Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from peft import PeftModel, PeftConfig
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 import torch
 
 # Device configuration (prioritize GPU if available)
@@ -26,7 +26,8 @@ def greet(text):
     with torch.no_grad():  # Disable gradient calculation for inference
         batch = tokenizer(f'"{text}" ->:', return_tensors='pt')  # Move tensors to device
         with torch.cuda.amp.autocast():  # Enable mixed-precision if available
-            output_tokens = model.generate(**batch, max_new_tokens=15)
+            output_tokens = model.generate(**batch
+, max_new_tokens=15)
     return tokenizer.decode(output_tokens[0], skip_special_tokens=True)
 
 iface = gr.Interface(fn=greet, inputs="text", outputs="text", title="PEFT Model for Big Brain")