This repository was archived by the owner on Jun 3, 2025. It is now read-only.
Fix onnx export for quantized MPT models 2 #1647
Merged
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
MPT models appear as HF models wrapped additionally for Composer library compatibility which results in `model.` prefix (instead of the classic `module.`) At the moment this causes errors during export of quantized models as some modules are missed during matching of names. This PR fixes it.
shubhra
approved these changes
Jul 13, 2023
ohaijen
approved these changes
Jul 14, 2023
rahul-tuli
added a commit
that referenced
this pull request
Jul 21, 2023
This reverts commit e8ff0f6.
rahul-tuli
added a commit
that referenced
this pull request
Jul 21, 2023
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
MPT models appear as HF models wrapped additionally for Composer library compatibility which results in
model.prefix (instead of the classicmodule.) At the moment this causes errors during export of quantized models as some modules are missed during matching of names. This PR fixes it.