Update app.py

app.py

@@ -24,7 +24,7 @@ model = AutoModelForCausalLM.from_pretrained(BASE_MODEL)
 
 # === トークナイズ関数修正版 ===
 def preprocess(examples):
-    texts = [en + " " + ja for en, ja in zip(examples["en"], examples["ja"])]
+    texts = [english + " " + japanese for english, japanese in zip(examples["english"], examples["japanese"])]
     tokenized = tokenizer(texts, max_length=256, truncation=True)
     tokenized["labels"] = tokenized["input_ids"].copy()
     return tokenized