Update app.py

app.py

@@ -1,6 +1,6 @@
 import os
 from dotenv import load_dotenv
-from datasets import load_dataset
+from datasets import load_dataset, concatenate_datasets
 from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingArguments
 from huggingface_hub import login
 
@@ -14,10 +14,12 @@ login(HF_TOKEN)
 # === 設定 ===
 BASE_MODEL = "Sakalti/template-4"
 HF_REPO = "Sakalti/template-16"
-
+HachiML/alpaca_jp_python
 # === データ読み込み ===
-dataset = load_dataset("Verah/JParaCrawl-Filtered-English-Japanese-Parallel-Corpus", split="train")
-
+dataset1 = load_dataset("Verah/JParaCrawl-Filtered-English-Japanese-Parallel-Corpus", split="train")
+dataset2 = load_dataset("HachiML/alpaca_jp_python", split="train")
+dataset3 = load_dataset("HachiML/alpaca_jp_math", split="train")
+dataset = concatenate_dataset([dataset1],[dataset2],[dataset3])
 # === トークナイザー & モデル準備 ===
 tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
 model = AutoModelForCausalLM.from_pretrained(BASE_MODEL)