Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
-from peft import PeftModel, PeftConfig
+from peft import PeftModel
+, PeftConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
@@ -20,7 +21,7 @@ def greet(text):
     
     # Use torch.no_grad to disable gradient calculation
     with torch.no_grad():
-        output_tokens = model.generate(**batch, max_new_tokens=15)
+        output_tokens = model.generate(**batch, do_sample=True, max_new_tokens=15)
 
     return tokenizer.decode(output_tokens[0], skip_special_tokens=True)