Skip to content
This repository was archived by the owner on Jun 4, 2025. It is now read-only.

enable a QATWrapper for non-parameterized matmuls in BERT self attention #9

Merged
merged 1 commit into from
Aug 23, 2021
Merged

enable a QATWrapper for non-parameterized matmuls in BERT self attention #9

merged 1 commit into from
Aug 23, 2021

Conversation

bfineran
Copy link

updated quantized self attention block structure (through attention scores matmul):
Screen Shot 2021-08-16 at 1 52 26 PM

@bfineran bfineran self-assigned this Aug 16, 2021
spacemanidol
spacemanidol approved these changes Aug 23, 2021
View reviewed changes
Copy link

@spacemanidol spacemanidol left a comment

Choose a reason for hiding this comment

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

Looks good. One thing I wish we had was a way to add QATwrapper without having to update each model.

@natuan natuan merged commit d7878ea into master Aug 23, 2021
@natuan natuan deleted the bert-qat-matmul branch August 23, 2021 20:10
KSGulin pushed a commit that referenced this pull request Mar 9, 2022
@bfineran @KSGulin
enable a QATWrapper for non-parameterized matmuls in BERT self attent…
5553e7b 
…ion (#9)
KSGulin pushed a commit that referenced this pull request Mar 9, 2022
@bfineran @KSGulin
enable a QATWrapper for non-parameterized matmuls in BERT self attent…
910e257 
…ion (#9)
KSGulin pushed a commit that referenced this pull request Oct 14, 2022
@bfineran @KSGulin
Update trainer and model flows to accommodate sparseml
cfbffdb 
Disable FP16 on QAT start (#12)

* Override LRScheduler when using LRModifiers

* Disable FP16 on QAT start

* keep wrapped scaler object for training after disabling

Using QATMatMul in DistilBERT model class (#41)

Removed double quantization of output of context layer. (#45)

Fix DataParallel validation forward signatures (#47)

* Fix: DataParallel validation forward signatures

* Update: generalize forward_fn selection

Best model after epoch (#46)

fix sclaer check for non fp16 mode in trainer (#38)

Mobilebert QAT (#55)

* Remove duplicate quantization of vocabulary.

enable a QATWrapper for non-parameterized matmuls in BERT self attention (#9)
bfineran added a commit that referenced this pull request Oct 18, 2022
@KSGulin @bfineran
Upgrade to transformers release V4.23.1 (#62)
46f78c1 
* Update trainer and model flows to accommodate sparseml

Disable FP16 on QAT start (#12)

* Override LRScheduler when using LRModifiers

* Disable FP16 on QAT start

* keep wrapped scaler object for training after disabling

Using QATMatMul in DistilBERT model class (#41)

Removed double quantization of output of context layer. (#45)

Fix DataParallel validation forward signatures (#47)

* Fix: DataParallel validation forward signatures

* Update: generalize forward_fn selection

Best model after epoch (#46)

fix sclaer check for non fp16 mode in trainer (#38)

Mobilebert QAT (#55)

* Remove duplicate quantization of vocabulary.

enable a QATWrapper for non-parameterized matmuls in BERT self attention (#9)

* Utils and auxillary changes

update Zoo stub loading for SparseZoo 1.1 refactor (#54)

add flag to signal NM integration is active (#32)

Add recipe_name to file names

* Fix errors introduced in manual cherry-pick upgrade

Co-authored-by: Benjamin Fineran <[email protected]>
KSGulin added a commit that referenced this pull request Jun 19, 2023
@bfineran @KSGulin @dhuangnm
Update base to transformers v4.30.2 (#81)
0798c9e 
* Add recipe_name to default file names

* Upgrade to transformers release V4.30.2 (#62)

* Update trainer and model flows to accommodate sparseml

Disable FP16 on QAT start (#12)

* Override LRScheduler when using LRModifiers

* Disable FP16 on QAT start

* keep wrapped scaler object for training after disabling

Using QATMatMul in DistilBERT model class (#41)

Removed double quantization of output of context layer. (#45)

Fix DataParallel validation forward signatures (#47)

* Fix: DataParallel validation forward signatures

* Update: generalize forward_fn selection

Best model after epoch (#46)

fix sclaer check for non fp16 mode in trainer (#38)

Mobilebert QAT (#55)

* Remove duplicate quantization of vocabulary.

enable a QATWrapper for non-parameterized matmuls in BERT self attention (#9)

* Utils and auxillary changes

update Zoo stub loading for SparseZoo 1.1 refactor (#54)

add flag to signal NM integration is active (#32)

Add recipe_name to file names

* Fix errors introduced in manual cherry-pick upgrade

Co-authored-by: Benjamin Fineran <[email protected]>

* update build versions for NM fork pypi push (#74)

* fix nightly package name (#75)

* add make build command (#76)

* add GHA workflow files to build nightly and release packages (#77)

* add GHA workflow files to build nightly and release packages

* fix name

---------

Co-authored-by: dhuang <[email protected]>

* bump up version to 1.6.0 (#79)

