Skip to content

Cap Seq Length for Some Models#4873

Open
AdnanElAssadi56 wants to merge 3 commits into
embeddings-benchmark:mainfrom
AdnanElAssadi56:fix/omni-encode-length
Open

Cap Seq Length for Some Models#4873
AdnanElAssadi56 wants to merge 3 commits into
embeddings-benchmark:mainfrom
AdnanElAssadi56:fix/omni-encode-length

Conversation

@AdnanElAssadi56

Copy link
Copy Markdown
Contributor

I got oom for some models while evaluating MTEB(eng, v2) on an h100. I think these new caps match the authors' evals.

"text": {"truncation": True, "max_length": 512},
}
)
self.model.max_seq_length = 512

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think this is needed for new sentence transformers

Suggested change
self.model.max_seq_length = 512

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