Update app.py

app.py

@@ -5,7 +5,7 @@ from threading import Thread
 from typing import Iterator
 
 # Load model and tokenizer
-model_name = "Magpie-Align/MagpieLM-4B-Chat-v0.1"
+model_name = "Magpie-Align/MagpieLM-8B-Chat-v0.1"
 
 device = "cuda" # the device to load the model onto
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
@@ -65,7 +65,7 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are Magpie, a helpful AI assistant.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=2048, value=1024, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.6, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,