Update app.py

app.py

@@ -6,7 +6,7 @@ tokenizer = AutoTokenizer.from_pretrained("universitytehran/PersianMind-v1.0")
 model = AutoModelForCausalLM.from_pretrained(
     "universitytehran/PersianMind-v1.0",
     torch_dtype=torch.bfloat16  
-).to("cpu")  
+).to("cpu") 
 
 CONTEXT = (
     "This is a conversation with ParvizGPT. It is an artificial intelligence model designed by Amir Mahdi Parviz, "
@@ -19,7 +19,8 @@ pretokenized_context = tokenizer(CONTEXT, return_tensors="pt").input_ids.to("cpu
 
 def generate_response(message, chat_history):
 
-        prompt = torch.cat(
+    
+    prompt = torch.cat(
         [pretokenized_context, tokenizer("\nYou: " + message + "\nParvizGPT: ", return_tensors="pt").input_ids.to("cpu")],
         dim=1
     )
@@ -27,7 +28,7 @@ def generate_response(message, chat_history):
     with torch.no_grad():
         outputs = model.generate(
             prompt,
-            max_new_tokens=64,  
+            max_new_tokens=64, 
             do_sample=True,
             temperature=0.7,
             top_k=40,
@@ -35,7 +36,7 @@ def generate_response(message, chat_history):
         )
 
     result = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    response = result.split("ParvizGPT:")[-1].strip() 
+    response = result.split("ParvizGPT:")[-1].strip()  
     return chat_history + [(message, response)]