Update app.py

app.py

@@ -2,13 +2,16 @@
 import torch
 from peft import AutoPeftModelForCausalLM
 from transformers import  AutoModelForCausalLM, AutoTokenizer
+import gradio as gr
+import random
+import time
 
 model_id = "hikinegi/Llama-JAVA_tuned"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoPeftModelForCausalLM.from_pretrained(model_id, device_map='auto', torch_dtype=torch.float16)
 
 # Set the model to evaluation mode
-model.eval()
+#model.eval()
 
 def generate_pred(text):
     # Disable gradient calculation
@@ -22,9 +25,6 @@ def generate_pred(text):
                                  pad_token_id=tokenizer.eos_token_id)
         return (tokenizer.decode(outputs[0], skip_special_tokens=False))
 
-import gradio as gr
-import random
-import time
 
 with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
     gr.Markdown("""<h1><center>CodeGuru will answer all of your'e JAVA coding Question</center></h1> """)