Update app.py

app.py

@@ -1,3 +1,6 @@
+            alpaca_prompt.format(
+            "", # input
+                            "", outputs
 from unsloth import FastLanguageModel
 import torch
 import gradio as gr
@@ -27,10 +30,14 @@ if True:
 
 
 # Fungsi untuk menghasilkan respons
-def generate_response(prompt, max_length=4096):
+def generate_response(prompt, max_length=1024):
     inputs = tokenizer(
 [
-    prompt, # instruction  
+    alpaca_prompt.format(
+                prompt, # instruction  
+                "", # input
+                "" outputs
+    )
 ], return_tensors = "pt").to("cuda")
     outputs = model.generate(**inputs, max_length=max_length, pad_token_id=tokenizer.eos_token_id)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)