Skip to content

fix: add trust_remote_code=True to AutoTokenizer for embedqa model#1461

Merged
jperez999 merged 1 commit intoNVIDIA:mainfrom
jioffe502:fix/tokenizer-trust-remote-code
Mar 2, 2026
Merged

fix: add trust_remote_code=True to AutoTokenizer for embedqa model#1461
jperez999 merged 1 commit intoNVIDIA:mainfrom
jioffe502:fix/tokenizer-trust-remote-code

Conversation

@jioffe502
Copy link
Copy Markdown
Collaborator

Description

The AutoModel.from_pretrained call already passes trust_remote_code=True, but the AutoTokenizer.from_pretrained call was missing it. This causes an interactive [y/N] prompt that hangs non-interactive contexts (CI, batch jobs, production pipelines).

Checklist

  • I am familiar with the Contributing Guidelines.
  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.
  • If adjusting docker-compose.yaml environment variables have you ensured those are mimicked in the Helm values.yaml file.

The AutoModel.from_pretrained call already passes trust_remote_code=True,
but the AutoTokenizer.from_pretrained call was missing it. This causes an
interactive [y/N] prompt that hangs non-interactive contexts (CI, batch
jobs, production pipelines).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: Jacob Ioffe <jioffe@nvidia.com>
@jioffe502 jioffe502 requested a review from a team as a code owner March 2, 2026 18:07
@jioffe502 jioffe502 requested a review from edknv March 2, 2026 18:07
@jperez999 jperez999 merged commit 233505e into NVIDIA:main Mar 2, 2026
9 of 10 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants