{"id":19023674,"url":"https://github.com/neuralmagic/examples","last_synced_at":"2025-04-15T07:05:49.712Z","repository":{"id":181229785,"uuid":"665638315","full_name":"neuralmagic/examples","owner":"neuralmagic","description":"Notebooks using the Neural Magic libraries 📓","archived":false,"fork":false,"pushed_at":"2024-07-24T17:37:45.000Z","size":47452,"stargazers_count":42,"open_issues_count":4,"forks_count":8,"subscribers_count":12,"default_branch":"main","last_synced_at":"2025-04-15T07:05:38.349Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/neuralmagic.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-07-12T16:42:43.000Z","updated_at":"2025-03-23T20:11:29.000Z","dependencies_parsed_at":"2023-08-09T22:00:53.468Z","dependency_job_id":"dd18f7f1-7a0e-4838-8871-cfd3ef02629b","html_url":"https://github.com/neuralmagic/examples","commit_stats":null,"previous_names":["neuralmagic/notebooks","neuralmagic/examples"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neuralmagic%2Fexamples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neuralmagic%2Fexamples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neuralmagic%2Fexamples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neuralmagic%2Fexamples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/neuralmagic","download_url":"https://codeload.github.com/neuralmagic/examples/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249023700,"owners_count":21199958,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-08T20:31:51.794Z","updated_at":"2025-04-15T07:05:49.684Z","avatar_url":"https://github.com/neuralmagic.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural Magic 🪄 Model Optimization Examples \n\nDeep learning models have grown bigger over the years making their deployment complex and expensive. [Neural Magic](https://github.com/neuralmagic) \nis building model optimization tools to change this narrative.  We provide tools for optimizing these models to make them more \nperformant and easier to deploy. For example, you can use [SparseML](https://github.com/neuralmagic/sparseml) to\nmake your model sparse in a couple of lines of code. Neural Magic also provides numerous optimized natural language and computer  vision models on the\n[SparseZoo](https://sparsezoo.neuralmagic.com/). When you are ready to move to production, you can take advantage of the [DeepSparse](https://github.com/neuralmagic/deepsparse) \ninference runtime to achieve GPU-class performance on commodity CPUs. \n\nIn this repository, you will find examples that show how to use Neural Magic's tools to apply optimizations on your models.\nYou will also find examples on how to use Neural Magic's libraries with other machine learning packages. \n\n## Highlighted Notebooks \nHere are three notebooks you can look at immediately: \n\n### Stable Diffusion on CPUs With DeepSparse\n[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuralmagic/notebooks/blob/main/notebooks/deepsparse-stable-diffusion/notebook.ipynb)\n\nIn this notebook, you will learn how to perform text-to-image generation on DeepSparse using stable diffusion models. \nDeepSparse accelerates inference, enabling the images to be generated on commodity CPUs. \n\n![Stable diffusion notebook](images/stable.png)\n\n### Optimize YOLOv5 Model With SparseML\n[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuralmagic/examples/blob/main/notebooks/yolov5-custom-data/yolov5_custom_data.ipynb)\n\nThis notebook will take you through the process of optimizing a YOLOv5 model for real-time object detection. You will also \nlearn how to deploy the resulting model on CPU using DeepSparse. \n\n![YOLOv5 notebook](images/yolov5.png)\n### Run Hugging Face Models on DeepSparse\n[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/neuralmagic/notebooks/blob/main/notebooks/optimum-deepsparse/optimum-deepsparse.ipynb)\n\nDeepSparse supports numerous transformer models. This notebook illustrates how to pull models from Hugging Face using \nOptimum and run them on CPU using DeepSparse. \n\n![Optimum notebook](images/optimum.png)\n\n## Bugs and Contribution \nLet us know in case something isn't working by [creating an issue](https://github.com/neuralmagic/examples/issues). You \ncan also propose a fix by [submitting a pull request](https://github.com/neuralmagic/examples/pulls). Join our \n[Slack community](https://neuralmagic.com/community/) to \nengage with other practitioners or inform us of any examples you'd like to see. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneuralmagic%2Fexamples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fneuralmagic%2Fexamples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneuralmagic%2Fexamples/lists"}