-
Notifications
You must be signed in to change notification settings - Fork 27
base weight loading for pytorch sparse quant models #39
Conversation
blocks neuralmagic/sparseml#81 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we should likely clean up the flow in this function. There are a few edge cases in here that can get by right now; specifically: passing in an invalid recipe type, returning checkpoint files if recipe type is not transfer learning, etc.
I'd recommend we reorganize the logic to gathering and downloading the framework files from the correct base model based on if it's transfer learning or the original sparsification run (and failing if the recipe type doesn't match one of these; None would match to original), and then restricting those files for the ckpt or end framework file based on what was requested
* GA code, toctree links (#32) - added tracking for docs output - added help links for docs output * Update README.md (#34) removed placeholder reference to comingsoon repo in favor of active repo * Makefile build command for nightly builds (#35) * docs updates (#36) - correcting double-slash URL issue - enhancing left nav for Help - revised mission statement provided for readme and docs * Zoo functions for loading recipes and base checkpoint weights from stubs (#37) * Update for 0.1.1 release (#40) - update python version to 0.1.1 - setup.py add in version parts and _VERSION_MAJOR_MINOR for more flexibility with dependencies between neural magic packages * base weight loading for pytorch sparse quant models (#39) * add hard check for valid recipe types in download_recipe_from_stub (#42) * Log Level Changes (#44) Logging level to warn, changed credential log to debug, increased credential duration to 30 days * Sparsification update (#43) * Update sparsification descriptions and move to preferred verbage * more sparsification updates * update from comments in deepsparse for sparsification * Update README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update docs/source/index.rst Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update docs/source/index.rst Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update docs/source/index.rst Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update docs/source/index.rst Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update README.md Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * Update docs/source/index.rst Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> * fix links in index.rst for reviewed content * update compontent overviews and taglines * update "this repository link" for docs in overview * update doc links to not have trailing slash Co-authored-by: Jeannie Finks <74554921+jeanniefinks@users.noreply.github.com> Co-authored-by: Jeannie Finks (NM) <74554921+jeanniefinks@users.noreply.github.com> Co-authored-by: Benjamin Fineran <bfineran@users.noreply.github.com> Co-authored-by: Kevin Escobar Rodriguez <kevin.rodriguez@neuralmagic.com>
No description provided.