Update app.py

app.py

@@ -75,7 +75,7 @@ def respond(
     system_message,
     max_tokens,
     temperature,
-    top_p
+    top_p,
     ):
     
     messages = [{"role": "system", "content": system_message}]
@@ -88,37 +88,6 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-"""
-    input_ids = tokenizer.apply_chat_template(
-        messages,
-        add_generation_prompt=True,
-        return_tensors="pt"
-    ).to(model.device)
-
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-
-    generate_kwargs = dict(
-        input_ids= input_ids,
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        do_sample=True,
-        temperature=temperature,
-        eos_token_id=terminators,
-    )
-    # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
-    if temperature == 0:
-        generate_kwargs['do_sample'] = False
-        
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
-
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        #print(outputs)
-        yield "".join(outputs)
-"""
-
     response = ""
         
     for message in client.chat_completion(