re arranging ui

app.py

@@ -345,6 +345,8 @@ with gr.Blocks(analytics_enabled=False) as demo:
     gr.Markdown("### Device specific settings")
     with gr.Row():
         in_devices = gr.Dropdown(label="Device:", value=config.value["device"], choices=devices, filterable=True, multiselect=False, allow_custom_value=True, info="(you may add a custom device address at any time)")
+        in_cpu_offload = gr.Radio(label="CPU Offload:", value=config.value["cpu_offload"], choices=["True", "False"], info="This may increase performance, as it offloads computations from the GPU to the CPU. But this can also lead to slower executions and lower effectiveness. Compare running time and outputs before making sure, that this setting will help you")
+    with gr.Row():
         in_data_type = gr.Radio(label="Data Type:", value=config.value["data_type"], choices=["bfloat16", "float16", "float32"], info="`bfloat16` is not supported on MPS devices right now; `float16` may also not be supported on all devices, Half-precision weights, will save GPU memory, see https://huggingface.co/docs/diffusers/main/en/optimization/fp16")
         in_allow_tensorfloat32 = gr.Radio(label="Allow TensorFloat32:", value=config.value["allow_tensorfloat32"], choices=["True", "False"], info="is not supported on MPS devices right now; use TensorFloat-32 is faster, but results in slightly less accurate computations, see https://huggingface.co/docs/diffusers/main/en/optimization/fp16 ")
         in_variant = gr.Radio(label="Variant:", value=config.value["variant"], choices=["fp16", None], info="Use half-precision weights will save GPU memory, not all models support that, see https://huggingface.co/docs/diffusers/main/en/optimization/fp16 ")
@@ -356,10 +358,9 @@ with gr.Blocks(analytics_enabled=False) as demo:
     with gr.Row():
         with gr.Column(scale=1):
             in_trigger_token = gr.Textbox(value=config.value["trigger_token"], label="Trigger Token", info="will be added to your prompt to `activate` a fine tuned model")
-            in_use_safetensors = gr.Radio(label="Use safe tensors:", choices=["True", "False"], interactive=False)
             in_model_refiner = gr.Dropdown(value=config.value["refiner"], choices=['none'] + refiners, label="Refiner", allow_custom_value=True, multiselect=False)
         with gr.Column(scale=1):
-            in_cpu_offload = gr.Radio(label="CPU Offload:", value=config.value["cpu_offload"], choices=["True", "False"], info="This may increase performance, as it offloads computations from the GPU to the CPU. But this can also lead to slower executions and lower effectiveness. Compare running time and outputs before making sure, that this setting will help you")
+            in_use_safetensors = gr.Radio(label="Use safe tensors:", choices=["True", "False"], interactive=False)
             in_safety_checker = gr.Radio(label="Enable safety checker:", value=config.value["safety_checker"], choices=["True", "False"])
             in_requires_safety_checker = gr.Radio(label="Requires safety checker:", value=config.value["requires_safety_checker"], choices=["True", "False"])