{"data":{"slug":"roboflow-maestro","name":"maestro","tagline":"Streamlines fine-tuning for multimodal models PaliGemma 2, Florence-2, Qwen2.5-VL","github_url":"https://github.com/roboflow/maestro","owner":"roboflow","repo":"maestro","owner_avatar_url":"https://avatars.githubusercontent.com/u/53104118?v=4","primary_language":"Python","stars":2699,"forks":224,"topics":["captioning","fine-tuning","florence-2","multimodal","objectdetection","paligemma","phi-3-vision","qwen2-vl","transformers","vision-and-language","vqa"],"archived":false,"github_pushed_at":"2026-09-14T17:53:59+00:00","maintenance_label":"Very active","stars_delta_30d":12,"url":"https://www.graphcanon.com/tools/roboflow-maestro","markdown_url":"https://www.graphcanon.com/tools/roboflow-maestro.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/roboflow-maestro","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=roboflow-maestro","description":"streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL","homepage_url":"https://maestro.roboflow.com","license":"Apache-2.0","open_issues":34,"watchers":29,"ai_summary":"A Python-based repository for simplifying the fine-tuning process of multimodal models with a focus on tasks like captioning, object detection, and vision-and-language understanding.","readme_excerpt":"### Install\n\nTo begin, install the model-specific dependencies. Since some models may have clashing requirements,\nwe recommend creating a dedicated Python environment for each model.\n\n```bash\npip install \"maestro[paligemma_2]\"\n```","github_created_at":"2023-11-24T13:28:57+00:00","created_at":"2026-07-11T11:38:02.170277+00:00","updated_at":"2026-09-20T06:28:48.193668+00:00","categories":[{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"captioning","name":"captioning"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"florence-2","name":"florence-2"},{"slug":"multimodal","name":"multimodal"},{"slug":"objectdetection","name":"objectdetection"},{"slug":"paligemma-2","name":"paligemma 2"},{"slug":"qwen2-5-vl","name":"qwen2.5-vl"},{"slug":"transformers","name":"transformers"}],"trust":{"provenance":{"is_fork":false,"github_id":723015178,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-19T18:23:26.566Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":5,"last_release_at":"2025-02-05T08:45:17Z","stars_delta_30d":12,"open_issues_delta_30d":6},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:38:03.471Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-19T18:23:27.597Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-19T18:23:27.597Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-19T18:23:27.597Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-19T18:23:27.597Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use Maestro when focusing on tasks such as captioning, object detection, or vision-and-language understanding with the aforementioned models.","Select Maestro if you are working specifically within projects that require fine-tuning PaliGemma 2, Florence-2, or Qwen2.5-VL."],"when_not_to_use":["Avoid using Maestro for fine-tuning other multimodal models outside of the specified trio: PaliGemma 2, Florence-2 and Qwen2.5-VL.","Do not opt for Maestro if your project does not align with captioning, object detection or vision-and-language tasks."],"source":"enrich:decision_facts","observed_at":"2026-07-15T09:21:45.165Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Maestro is a specialized Python tool for streamlining fine-tuning processes of specific multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL."}]}}