{"id":28268448,"url":"https://github.com/jonhue/activeft","last_synced_at":"2025-10-29T02:04:48.603Z","repository":{"id":257806156,"uuid":"758430178","full_name":"jonhue/activeft","owner":"jonhue","description":"PyTorch library for Active Fine-Tuning","archived":false,"fork":false,"pushed_at":"2025-09-27T11:39:34.000Z","size":376,"stargazers_count":92,"open_issues_count":7,"forks_count":9,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-10-04T17:57:03.468Z","etag":null,"topics":["active-fine-tuning","active-inference","active-learning","artificial-intelligence","data-loader","data-retrieval","deep-learning","fine-tuning","machine-learning","python","pytorch"],"latest_commit_sha":null,"homepage":"https://jonhue.github.io/activeft/","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/jonhue.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-02-16T09:58:35.000Z","updated_at":"2025-09-27T21:51:43.000Z","dependencies_parsed_at":null,"dependency_job_id":"2e6f85b2-af5c-419d-863f-a2d945b74268","html_url":"https://github.com/jonhue/activeft","commit_stats":null,"previous_names":["jonhue/activeft"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/jonhue/activeft","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonhue%2Factiveft","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonhue%2Factiveft/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonhue%2Factiveft/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonhue%2Factiveft/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jonhue","download_url":"https://codeload.github.com/jonhue/activeft/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonhue%2Factiveft/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281544195,"owners_count":26519554,"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":"2025-10-29T02:00:06.901Z","response_time":59,"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":["active-fine-tuning","active-inference","active-learning","artificial-intelligence","data-loader","data-retrieval","deep-learning","fine-tuning","machine-learning","python","pytorch"],"created_at":"2025-05-20T15:12:50.436Z","updated_at":"2025-10-29T02:04:48.565Z","avatar_url":"https://github.com/jonhue.png","language":"Python","readme":"# Active Fine-Tuning\n\nA library for automatic data selection in active fine-tuning of large neural networks.\n\n**[Website](https://jonhue.github.io/activeft)** | **[Documentation](https://jonhue.github.io/activeft/docs)**\n\nPlease cite our work if you use this library in your research ([bibtex below](#citation)):\n\n- [Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs](https://arxiv.org/abs/2410.08020)\n- [Transductive Active Learning: Theory and Applications](https://arxiv.org/abs/2402.15898) (Section 4)\n\n## Installation\n\n```\npip install activeft\n```\n\n## Usage Example\n\n```python\nfrom activeft.sift import Retriever\n\n# Load embeddings\nembeddings = np.random.rand(1000, 512)\nquery_embeddings = np.random.rand(1, 512)\n\nindex = faiss.IndexFlatIP(d)\nindex.add(embeddings)\nretriever = Retriever(index)\nindices = retriever.search(query_embeddings, N=10)\n```\n\n## Development\n\n### CI checks\n\n* The code is auto-formatted using `black .`.\n* Static type checks can be run using `pyright`.\n* Tests can be run using `pytest test`.\n\n### Documentation\n\nTo start a local server hosting the documentation run ```pdoc ./activeft --math```.\n\n### Publishing\n\n1. update version number in `pyproject.toml` and `activeft/__init__.py`\n2. build: `poetry build`\n3. publish: `poetry publish`\n4. push version update to GitHub\n5. create new release on GitHub\n\n## Citation\n\n```bibtex\n@article{hubotter2024efficiently,\n\ttitle        = {Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs},\n\tauthor       = {H{\\\"u}botter, Jonas and Bongni, Sascha and Hakimi, Ido and Krause, Andreas},\n\tyear         = 2024,\n\tjournal      = {arXiv preprint arXiv:2410.08020}\n}\n\n@inproceedings{hubotter2024transductive,\n\ttitle        = {Transductive Active Learning: Theory and Applications},\n\tauthor       = {H{\\\"u}botter, Jonas and Sukhija, Bhavya and Treven, Lenart and As, Yarden and Krause, Andreas},\n\tyear         = 2024,\n\tbooktitle    = {Advances in Neural Information Processing Systems}\n}\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjonhue%2Factiveft","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjonhue%2Factiveft","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjonhue%2Factiveft/lists"}