Co-authored-by: dhuang <[email protected]>

---------

Co-authored-by: Konstantin <[email protected]>
Co-authored-by: Konstantin Gulin <[email protected]>
Co-authored-by: dhuangnm <[email protected]>
Co-authored-by: dhuang <[email protected]>
dsikka pushed a commit that referenced this pull request Aug 17, 2023
@bfineran @KSGulin
@dhuangnm @dsikka
Update base to transformers v4.30.2 (#81)
552565a 
* Add recipe_name to default file names

* Upgrade to transformers release V4.30.2 (#62)

* Update trainer and model flows to accommodate sparseml

Disable FP16 on QAT start (#12)

* Override LRScheduler when using LRModifiers

* Disable FP16 on QAT start

* keep wrapped scaler object for training after disabling

Using QATMatMul in DistilBERT model class (#41)

Removed double quantization of output of context layer. (#45)

Fix DataParallel validation forward signatures (#47)

* Fix: DataParallel validation forward signatures

* Update: generalize forward_fn selection

Best model after epoch (#46)

fix sclaer check for non fp16 mode in trainer (#38)

Mobilebert QAT (#55)

* Remove duplicate quantization of vocabulary.

enable a QATWrapper for non-parameterized matmuls in BERT self attention (#9)

* Utils and auxillary changes

update Zoo stub loading for SparseZoo 1.1 refactor (#54)

add flag to signal NM integration is active (#32)

Add recipe_name to file names

* Fix errors introduced in manual cherry-pick upgrade

Co-authored-by: Benjamin Fineran <[email protected]>

* update build versions for NM fork pypi push (#74)

* fix nightly package name (#75)

* add make build command (#76)

* add GHA workflow files to build nightly and release packages (#77)

* add GHA workflow files to build nightly and release packages

* fix name

---------

Co-authored-by: dhuang <[email protected]>

* bump up version to 1.6.0 (#79)

Co-authored-by: dhuang <[email protected]>

---------

Co-authored-by: Konstantin <[email protected]>
Co-authored-by: Konstantin Gulin <[email protected]>
Co-authored-by: dhuangnm <[email protected]>
Co-authored-by: dhuang <[email protected]>
dsikka pushed a commit that referenced this pull request Aug 17, 2023
@bfineran @KSGulin
@dhuangnm @dsikka
Update base to transformers v4.30.2 (#81)
1534ec1 
* Add recipe_name to default file names

* Upgrade to transformers release V4.30.2 (#62)

* Update trainer and model flows to accommodate sparseml

Disable FP16 on QAT start (#12)

* Override LRScheduler when using LRModifiers

* Disable FP16 on QAT start

* keep wrapped scaler object for training after disabling

Using QATMatMul in DistilBERT model class (#41)

Removed double quantization of output of context layer. (#45)

Fix DataParallel validation forward signatures (#47)

* Fix: DataParallel validation forward signatures

* Update: generalize forward_fn selection

Best model after epoch (#46)

fix sclaer check for non fp16 mode in trainer (#38)

Mobilebert QAT (#55)

* Remove duplicate quantization of vocabulary.

enable a QATWrapper for non-parameterized matmuls in BERT self attention (#9)

* Utils and auxillary changes

update Zoo stub loading for SparseZoo 1.1 refactor (#54)

add flag to signal NM integration is active (#32)

Add recipe_name to file names

* Fix errors introduced in manual cherry-pick upgrade

Co-authored-by: Benjamin Fineran <[email protected]>

* update build versions for NM fork pypi push (#74)

* fix nightly package name (#75)

* add make build command (#76)

* add GHA workflow files to build nightly and release packages (#77)

* add GHA workflow files to build nightly and release packages

* fix name

---------

Co-authored-by: dhuang <[email protected]>

* bump up version to 1.6.0 (#79)

Co-authored-by: dhuang <[email protected]>

---------

Co-authored-by: Konstantin <[email protected]>
Co-authored-by: Konstantin Gulin <[email protected]>
Co-authored-by: dhuangnm <[email protected]>
Co-authored-by: dhuang <[email protected]>
bfineran added a commit that referenced this pull request Oct 26, 2023
@bfineran @KSGulin @dhuangnm
Update base to transformers v4.30.2 (#81)
7c04f76 
* Add recipe_name to default file names

* Upgrade to transformers release V4.30.2 (#62)

* Update trainer and model flows to accommodate sparseml

Disable FP16 on QAT start (#12)

* Override LRScheduler when using LRModifiers

* Disable FP16 on QAT start

* keep wrapped scaler object for training after disabling

Using QATMatMul in DistilBERT model class (#41)

Removed double quantization of output of context layer. (#45)

Fix DataParallel validation forward signatures (#47)

* Fix: DataParallel validation forward signatures

* Update: generalize forward_fn selection

Best model after epoch (#46)

fix sclaer check for non fp16 mode in trainer (#38)

Mobilebert QAT (#55)

* Remove duplicate quantization of vocabulary.

enable a QATWrapper for non-parameterized matmuls in BERT self attention (#9)

