forked from datawhalechina/llm-cookbook
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request datawhalechina#103 from 0-yy-0/August
添加<Evaluating and Debugging Generative Al> 课程 1,6,7章内容
- Loading branch information
Showing
8 changed files
with
51 additions
and
0 deletions.
There are no files selected for viewing
37 changes: 37 additions & 0 deletions
37
content/Evaluating and Debugging Generative AI/1.简介 Introduction.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,37 @@ | ||
# 评估和调试生成式 AI | ||
|
||
## 简介 | ||
|
||
欢迎来到课程《评估和调试生成式 AI》👏🏻👏🏻 | ||
|
||
本课程由 Carey Phelps (Weights & Biases 首席产品经理) 与 Deeplearning.ai 合作开发,本课程旨在提供一套系统化的方法和工具,帮助您有效地跟踪和调试生成式 AI 模型。 | ||
|
||
在构建机器学习系统的过程中,管理和跟踪所有的数据、模型和超参数可能会变得复杂。随着团队规模的增大,这种复杂性可能会进一步加剧。生成式 AI 模型相比于监督学习模型增加了一层复杂性,因为它们的输出是复杂的,所以它们可能更难评估。 | ||
|
||
本课程将使用 Weights & Biases 的工具,这是一套易用且灵活的工具集,已经成为机器学习实验跟踪的行业标准。本课程涵盖用于文本生成的大型语言模型和用于图像生成的扩散模型。 | ||
|
||
|
||
## 课程内容 | ||
|
||
在本课程中,我们将专注于以下内容: | ||
|
||
1. 如何跟踪和可视化实验 | ||
2. 如何监控扩散模型 | ||
3. 如何评估和微调大型语言模型(LLMs) | ||
|
||
您将学习到一系列的调试和评估工具,包括: | ||
|
||
- Experiments:用于跟踪机器学习实验 | ||
- Artifacts:用于版本控制和存储数据集和模型 | ||
- Tables:用于可视化和检查模型做出的预测 | ||
- Reports:用于协作和分享实验结果 | ||
- Model Registry:用于管理模型的生命周期 | ||
- Prompts:用于评估大型语言模型生成 | ||
|
||
这些工具可以与 Python、TensorFlow 或 PyTorch 等主流的框架和计算平台一起工作。 | ||
|
||
## 致谢 | ||
|
||
我们要特别感谢 Weights & Biases 的 Darek Kleczek 和 Thomas Capelle,以及 Deeplearning.ai 的 Geoff Ludwig 和 Tommy Nelson 对本课程的贡献。 | ||
|
||
在完成本课程后,您将理解评估和调试生成式 AI 的最佳实践,并且将掌握一套用于系统评估和调试生成式 AI 项目的工具。我们期待您的参与,希望您能从本课程中获益,从而推动您的机器学习项目取得更大的成功。 |
1 change: 1 addition & 0 deletions
1
content/Evaluating and Debugging Generative AI/6.微调语言模型 Finetuning a language model.ipynb
Large diffs are not rendered by default.
Oops, something went wrong.
13 changes: 13 additions & 0 deletions
13
content/Evaluating and Debugging Generative AI/7.总结 Conclusion.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,13 @@ | ||
第七章、吴恩达《评估和调试生成式 AI》总结篇 | ||
|
||
恭喜您成功地完成了这门专业的机器学习课程!这不仅标志着您在机器学习领域的知识和技能有了显著的提升,更意味着您已经掌握了以下几个关键技能: | ||
|
||
- **生成模型的迭代和优化**:您已经理解并掌握了如何迭代和优化生成模型的方法,这是机器学习领域的核心技能。 | ||
|
||
- **实验结果的追踪和分析**:您已经学会了如何追踪和分析实验结果,这将有助于您深入理解模型的性能和改进策略。 | ||
|
||
- **研究成果的分享**:您已经学会了如何有效地分享您的研究成果,这将促进您与他人的交流和学习。 | ||
|
||
这些工具和技能将使您的开发过程更加透明和可复制,从而提升您的工作效率。我们期待看到您利用这些新技能创造的成果! | ||
|
||
请记住,这是一门专业的机器学习课程,需要您的专注和耐心。在学习过程中,持续的实践和尝试是理解和掌握这些知识的关键。我们鼓励您在实践中发现问题,解决问题,这样才能真正提升您的技能和理解。 |
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.