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

Inference with AWQ quantized base model + compile enabled results in the <unk> tokens #426

Open
4 tasks
thincal opened this issue Apr 19, 2024 · 0 comments
Open
4 tasks

Inference with AWQ quantized base model + compile enabled results in the <unk> tokens #426

thincal opened this issue Apr 19, 2024 · 0 comments

Comments

@thincal
Copy link
Contributor

thincal commented Apr 19, 2024 •
edited

System Info

lorax: v0.9.0
awq: main branch
transformers: v4.39.3

Information

  • Docker
  • The CLI directly

Tasks

  • An officially supported command
  • My own modifications

Reproduction

  1. base model with awq quantized, startup lorax with --compile option
  2. inference without adapter, but result is: <unk><unk><unk><unk>...

But, it works fine if without --compile added.

Expected behavior

Normal reaction
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@thincal