Update app.py

app.py

@@ -36,13 +36,11 @@ def generate(prompt,history,max_new_tokens,seed):
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
     buf = ""
-    out_b=[]
     for response in stream:
         output += response.token.text
-        buf += response.token.text
-        if response.token.text == "\n" or response.token.text == "</s>" or response.token.text == ". ":
-            yield [(prompt,output)], output
-            buf=""
+        #buf += response.token.text
+        #if response.token.text == "\n" or response.token.text == "</s>" or response.token.text == ". ":
+        yield [(prompt,output)], output
     
 def tts(inp,voice,length,noise,width,sen_pause):
     yield from pp.stream_tts(inp,voice,length,noise,width,sen_pause)