Skip to content

docs: add MNIST magnitude pruning tutorial #33

Open
u-simha wants to merge 5 commits into
apple:mainfrom
u-simha:u/usimha/add-mnist-magnitude-pruning-tutorial
Open

docs: add MNIST magnitude pruning tutorial #33
u-simha wants to merge 5 commits into
apple:mainfrom
u-simha:u/usimha/add-mnist-magnitude-pruning-tutorial

Conversation

@u-simha

@u-simha u-simha commented Jul 10, 2026

Copy link
Copy Markdown
Contributor

This PR:

  • Adds a MNIST magnitude pruning tutorial notebook
  • Updates the sidebar to surface the Pruning documentation

Testing

  • Execute notebook locally

@u-simha u-simha changed the title docs: add MNIST magnitude pruning tutorial (rdar://178094625) docs: add MNIST magnitude pruning tutorial Jul 10, 2026
@u-simha u-simha requested a review from guru-desh July 15, 2026 01:25
Comment thread docs/src/examples/toy_models.md
Comment thread docs/src/tutorials/mnist_pruning.ipynb
@u-simha u-simha force-pushed the u/usimha/add-mnist-magnitude-pruning-tutorial branch from e82fa10 to 7267e05 Compare July 16, 2026 20:19
u-simha added 5 commits July 16, 2026 13:26
Adds a tutorial notebook demonstrating post-training and
fine-tuning-based magnitude pruning on an MNIST model, mirroring the
existing quantization and palettization tutorials. Also adds the
missing Pruning entry to the sidebar toctree.
Aligns the post-training pruning section with the fine-tuning
section, which already targets 70% sparsity, instead of the default
50%.
Aligns post-training and fine-tuning sparsity at 50% and ships the
notebook with executed cell outputs, showing the actual effect of
pruning on accuracy end-to-end.
Removes a local scikit-learn/coremltools version warning baked into
the notebook's output; it's environment noise, not tutorial content.
@u-simha u-simha force-pushed the u/usimha/add-mnist-magnitude-pruning-tutorial branch from 7267e05 to dbb2e2b Compare July 16, 2026 20:27
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.

2 participants