Update app.py

app.py

@@ -3,7 +3,6 @@ from PIL import Image
 import gradio as gr
 import spaces
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-from huggingface_hub.inference._generated.types import TextGenerationStreamOutput, TextGenerationStreamOutputToken
 import os
 from threading import Thread
 
@@ -64,17 +63,11 @@ def stream_chat(message: str, history: list, temperature: float, max_length: int
     with torch.no_grad():
         thread = Thread(target=model.generate, kwargs=gen_kwargs)
         thread.start()
-        for next_text in streamer:
-            yield TextGenerationStreamOutput(
-                index=0,
-                token=TextGenerationStreamOutputToken(
-                    id=0,
-                    logprob=0,
-                    text=next_text,
-                    special=False,
-                )
-            )
-        
+        for new_token in streamer:
+            if new_token:
+                history[-1][1] += new_token
+            yield history
+