This repository was archived by the owner on Jun 3, 2025. It is now read-only.
Phased pruning #311
Merged
Phased pruning #311
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
markurtz
requested review from
bfineran,
mgoin and
rahul-tuli
and removed request for
a team
bfineran
approved these changes
Jun 27, 2021
Contributor
bfineran
left a comment
bfineran
left a comment
There was a problem hiding this comment.
really slick implementation. LGTM. Will we want to enable variable lengths for pruning/non-pruning phases in the future?
Member
Author
Good question, I could potentially see that happening. For now, though, I've only heard about equivalent phases from the research. Shouldn't be too much in the future to overload the phased param to support this if we need it |
markurtz
added a commit
that referenced
this pull request
Jun 29, 2021
* Update sparsifying_bert_using_recipes.md (#299) Fix wrong link to tutorial images * BERT pruning tutorial clean up (#300) * Disable save ckpt for BERT tutorial command (#301) * Add output for eval in tutorial (#302) * Rewrite readme for hugging face transformers integration (#303) * Rewrite readme for hugging face transformers integration * Update integrations/huggingface-transformers/README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update integrations/huggingface-transformers/README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update integrations/huggingface-transformers/README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update integrations/huggingface-transformers/README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update integrations/huggingface-transformers/README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update integrations/huggingface-transformers/README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update integrations/huggingface-transformers/README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * update from review Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Passage retrieval compression (#297) * adding IR elastic stuff * adding data download and modified es dense ranking * adding Doc2query * adding DPR code * updating doc2quyery code * adding msmarco eval scri[t * making dataset HF compatible * making dataset HF compatible * running doc2query t5 * model running * working on integrating * done with yaml recipe for all prunable layers * fixing config spacing for pruning yaml * work on dataset making * updaed thedownload data script and model training * running doc2query but missing the work for pruning * fixing issues in pruning * moving around DPR * added optimal lobotomizing project * adding to readme for baseline * new structures * cleaning up structure and pushing baseline numbers * moving sparse_ml_utils.py to src Co-authored-by: Mark Kurtz <mark@neuralmagic.com> * Update example commands for hugging face integration (#306) * fix: correct minor typo (#307) * Phased pruning (#311) * Update example commands for hugging face integration * Phased pruning implementation * Update for quality * Upgrade version to 0.5.1 for bug fix release Co-authored-by: Tuan Nguyen <tuan@neuralmagic.com> Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> Co-authored-by: spacemanidol <dcampos3@illinois.edu> Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
3 participants
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.
Implementation for allowing for phased pruning where the imposed sparsity alternates between the normal function for sparsity and no sparsity. Pruning starts on and alternates with the update_frequency. All weight pruning modifiers are supported with this. Note, if the sparsity ends up not being imposed at the final_epoch, it will be at the very end. Example: