Fix maximum seqlen for gptq quantization #1748
Merged
Conversation
This file contains 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
fxmarty
approved these changes
Mar 18, 2024
young-developer
pushed a commit
to young-developer/optimum
that referenced
this pull request
May 10, 2024
fix gptq calibration data
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Outdated suggestions cannot be applied.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.
What does this PR do
This PR set a maximum seqlen that we use to create our calibration dataset. For models like mistral, we have a seqlen of 32768 which results in issues when creating the calibration dataset. The dataset don't need to have data with a big seqlen too.
Fixes huggingface/transformers#29494