Skip to content

replaced call to _prepare_decoder_attention_mask() with _prepare_4d_causal_attention_mask()#545

Draft
poedator wants to merge 11 commits intobigscience-workshop:mainfrom
poedator:fix536
Draft

replaced call to _prepare_decoder_attention_mask() with _prepare_4d_causal_attention_mask()#545
poedator wants to merge 11 commits intobigscience-workshop:mainfrom
poedator:fix536

Conversation

@poedator
Copy link
Collaborator

@poedator poedator commented Nov 21, 2023

fixes issue #536
edited calls to mask methods consistently with huggingface/transformers#27086

@justheuristic
Copy link
Collaborator

justheuristic commented Nov 23, 2023

Hi!

Note: a day ago, we had suspicions that the issue is with the main branch and not this one. It appears not to be the case.

I can confirm that def test_input_ids, specifically, passes in the main branch but fails here. This is most likely a bug. I can look into this eventually, but if you have time, please look into this yourself first.

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

Comments