debug

app.py

@@ -769,7 +769,8 @@ def generate_chat_optimized(
     repetition_penalty=1.2,
     penalize_len_below=50,
     device=None,
-    batch_size=1  # Added parameter
+    batch_size=1,  # Added parameter
+    clean_the_text=True
 ):
     if device is None:
         device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -1033,8 +1034,7 @@ def generate_text(prompt, max_new_tokens, top_k, top_p, temperature, repetition_
         repetition_penalty=repetition_penalty,
         penalize_len_below=penalize_len_below,
         device=device,
-        batch_size=1,  # Added parameter
-        clean_the_text=True
+        batch_size=1
     )