Skip to content

fix: assisted-generation code example #2 in zh #3000

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

Merged
merged 1 commit into from
Aug 6, 2025
Merged

fix: assisted-generation code example #2 in zh #3000

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
2 changes: 1 addition & 1 deletion zh/assisted-generation.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ forward_confirmation = model(generated).logits.argmax(-1)

# We exclude the opposing tips from each sequence: the forward pass returns
# the logits for the next token, so it is shifted by one position.
print(generated[:-1].tolist() == forward_confirmation[1:].tolist()) # True
print(generated[0, 1:].tolist() == forward_confirmation[0, :-1].tolist()) # True
```

这意味着你可以将模型前向传递用于不同的目的: 除了提供一些 token 来预测下一个标记外，你还可以将序列传递给模型并检查模型是否会生成相同的序列 (或部分相同序列)。
Expand Down