The Wayback Machine - https://web.archive.org/web/20220322213140/https://github.com/deepset-ai/haystack/issues/2319
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.

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

Validate max_seq_length #2319

Open
ZanSara opened this issue Mar 16, 2022 · 0 comments
Open

Validate max_seq_length #2319

ZanSara opened this issue Mar 16, 2022 · 0 comments
Labels
good first issue journey:intermediate topic:models type:feature

Comments

@ZanSara
Copy link
Member

@ZanSara ZanSara commented Mar 16, 2022

Problem
Currently FARMReader will ask users to raise max_seq_length every time some samples are longer than the value set to it. However, this can be confusing if max_seq_length is already set to the maximum value allowed by the model, because raising it further will cause hard-to-read CUDA errors.

See #2177.

Solution
We should find a way to query the model for the maximum value max_seq_length can take and tweak the warning message accordingly. We could even use the value to validate max_seq_length.
@ZanSara ZanSara added type:feature topic:models journey:intermediate good first issue labels Mar 16, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
good first issue journey:intermediate topic:models type:feature
1 participant
@ZanSara