{"id":50551903,"url":"https://github.com/vectifyai/model-augmented-fine-tuning","last_synced_at":"2026-06-04T04:03:12.648Z","repository":{"id":205983823,"uuid":"694767404","full_name":"VectifyAI/Model-Augmented-Fine-Tuning","owner":"VectifyAI","description":"Fine-tuning black-box OpenAI embedding models","archived":false,"fork":false,"pushed_at":"2025-08-04T08:50:40.000Z","size":16771,"stargazers_count":11,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-08-04T12:12:59.047Z","etag":null,"topics":["embedding-models","embeddings","fine-tuning","openai","rag","retrieval","retrieval-augmented-generation","vector-database"],"latest_commit_sha":null,"homepage":"https://arxiv.org/pdf/2402.12177","language":"Jupyter Notebook","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/VectifyAI.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}},"created_at":"2023-09-21T16:45:08.000Z","updated_at":"2025-08-04T08:50:43.000Z","dependencies_parsed_at":null,"dependency_job_id":"e6af5c13-c7cc-4467-a0c6-9ce145d548ea","html_url":"https://github.com/VectifyAI/Model-Augmented-Fine-Tuning","commit_stats":null,"previous_names":["vectifyai/fae"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/VectifyAI/Model-Augmented-Fine-Tuning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VectifyAI%2FModel-Augmented-Fine-Tuning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VectifyAI%2FModel-Augmented-Fine-Tuning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VectifyAI%2FModel-Augmented-Fine-Tuning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VectifyAI%2FModel-Augmented-Fine-Tuning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/VectifyAI","download_url":"https://codeload.github.com/VectifyAI/Model-Augmented-Fine-Tuning/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VectifyAI%2FModel-Augmented-Fine-Tuning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33888302,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-04T02:00:06.755Z","response_time":64,"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":["embedding-models","embeddings","fine-tuning","openai","rag","retrieval","retrieval-augmented-generation","vector-database"],"created_at":"2026-06-04T04:03:11.797Z","updated_at":"2026-06-04T04:03:12.634Z","avatar_url":"https://github.com/VectifyAI.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning\n\nA method to fine-tune the black-box OpenAI embedding to improve the retrieval performance 📈.\n\n📝 See our paper [Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning](https://arxiv.org/pdf/2402.12177) for a detailed introduction to this method.\n\nOther training details and dataset construction can be found in [LlamaIndex's Blog](https://medium.com/llamaindex-blog/fine-tuning-embeddings-for-rag-with-synthetic-data-e534409a3971).\n\n## Install 🛠️ \n```bash\npip install -r requirements.txt\n```\n\n## Fine-tune the BAAI/bge-small-en model\n```bash\ncd ./finetune\npython train.py\n```\n\n## Fine-tune the FAE model\n```bash\ncd ./finetune\npython fae_train.py\n```\n\nThe comparison of the evaluation results can be found in the [jupyter notebook](https://github.com/VectifyAI/FAE/blob/main/finetune/eval.ipynb) 📊.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvectifyai%2Fmodel-augmented-fine-tuning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvectifyai%2Fmodel-augmented-fine-tuning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvectifyai%2Fmodel-augmented-fine-tuning/lists"}