Update app.py

app.py

@@ -37,9 +37,9 @@ from peft import PeftModel
 # Load tokenizer
 tokenizer = AutoTokenizer.from_pretrained(".")
 
-# Load base model normally (no 4-bit quantization)
+# Load base model (non-quantized)
 base_model = AutoModelForCausalLM.from_pretrained(
-    "unsloth/Meta-Llama-3.1-8B-bnb-4bit",  # same base you fine-tuned
+    "meta-llama/Meta-Llama-3-8B",  # use standard non-quantized base model
     device_map="auto"
 )