Update app.py

app.py

@@ -4,8 +4,8 @@ import torch
 
 MODEL_NAME = "Qwen/Qwen2.5-0.5B-Instruct"
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
-model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float32)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, fast_tokenizer=True)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, deivce_map="auto", load_in_8bit=True, torch_dtype=torch.float32)
 
 def respond(
     message,
@@ -35,7 +35,7 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=512, value=64, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=512, value=128, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=1.5, value=0.3, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,