Update app.py

app.py

@@ -49,7 +49,6 @@ 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, timeout=60, skip_prompt=True, skip_special_tokens=True)
 
     generate_kwargs = dict(
         input_ids=input_ids, 
@@ -60,17 +59,9 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
         temperature=temperature,
         repetition_penalty=1.2,
     )
-'''
-    thread = Thread(target=model.generate, kwargs=generate_kwargs)
-    thread.start()
-
-    buffer = ""
-    for new_text in streamer:
-        buffer[-1][1] += new_text
-        yield buffer
-'''    
+
     with torch.no_grad():
-        outputs = model.generate(**inputs, **gen_kwargs)
+        outputs = model.generate(**generate_kwargs)
         outputs = outputs[:, inputs['input_ids'].shape[1]:]
         results = tokenizer.decode(outputs[0], skip_special_tokens=True)
         return results