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.

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

Support rope scaling #1391

Merged
merged 24 commits into from
Jul 24, 2024
Merged

Conversation

milocress
Copy link
Contributor

@milocress milocress commented Jul 23, 2024

Adds support for llama3 Rope scaling.

@milocress milocress requested a review from a team as a code owner July 23, 2024 21:08
Copy link
Collaborator

@dakinggg dakinggg left a comment

Choose a reason for hiding this comment

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

Note: when transformers 4.43.2 is released tomorrow, we should bump the min version to that in this PR

llmfoundry/models/mpt/modeling_mpt.py Outdated Show resolved Hide resolved
llmfoundry/models/mpt/modeling_mpt.py Outdated Show resolved Hide resolved
llmfoundry/models/mpt/modeling_mpt.py Outdated Show resolved Hide resolved
llmfoundry/models/mpt/modeling_mpt.py Show resolved Hide resolved
tests/models/test_rope_scaling.py Show resolved Hide resolved
Copy link
Contributor

@snarayan21 snarayan21 left a comment

Choose a reason for hiding this comment

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

some comments

llmfoundry/models/mpt/modeling_mpt.py Outdated Show resolved Hide resolved
llmfoundry/models/mpt/modeling_mpt.py Outdated Show resolved Hide resolved
tests/models/test_rope_scaling.py Show resolved Hide resolved
@milocress milocress merged commit 70586c4 into mosaicml:main Jul 24, 2024
9 checks passed
@milocress milocress deleted the milo/support-llama3-rope branch July 24, 2024 18:07
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.

5 participants