Update app.py

app.py

@@ -36,7 +36,7 @@ if torch.cuda.is_available():
     )
     model_id = "meta-llama/Llama-2-7b-chat-hf"
     base_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto",quantization_config=bnb_config)
-    model = PeftModel.from_pretrained(model,"ranamhamoud/storytell")
+    model = PeftModel.from_pretrained(base_model,"ranamhamoud/storytell")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.pad_token = tokenizer.eos_token