Update app.py

app.py

@@ -7,14 +7,19 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 import bitsandbytes as bnb
 
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
 model_name = "microsoft/phi-2"
 model = AutoModelForCausalLM.from_pretrained(
     model_name, 
-    load_in_8bit=True,  
-    device_map="auto"
+    torch_dtype=torch.float32  # Use full precision for CPU
 )
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
+device = "cpu"
+model.to(device)
+
 # Set device
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)