Skip to content

Sa/model reload #2250

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 19, 2024
Merged

Sa/model reload #2250

merged 2 commits into from
Apr 19, 2024

Conversation

Satrat
Copy link

@Satrat Satrat commented Apr 19, 2024

No description provided.

@Satrat Satrat merged commit 63266d8 into sa/quant_mod_refactor Apr 19, 2024
@Satrat Satrat deleted the sa/model_reload branch April 19, 2024 19:59
bfineran pushed a commit that referenced this pull request May 6, 2024
* initial commit

* update setup.py

* Update setup.py

* fix setup.py

* move all config to sparsetensors

* cleanup class name and comments

* initial implementation untested

* fixing issues

* add test script

* update perplexity test

* refactor to compressed-tensors

* rename sparsetensors

* update setup

* Sa/model reload (#2250)

* working reload

* sparsegpt

* cleanup

* refactor tests

* only run oneshot once

* all tests passing

* remove unused config

* reset models on each parameterize

* style

* bring back SparsityConfigMetadata

* Update setup.py

Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>

* add more comparisons, tighten threshold

* use wikitext for perplexity

* update setup

* fix import problem

* fix clearml test

* compressed-tensors are transformers dep

* address PR comments

* can't repeat freeze

* UX pr comments

* quality

* shape consistency

* address PR comments

---------

Co-authored-by: dbogunowicz <damian@neuralmagic.com>
Co-authored-by: dbogunowicz <97082108+dbogunowicz@users.noreply.github.com>
Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>
Co-authored-by: George Ohashi <george@neuralmagic.com>
Satrat pushed a commit that referenced this pull request May 9, 2024
* initial commit

* update setup.py

* Update setup.py

* fix setup.py

* move all config to sparsetensors

* cleanup class name and comments

* initial implementation untested

* fixing issues

* add test script

* update perplexity test

* refactor to compressed-tensors

* rename sparsetensors

* update setup

* Sa/model reload (#2250)

* working reload

* sparsegpt

* cleanup

* refactor tests

* only run oneshot once

* all tests passing

* remove unused config

* reset models on each parameterize

* style

* bring back SparsityConfigMetadata

* Update setup.py

Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>

* add more comparisons, tighten threshold

* use wikitext for perplexity

* update setup

* fix import problem

* fix clearml test

* compressed-tensors are transformers dep

* address PR comments

* can't repeat freeze

* UX pr comments

* initial commit

* style

* skipping unit tests

* tests for quantization

* reloading unit tests

* backwards compat

* test updates

* update format

* fix inferring

* quality

* shape consistency

* address PR comments

* PR comments

* fixing some things

* style

* pull from cp main

* postmerge too

* export needs it too

* Update src/sparseml/modifiers/obcq/utils/sgpt_wrapper.py

Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>

---------

Co-authored-by: dbogunowicz <damian@neuralmagic.com>
Co-authored-by: dbogunowicz <97082108+dbogunowicz@users.noreply.github.com>
Co-authored-by: Rahul Tuli <rahul@neuralmagic.com>
Co-authored-by: George Ohashi <george@neuralmagic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant