Update app.py

app.py

@@ -7,14 +7,15 @@ tokenizer = AutoTokenizer.from_pretrained("Sigurdur/icechat")
 
 
 def streaming_respond(question, history):
-    input_ids = tokenizer.encode("### Question: " + question, return_tensors="pt")
+    input_ids = tokenizer.encode(f"### Question:\n{question}\n\n### Answer:\n", return_tensors="pt")
     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=250,
+        max_new_tokens=100,
+        temperature=0.7,
         num_beams=1,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)