Update app.py

app.py

@@ -48,16 +48,15 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
     
     input_ids = tokenizer.apply_chat_template(conversation, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)
     
-    streamer = TextIteratorStreamer(tokenizer, **{"skip_special_tokens": True, "skip_prompt": True, 'clean_up_tokenization_spaces':False,})
+    streamer = TextIteratorStreamer(tokenizer, timeout=60, skip_prompt=True, skip_special_tokens=True)
 
     generate_kwargs = dict(
         input_ids=input_ids, 
         streamer=streamer,
-        max_new_tokens=max_new_tokens, 
+        max_length=max_new_tokens, 
         do_sample=True, 
         temperature=temperature,
         repetition_penalty=1.2,
-        eos_token_id=model.config.eos_token_id,
     )
     
     thread = Thread(target=model.generate, kwargs=generate_kwargs)
@@ -65,7 +64,7 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
 
     buffer = ""
     for new_text in streamer:
-        buffer += new_text
+        buffer[-1][1] += new_text
         yield buffer