Update app.py

app.py

@@ -5,7 +5,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 from peft import PeftModel
 
 BASE_MODEL =  "unsloth/Llama-3.2-3B-Instruct"
-LORA_REPO = "./"
+LORA_REPO = "./3B/" # Change this to 1B to use smaller model
 device = "cpu"
 
 print('loading tokenizer')