From 53519977b80f12afc00e65e53276f8de539c6430 Mon Sep 17 00:00:00 2001 From: yuhan Date: Wed, 18 Jun 2025 11:25:50 +0800 Subject: [PATCH] modify gitee url and ci preview code --- docs/mindformers/docs/source_en/feature/parallel_training.md | 2 +- docs/mindformers/docs/source_zh_cn/feature/parallel_training.md | 2 +- tools/ci_pipeline_gate_APIView/generate_pr_html.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/mindformers/docs/source_en/feature/parallel_training.md b/docs/mindformers/docs/source_en/feature/parallel_training.md index f279c54adb..14d19251ed 100644 --- a/docs/mindformers/docs/source_en/feature/parallel_training.md +++ b/docs/mindformers/docs/source_en/feature/parallel_training.md @@ -157,7 +157,7 @@ For more information on configuring distributed parallel parameters, see the [Mi ## MindSpore Transformers Distributed Parallel Application Practices -In the [Llama3-70B fine-tuning configuration](https://gitee.com/kong_de_shu/mindformers/blob/dev/research/llama3/llama3_70b/finetune_llama3_70b.yaml#) file provided on the official website, multiple distributed parallelism strategies are used to improve the training efficiency in the multi-node multi-device environment. The main parallelism strategies and key parameters involved in the configuration file are as follows: +In the [Llama3-70B fine-tuning configuration](https://gitee.com/mindspore/mindformers/blob/dev/research/llama3/llama3_70b/finetune_llama3_70b.yaml#) file provided on the official website, multiple distributed parallelism strategies are used to improve the training efficiency in the multi-node multi-device environment. The main parallelism strategies and key parameters involved in the configuration file are as follows: - **Data parallelism**: No additional data parallelism is enabled (`data_parallel: 1`). - **Model parallelism**: A model is sliced into eight parts, which are computed on different devices (`model_parallel: 8`). diff --git a/docs/mindformers/docs/source_zh_cn/feature/parallel_training.md b/docs/mindformers/docs/source_zh_cn/feature/parallel_training.md index 96a9adcfdc..0b8f4fd29a 100644 --- a/docs/mindformers/docs/source_zh_cn/feature/parallel_training.md +++ b/docs/mindformers/docs/source_zh_cn/feature/parallel_training.md @@ -157,7 +157,7 @@ parallel_config: ## MindSpore Transformers 分布式并行应用实践 -在官网提供的[Llama3-70B微调配置](https://gitee.com/kong_de_shu/mindformers/blob/dev/research/llama3/llama3_70b/finetune_llama3_70b.yaml#)文件中，使用了多种分布式并行策略，以提升多机多卡环境中的训练效率。以下是该配置文件中涉及的主要并行策略和关键参数： +在官网提供的[Llama3-70B微调配置](https://gitee.com/mindspore/mindformers/blob/dev/research/llama3/llama3_70b/finetune_llama3_70b.yaml#)文件中，使用了多种分布式并行策略，以提升多机多卡环境中的训练效率。以下是该配置文件中涉及的主要并行策略和关键参数： - **数据并行**：未启用额外的数据并行（`data_parallel: 1`）。 - **模型并行**：模型被切分成8个部分，在不同设备上计算（`model_parallel: 8`）。 diff --git a/tools/ci_pipeline_gate_APIView/generate_pr_html.py b/tools/ci_pipeline_gate_APIView/generate_pr_html.py index e0bd934483..9c03e6fd0e 100644 --- a/tools/ci_pipeline_gate_APIView/generate_pr_html.py +++ b/tools/ci_pipeline_gate_APIView/generate_pr_html.py @@ -1258,7 +1258,7 @@ if __name__ == "__main__": # 修改权限 pythonlib_dir = os.path.dirname(os.path.dirname(sphinx.__file__)) chmod_path = os.path.join(pythonlib_dir, 'sphinx') - cmd_chmod = ['sudo', 'chmod', '-R', '+w', chmod_path] + cmd_chmod = ['sudo', 'chmod', '-R', '777', chmod_path] subprocess.run(cmd_chmod) # 屏蔽sphinx 在python>=3.9时额外依赖引入的版本过高问题 -- Gitee