Update app.py

app.py

@@ -16,9 +16,8 @@ model = AutoModelForCausalLM.from_pretrained(
 
 def respond(message, history):
     messages = [{"role": "system", "content": "You are Spartacus, a helpful assistant."}]
-    for user_msg, bot_msg in history:
-        messages.append({"role": "user", "content": user_msg})
-        messages.append({"role": "assistant", "content": bot_msg})
+    for msg in history:
+        messages.append({"role": msg["role"], "content": msg["content"]})
     messages.append({"role": "user", "content": message})
 
     input_ids = tokenizer.apply_chat_template(
@@ -30,8 +29,7 @@ def respond(message, history):
     generate_kwargs = dict(
         input_ids=input_ids,
         streamer=streamer,
-        max_new_tokens=1024,
-        temperature=0.7,
+        temperature=0.5,
         top_p=0.9,
         do_sample=True,
     )