remove streamer

app.py

@@ -9,7 +9,6 @@ import spaces
 import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from transformers.generation.streamers import BaseStreamer
 
 
 MAX_MAX_NEW_TOKENS = 2048
@@ -133,7 +132,6 @@ def generate(
         top_k=top_k,
         temperature=temperature,
         repetition_penalty=repetition_penalty,
-        streamer=streamer,
         output_hidden_states=True,
         return_dict_in_generate=True,
     )
@@ -237,4 +235,4 @@ with gr.Blocks(title="Llama-2 7B Chat with Dual Probes", css="footer {visibility
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()