Update app.py

app.py

@@ -2,7 +2,9 @@ import gradio as gr
 from unsloth import FastLanguageModel
 from peft import PeftModel
 import torch
-
+# Load model directly
+from transformers import AutoModel
+model = AutoModel.from_pretrained("Sumit404/Llama-3.2-3B-Instruct-bnb-4bit-finetuned", torch_dtype="auto")
 # Load the base model and tokenizer
 max_seq_length = 4096
 dtype = None