From b4359b3335776a583377ee70771f126b15108e95 Mon Sep 17 00:00:00 2001 From: gongjy <2474590974@qq.com> Date: Mon, 23 Sep 2024 20:11:19 +0800 Subject: [PATCH] fix data_process bug --- README.md | 2 ++ README_en.md | 2 ++ data_process.py | 2 +- 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index d4f871e..ffaa032 100644 --- a/README.md +++ b/README.md @@ -687,6 +687,8 @@ minimind模型本身没有使用较大的数据集训练,也没有针对回答     + +  ## 😊鸣谢 diff --git a/README_en.md b/README_en.md index 7c88224..e2e558a 100644 --- a/README_en.md +++ b/README_en.md @@ -756,6 +756,8 @@ your model with third-party UIs, such as fastgpt, OpenWebUI, etc.     + +  ## 😊Thanks for diff --git a/data_process.py b/data_process.py index 9c03628..047ff0e 100644 --- a/data_process.py +++ b/data_process.py @@ -95,7 +95,7 @@ def process_seq_monkey(chunk_size=50000): if doc_ids: arr = np.array(doc_ids, dtype=np.uint16) - with open(f'./dataset/clean_seq_monkey.bin', 'wb') as f: + with open(f'./dataset/clean_seq_monkey.bin', 'ab') as f: f.write(arr.tobytes())