update export SpinQuant checkpoint to align with the new format #5645
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Summary: Per our new aligned checkpoint format with SpinQuant: - Original weights: drop it from the checkpoint - Int4 or int8 weight: .weight - Scales: .scales, grouped by group size for attention linear layers, grouped by per channel for embedding and output layer. This PR updates the export flow to follow this new format. Differential Revision: D63402708
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5645
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 5573ac1 with merge base cd46721 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D63402708 |
mergennachin
approved these changes
Sep 25, 2024
|
This pull request has been merged in 52d5218. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
Per our new aligned checkpoint format with SpinQuant:
This PR updates the export flow to follow this new format.
Differential Revision: D63402708