* Utils and auxillary changes

update Zoo stub loading for SparseZoo 1.1 refactor (#54)

add flag to signal NM integration is active (#32)

Add recipe_name to file names

* Fix errors introduced in manual cherry-pick upgrade

Co-authored-by: Benjamin Fineran <[email protected]>

* update build versions for NM fork pypi push (#74)

* fix nightly package name (#75)

* add make build command (#76)

* add GHA workflow files to build nightly and release packages (#77)

* add GHA workflow files to build nightly and release packages

* fix name

---------

Co-authored-by: dhuang <[email protected]>

* bump up version to 1.6.0 (#79)

Co-authored-by: dhuang <[email protected]>

---------

Co-authored-by: Konstantin <[email protected]>
Co-authored-by: Konstantin Gulin <[email protected]>
Co-authored-by: dhuangnm <[email protected]>
Co-authored-by: dhuang <[email protected]>
bfineran added a commit that referenced this pull request Oct 27, 2023
@bfineran
Update base to transformers v4.34.1 (#95)
a62f034 
(previous commits)
* Add recipe_name to default file names

* Upgrade to transformers release V4.30.2 (#62)

* Update trainer and model flows to accommodate sparseml

Disable FP16 on QAT start (#12)

* Override LRScheduler when using LRModifiers

* Disable FP16 on QAT start

* keep wrapped scaler object for training after disabling

Using QATMatMul in DistilBERT model class (#41)

Removed double quantization of output of context layer. (#45)

Fix DataParallel validation forward signatures (#47)

* Fix: DataParallel validation forward signatures

* Update: generalize forward_fn selection

Best model after epoch (#46)

fix sclaer check for non fp16 mode in trainer (#38)

Mobilebert QAT (#55)

* Remove duplicate quantization of vocabulary.

enable a QATWrapper for non-parameterized matmuls in BERT self attention (#9)

* Utils and auxillary changes

update Zoo stub loading for SparseZoo 1.1 refactor (#54)

add flag to signal NM integration is active (#32)

Add recipe_name to file names

* Fix errors introduced in manual cherry-pick upgrade

Co-authored-by: Benjamin Fineran <[email protected]>

* update build versions for NM fork pypi push (#74)

* fix nightly package name (#75)

* add make build command (#76)

* add GHA workflow files to build nightly and release packages (#77)

* add GHA workflow files to build nightly and release packages

* fix name

---------

Co-authored-by: dhuang <[email protected]>

* bump up version to 1.6.0 (#79)

Co-authored-by: dhuang <[email protected]>

---------

Co-authored-by: Konstantin <[email protected]>
Co-authored-by: Konstantin Gulin <[email protected]>
Co-authored-by: dhuangnm <[email protected]>
Co-authored-by: dhuang <[email protected]>

minor improvements for build workflow files (#83)

Co-authored-by: dhuang <[email protected]>

fix minor issue (#84)

Co-authored-by: dhuang <[email protected]>

OPT with quantizable MatMuls (#85)

fix a minor issue for release build (#86)

Co-authored-by: dhuang <[email protected]>

update version in version.py

Testmo (#91)

* improve GHA workflow files to build nightly and release, and report status to testmo

* clean up

* report exit code

* Assign value to exit_code

---------

Co-authored-by: dhuang <[email protected]>

Update trainer.py - fix DistributedSampler import (#93)

DistributedSampler is used but not imported in `trainer.py`

Research/llama/bmm quantization (#94)

* Quantize attention matmuls

* Quantize attention matmuls

bump base transformers version
bfineran pushed a commit that referenced this pull request Jun 5, 2024
@saurabhdash2512 @ahmetustun
@younesbelkada @Rocketknight1
Cohere Model Release (huggingface#29622)
0e4a1c3 
* Cohere Model Release (#1)

Cohere Model Release

* Remove unnecessary files and code (#2)

Some cleanup

* Delete cohere-model directory (#3)

* Make Fix (#5)

* Pr fixes (#6)

* fixes for pr

* pr fixes for the format

* pr fixes for the format

* src/transformers/models/auto/tokenization_auto.py

* Tokenizer test (#8)

* tokenizer test

* format fix

* Adding Docs and other minor changes (#7)

* Add modeling tests (#9)

* Smol Fix (#11)

* tokenization tests are fixed

* format fixes

* fix pr doc tests

* fix pr doc tests

* fix pr doc tests

* fix pr style check

* small changes in cohere.md

* FIX: Address final comments for transformers integration (#13)

* fix modeling final nits and add proper test file

* for now leave empty tests

* add integration test

* push new test

* fix modeling cohere (#14)

* Update chat templates to use the new API (#15)

---------

Co-authored-by: ahmetustun <[email protected]>
Co-authored-by: Younes Belkada <[email protected]>
Co-authored-by: Matt <[email protected]>
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Reviewers

@markurtz markurtz Awaiting requested review from markurtz

2 more reviewers

@natuan natuan natuan approved these changes

@spacemanidol spacemanidol spacemanidol approved these changes

Reviewers whose approvals may not affect merge requirements
Assignees

@bfineran bfineran

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@bfineran @natuan @spacemanidol