Upload app.py

app.py

@@ -13,8 +13,9 @@ base_model_name = "microsoft/phi-2"
 peft_model_path = "./phi2-openassistant-lora-final"
 
 # Load the base model with 4-bit quantization
-bnb_config = BitsAndBytesConfig(load_in_4bit=True)  # Ensure compatibility
-base_model = AutoModelForCausalLM.from_pretrained(base_model_name, quantization_config=bnb_config, device_map={"": device})
+#bnb_config = BitsAndBytesConfig(load_in_4bit=True)  # Ensure compatibility
+#base_model = AutoModelForCausalLM.from_pretrained(base_model_name, quantization_config=bnb_config, device_map={"": device})
+base_model = AutoModelForCausalLM.from_pretrained(base_model_name, torch_dtype=torch.float32, device_map={"": device})
 
 # Load LoRA adapter
 model = PeftModel.from_pretrained(base_model, peft_model_path)
@@ -49,4 +50,5 @@ iface = gr.Interface(
 )
 
 # Launch Gradio app
-iface.launch()
+iface.launch()
+