From d2bdff32692cac0a5ebdcad4ac4933c9d5f9d58a Mon Sep 17 00:00:00 2001 From: jingyaogong Date: Sat, 27 Dec 2025 10:56:07 +0800 Subject: [PATCH] [feat] test parquet --- dataset/lm_dataset.py | 1 + 1 file changed, 1 insertion(+) diff --git a/dataset/lm_dataset.py b/dataset/lm_dataset.py index dc81aec..e2def8f 100644 --- a/dataset/lm_dataset.py +++ b/dataset/lm_dataset.py @@ -76,6 +76,7 @@ class VLMDataset(Dataset): return X, Y, loss_mask, image_tensor +# 测试parquet数据读取和可视化 if __name__ == '__main__': import matplotlib.pyplot as plt; plt.rcParams['font.sans-serif'] = ['Arial Unicode MS', 'SimHei'] for path in ['pretrain_data.parquet', 'sft_data.parquet']: