Skip to content

fix microsoft/Phi-3-mini-4k-instruct crash in batch.slots[batch.slot_… #2148

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

Merged
merged 2 commits into from
Jul 1, 2024

Conversation

sywangyi
Copy link
Contributor

@sywangyi sywangyi commented Jul 1, 2024

sywangyi referenced this pull request Jul 1, 2024
* fix: refactor post_processor logic and add test

* fix: remove dev comment

* fix: adjust when post_processor is overridden and  improve create_post_processor
@Narsil
Copy link
Collaborator

Narsil commented Jul 1, 2024

We can't fix it that way (The initial goal was the fix Phi3 and DeepSeek).

Seems like we just need to override the processor because the one defined on the hub is wrong. https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/discussions/75/files

@Narsil Narsil merged commit 6ea570d into huggingface:main Jul 1, 2024
1 of 5 checks passed
@sywangyi sywangyi deleted the phi3 branch July 1, 2024 12:16
glegendre01 pushed a commit that referenced this pull request Jul 2, 2024
#2148)

* fix microsoft/Phi-3-mini-4k-instruct crash in batch.slots[batch.slot_indices]

Signed-off-by: Wang, Yi A <[email protected]>

* Apply suggestions from code review

---------

Signed-off-by: Wang, Yi A <[email protected]>
Co-authored-by: Nicolas Patry <[email protected]>
ErikKaum pushed a commit that referenced this pull request Jul 26, 2024
#2148)

* fix microsoft/Phi-3-mini-4k-instruct crash in batch.slots[batch.slot_indices]

Signed-off-by: Wang, Yi A <[email protected]>

* Apply suggestions from code review

---------

Signed-off-by: Wang, Yi A <[email protected]>
Co-authored-by: Nicolas Patry <[email protected]>
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.

2 participants