{"id":19146469,"url":"https://github.com/kahsolt/nn-prune-svd","last_synced_at":"2025-09-08T22:32:30.375Z","repository":{"id":193814807,"uuid":"687021421","full_name":"Kahsolt/nn-prune-svd","owner":"Kahsolt","description":"Neural network weights prune in a static LoRA–like way","archived":false,"fork":false,"pushed_at":"2023-12-29T12:37:09.000Z","size":134,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-09T07:47:16.476Z","etag":null,"topics":["svd","tutorial","weight-pruning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Kahsolt.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2023-09-04T12:40:06.000Z","updated_at":"2024-01-28T06:29:56.000Z","dependencies_parsed_at":"2024-11-09T07:44:19.043Z","dependency_job_id":"da567996-3af8-49f8-824c-930a08da8006","html_url":"https://github.com/Kahsolt/nn-prune-svd","commit_stats":null,"previous_names":["kahsolt/nn-prune-svd"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kahsolt%2Fnn-prune-svd","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kahsolt%2Fnn-prune-svd/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kahsolt%2Fnn-prune-svd/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kahsolt%2Fnn-prune-svd/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Kahsolt","download_url":"https://codeload.github.com/Kahsolt/nn-prune-svd/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":232362199,"owners_count":18511527,"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":["svd","tutorial","weight-pruning"],"created_at":"2024-11-09T07:44:13.766Z","updated_at":"2025-01-03T16:28:42.931Z","avatar_url":"https://github.com/Kahsolt.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# nn-prune-svd\n\n    Neural network weights prune in a static LoRA–like way -- via SVD.\n\n----\n\n### results\n\n⚠ Not correct, need more investigation\n\n![](img/run_grid.png)\n\n\n### dataset\n\nThe test dataset is 1000 images picked from the validset of ImageNet-1k. \n\n- download it from [https://pan.quark.cn/s/cf8688f5bca1](https://pan.quark.cn/s/cf8688f5bca1)\n- unzip under `/data` folder; the password is `]@vD4S%ojjH6UC#I!b37`, just to avoid content censorship :(\n\n```\ndata\n└── imagenet-1k\n    ├── image_name_to_class_id_and_name.json\n    └── val\n        └── ILSVRC2012_val_*.png\n```\n\n### reference\n\n- torch.svd [https://pytorch.org/docs/stable/generated/torch.svd.html](https://pytorch.org/docs/stable/generated/torch.svd.html)\n- LoRA: [https://arxiv.org/abs/2106.09685](https://arxiv.org/abs/2106.09685)\n\n----\nby Armit\n2023/09/04 \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkahsolt%2Fnn-prune-svd","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkahsolt%2Fnn-prune-svd","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkahsolt%2Fnn-prune-svd/lists"}