Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix: translation in moe.md #1742

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: translation in moe.md #1742

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions zh/moe.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -251,7 +251,7 @@ Switch Transformers 的作者观察到，在相同的预训练困惑度下，稀

<figure class="image text-center">
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/moe/08_superglue_dense_vs_sparse.png" alt="Table comparing fine-tuning batch size and learning rate between dense and sparse models.">
<figcaption>降低学习率和调大批量可以提升稀疏模型微调质量。该图来自 ST-MoE 论文</figcaption>
<figcaption>提高学习率和降低批量大小可以提升稀疏模型微调质量。该图来自 ST-MoE 论文</figcaption>
</figure>

此时，您可能会对人们微调 MoE 中遇到的这些挑战而感到沮丧，但最近的一篇论文 [《MoEs Meets Instruction Tuning》](https://arxiv.org/pdf/2305.14705.pdf) (2023 年 7 月) 带来了令人兴奋的发现。这篇论文进行了以下实验:
Expand Down Expand Up @@ -379,4 +379,4 @@ MoE 的 **量化** 也是一个有趣的研究领域。例如，[QMoE](https://a

```
Sanseviero, et al., "Mixture of Experts Explained", Hugging Face Blog, 2023.
```
```