From 4215941c4134063a52543e87a8590109e9266b16 Mon Sep 17 00:00:00 2001
From: niujunhao <niujunhao@huawei.com>
Date: Mon, 14 Apr 2025 20:06:04 +0800
Subject: [PATCH] fix dataset is_dynamic doc

---
 docs/mindformers/docs/source_en/function/dataset.md    | 6 +++---
 docs/mindformers/docs/source_zh_cn/function/dataset.md | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/docs/mindformers/docs/source_en/function/dataset.md b/docs/mindformers/docs/source_en/function/dataset.md
index 8c057b218d..1fb0722f1d 100644
--- a/docs/mindformers/docs/source_en/function/dataset.md
+++ b/docs/mindformers/docs/source_en/function/dataset.md
@@ -379,7 +379,6 @@ train_dataset: &train_dataset
     shuffle: False
     split: "train"
     path: "llm-wizard/alpaca-gpt4-data"
-    is_dynamic: False
     packing: pack
     handler:
       - type: AlpacaInstructDataHandler
@@ -387,11 +386,12 @@ train_dataset: &train_dataset
         seq_length: 4096
         prompt_key: "conversations"
         output_columns: ["input_ids", "labels"]
+        is_dynamic: False
       - type: PackingHandler
         seq_length: 4096
         output_columns: ["input_ids", "labels", "actual_seq_len"]
     adaptor_config:
-       compress_mask: False
+      compress_mask: False
     column_names: *input_columns
 ```
 
@@ -437,13 +437,13 @@ When packing is configured, the dataset returns an `actual_seq_len` column. For
       shuffle: True
       split: "train"                       # Subset name of the online dataset
       path: "llm-wizard/alpaca-gpt4-data"  # Online dataset name
-      is_dynamic: True
       handler:
         - type: AlpacaInstructDataHandler
           tokenizer_name: llama2_7b
           seq_length: 4096
           prompt_key: "conversations"
           output_columns: *input_columns
+          is_dynamic: True
     seed: 0
     num_parallel_workers: 8
     python_multiprocessing: False
diff --git a/docs/mindformers/docs/source_zh_cn/function/dataset.md b/docs/mindformers/docs/source_zh_cn/function/dataset.md
index fca326a4e3..ddd7fbe3c1 100644
--- a/docs/mindformers/docs/source_zh_cn/function/dataset.md
+++ b/docs/mindformers/docs/source_zh_cn/function/dataset.md
@@ -379,7 +379,6 @@ train_dataset: &train_dataset
     shuffle: False
     split: "train"
     path: "llm-wizard/alpaca-gpt4-data"
-    is_dynamic: False
     packing: pack
     handler:
       - type: AlpacaInstructDataHandler
@@ -387,11 +386,12 @@ train_dataset: &train_dataset
         seq_length: 4096
         prompt_key: "conversations"
         output_columns: ["input_ids", "labels"]
+        is_dynamic: False
       - type: PackingHandler
         seq_length: 4096
         output_columns: ["input_ids", "labels", "actual_seq_len"]
     adaptor_config:
-       compress_mask: False
+      compress_mask: False
     column_names: *input_columns
 ```
 
@@ -437,13 +437,13 @@ train_dataset: &train_dataset
       shuffle: True
       split: "train"                       # 在线数据集子集名称
       path: "llm-wizard/alpaca-gpt4-data"  # 在线数据集名称
-      is_dynamic: True
       handler:
         - type: AlpacaInstructDataHandler
           tokenizer_name: llama2_7b
           seq_length: 4096
           prompt_key: "conversations"
           output_columns: *input_columns
+          is_dynamic: True
     seed: 0
     num_parallel_workers: 8
     python_multiprocessing: False
-- 
Gitee