Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 import json
+import torch
 
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
@@ -43,8 +44,9 @@ def respond(
     data.append({"input": messages, "output": response})
 
     # Write the data to a JSON file
-    with open('data.json', 'w') as f:
+    with open('./data.json', 'w') as f:
         json.dump(data, f)
+        print("Data successfully saved to data.json")
 
 
 # Add a title to the UI
@@ -59,14 +61,14 @@ pre_prompt = gr.Textbox(
     label="Pre-prompt",
     interactive=False,
     placeholder="Type here...",
+    visible=False,
 )
 
 demo = gr.ChatInterface(
     respond,
     title=title,
     description=description,
-    additional_inputs=[
-        pre_prompt,
+    additional_inputs=[pre_prompt,
         gr.Slider(minimum=256, maximum=8192, value=512, step=1, label="Max Gen tokens"),
         gr.Slider(minimum=0.3, maximum=2.5, value=0.8, step=0.1, label="Creativity"),
         gr.Slider(
@@ -81,5 +83,9 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
- 
+    # Check if CUDA GPU is installed
+    if torch.cuda.is_available():
+        print("CUDA GPU is installed. Running inference on GPU.")
+    else:
+        print("CUDA GPU is not installed. Running inference on CPU.")
+    demo.launch()