{"id":19932337,"url":"https://github.com/amazon-science/dq-bart","last_synced_at":"2025-10-15T15:49:57.250Z","repository":{"id":48493030,"uuid":"470063308","full_name":"amazon-science/dq-bart","owner":"amazon-science","description":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization (ACL 2022)","archived":false,"fork":false,"pushed_at":"2023-06-12T21:35:29.000Z","size":30,"stargazers_count":51,"open_issues_count":1,"forks_count":10,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-09-09T05:05:23.600Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/amazon-science.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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,"zenodo":null}},"created_at":"2022-03-15T08:14:18.000Z","updated_at":"2025-09-08T14:20:06.000Z","dependencies_parsed_at":"2025-05-03T11:43:17.682Z","dependency_job_id":null,"html_url":"https://github.com/amazon-science/dq-bart","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/amazon-science/dq-bart","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fdq-bart","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fdq-bart/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fdq-bart/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fdq-bart/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/amazon-science","download_url":"https://codeload.github.com/amazon-science/dq-bart/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amazon-science%2Fdq-bart/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279089911,"owners_count":26101079,"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":"2025-10-15T02:00:07.814Z","response_time":56,"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":[],"created_at":"2024-11-12T23:09:50.576Z","updated_at":"2025-10-15T15:49:57.200Z","avatar_url":"https://github.com/amazon-science.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## DQ-BART:  Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization\nThis repository contains the authors' implementation of the ACL 2022 paper \"[DQ-BART: Efficient Sequence-to-Sequence Model via\nJoint Distillation and Quantization](https://arxiv.org/pdf/2203.11239.pdf).\"\n\n## Requirements\n- Install PyTorch from the [official website](https://pytorch.org/get-started/locally/).\n- Install dependencies via `pip install -r requirements.txt`. \n- The teacher model should be available locally, e.g., downloading manually from the [huggingface model hub](https://huggingface.co/models).\n\n## Sample Command\n- The following command will train an `8-8-8 3-1` model on CNN/DailyMail dataset. You may use [accelerate](https://github.com/huggingface/accelerate) for distributed training. \n    ```bash\n    python3 run_summarization_no_trainer.py \\\n      --model_name_or_path ainize/bart-base-cnn \\\n      --dataset_name cnn_dailymail \\\n      --dataset_config_name 3.0.0 \\\n      --pred_distill \\\n      --intermediate_distill \\\n      --num_train_epochs 20 \\\n      --weight_bits 8 \\\n      --do_train \\\n      --do_test \\\n      --distill_encoder 3 \\\n      --distill_decoder 1 \\\n      --learning_rate 3e-5 \n    ```\n## Citation\nYou may cite our work using\n```\n@inproceedings{li2022dqbart,\n  title={DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization},\n  author={Li, Zheng and Wang, Zijian and Tan, Ming and Nallapati, Ramesh and Bhatia, Parminder and Arnold, Andrew and Xiang, Bing and Roth, Dan},\n  booktitle={Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},\n  pages={203--211},\n  year={2022}\n}\n```\n\n\n## Security\n\nSee [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.\n\n## License\n\nThis project is licensed under the Apache-2.0 License.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famazon-science%2Fdq-bart","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famazon-science%2Fdq-bart","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famazon-science%2Fdq-bart/lists"}