Upload app.py

app.py

@@ -8,7 +8,8 @@ print(f"Using device: {device}")
 
 # Load the fine-tuned Phi-2 model in 4-bit quantization with CPU support
 
-model_name = "Monimoy/phi2-openassistant-lora-final"
+#model_name = "Monimoy/phi2-openassistant-lora-final"
+model_name = "microsoft/phi-2"
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32, device_map={"": device})
 
 # Load tokenizer