tensors="pt").to("cuda:0")
 
@@ -49,7 +50,7 @@ def bot_streaming(message, history):
   thread.start()
 
   text_prompt =f"<|start_header_id|>user<|end_header_id|>\n\n{message['text']}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"
-  
+  print(f"text_prompt: {text_prompt}")
 
   buffer = ""
   for new_text in streamer: