{"id":15659730,"url":"https://github.com/sayakpaul/bert-for-mobile","last_synced_at":"2025-08-31T09:34:11.740Z","repository":{"id":43780071,"uuid":"298930835","full_name":"sayakpaul/BERT-for-Mobile","owner":"sayakpaul","description":"Compares the DistilBERT and MobileBERT architectures for mobile deployments.","archived":false,"fork":false,"pushed_at":"2020-10-15T03:48:24.000Z","size":424,"stargazers_count":33,"open_issues_count":0,"forks_count":5,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-06-23T22:03:33.055Z","etag":null,"topics":["bert","distilbert","mobile","mobile-bert","nlp","tensorflow-lite"],"latest_commit_sha":null,"homepage":"","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/sayakpaul.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}},"created_at":"2020-09-27T01:40:43.000Z","updated_at":"2024-09-05T21:22:52.000Z","dependencies_parsed_at":"2022-07-08T00:00:26.677Z","dependency_job_id":null,"html_url":"https://github.com/sayakpaul/BERT-for-Mobile","commit_stats":null,"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/sayakpaul/BERT-for-Mobile","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayakpaul%2FBERT-for-Mobile","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayakpaul%2FBERT-for-Mobile/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayakpaul%2FBERT-for-Mobile/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayakpaul%2FBERT-for-Mobile/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sayakpaul","download_url":"https://codeload.github.com/sayakpaul/BERT-for-Mobile/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayakpaul%2FBERT-for-Mobile/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272965354,"owners_count":25023066,"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","status":"online","status_checked_at":"2025-08-31T02:00:09.071Z","response_time":79,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["bert","distilbert","mobile","mobile-bert","nlp","tensorflow-lite"],"created_at":"2024-10-03T13:18:28.676Z","updated_at":"2025-08-31T09:34:11.718Z","avatar_url":"https://github.com/sayakpaul.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# BERT-for-Mobile\nCompares the [DistilBERT](https://arxiv.org/abs/1910.01108) and [MobileBERT](https://arxiv.org/abs/2004.02984) architectures for mobile deployments. It is a part of the [End-To-End TFLite Tutorials](https://github.com/ml-gde/e2e-tflite-tutorials) project. Here's blog post (TODO: link) that presents this comparison in a comprehensive manner. \n\nThe notebooks included in this repository show how to use the DistilBERT model with the **SST-2 dataset** for text classification. The notebooks also include the code for TensorFlow Lite model conversion and evaluation. In the future, I also plan to cover question-answering with DistilBERT. \n\n**Note** that this repository does not contain the model training and model conversion code for MobileBERT since TensorFlow Lite has got a pretty [straightforward guide](https://www.tensorflow.org/lite/tutorials/model_maker_text_classification) already available. A similar guide is also available [here](https://www.tensorflow.org/lite/tutorials/model_maker_question_answer) for question-answering. \n\n## TensorFlow Lite model files and fine-tuned weights\n\n* [ALBERT](https://github.com/sayakpaul/BERT-for-Mobile/releases/tag/v0.5.0)\n* [DistilBERT](https://github.com/sayakpaul/BERT-for-Mobile/releases/tag/v0.4.0)\n* [MobileBERT](https://github.com/sayakpaul/BERT-for-Mobile/releases/tag/v0.3.0)\n\n## Benchmarks \n\n\u003cdiv align=\"center\"\u003e\u003cimg src=\"https://i.ibb.co/0GNVQRz/IMAGE.png\"\u003e\u003c/img\u003e\u003c/div\u003e\n\n## Acknowledgements\n\nThanks to the [ML-GDE program](https://developers.google.com/community/experts) for providing GCP credits that were used in order to spin up an AI Platform Notebook. Thanks to [Khanh LeViet](https://twitter.com/khanhlvg) for his guidance. \n\n\u003cdiv align=\"center\"\u003e\u003cimg src=\"https://i.ibb.co/ZXtwJjV/Webp-net-resizeimage.png\" width=\"100\" height=\"100\"\u003e\u003c/img\u003e\u003c/div\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsayakpaul%2Fbert-for-mobile","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsayakpaul%2Fbert-for-mobile","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsayakpaul%2Fbert-for-mobile/lists"}