Update app.py

app.py

@@ -2,8 +2,10 @@ import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# Load model and tokenizer
+# Model name
 model_name = "MONAI/Llama3-VILA-M3-8B"
+
+# Load tokenizer and model with trust_remote_code=True
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -18,7 +20,7 @@ def generate_response(prompt):
         output = model.generate(**inputs, max_length=200)
     return tokenizer.decode(output[0], skip_special_tokens=True)
 
-# Create Gradio Interface
+# Gradio Interface
 iface = gr.Interface(
     fn=generate_response,
     inputs=gr.Textbox(lines=2, placeholder="Enter your prompt..."),
@@ -28,4 +30,3 @@ iface = gr.Interface(
 )
 
 iface.launch()
-