Update app.py

app.py

@@ -56,8 +56,10 @@ from peft import LoraConfig, get_peft_model
 # Load LLaMA 2 model in 4-bit mode to save memory
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
-    load_in_4bit=True,  # Use 4-bit quantization for efficiency
-    device_map="auto"
+    #load_in_4bit=True,  # Use 4-bit quantization for efficiency
+    #device_map="auto"
+    device_map="cpu",
+    quantization_config=None
 )
 
 # Apply LoRA (efficient fine-tuning)