# roboflow/maestro

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/roboflow-maestro).**

2,659 stars · 221 forks · Python · apache-2.0

## Links

- GitHub: https://github.com/roboflow/maestro
- Homepage: https://maestro.roboflow.com
- awesome-repositories: https://awesome-repositories.com/repository/roboflow-maestro.md

## Topics

`captioning` `fine-tuning` `florence-2` `multimodal` `objectdetection` `paligemma` `phi-3-vision` `qwen2-vl` `transformers` `vision-and-language` `vqa`

## Tags

### Artificial Intelligence & ML

- [Fine-Tuning Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training-frameworks/vision-model-training/vision-language-training/vision-language-fine-tunings/fine-tuning-frameworks.md) — A framework for fine-tuning multimodal vision-language models like Florence-2 and PaliGemma 2 on custom datasets with a streamlined Python API and CLI.
- [Streamlined Fine-Tuning Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training-frameworks/vision-model-training/vision-language-training/vision-language-fine-tunings/streamlined-fine-tuning-pipelines.md) — Fine-tune multimodal models on custom datasets using a streamlined configuration and training pipeline. ([source](https://cdn.jsdelivr.net/gh/roboflow/maestro@develop/README.md))
- [Static Dictionary Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning-frameworks/declarative-training-frameworks/static-dictionary-definitions.md) — Defines all training parameters (dataset, epochs, batch size, optimizer) as a static dictionary rather than imperative code.
- [Vision-Language Fine-Tunings](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training-frameworks/vision-model-training/vision-language-training/vision-language-fine-tunings.md) — Fine-tuning multimodal vision-language models on custom datasets for specialized computer vision tasks using a streamlined pipeline.
- [Python API](https://awesome-repositories.com/f/artificial-intelligence-ml/training-configurations/python-api.md) — Configure fine-tuning programmatically by importing a training function and passing a configuration dictionary. ([source](https://maestro.roboflow.com))

### Development Tools & Productivity

- [Training](https://awesome-repositories.com/f/development-tools-productivity/cli-configurations/training.md) — Configure fine-tuning jobs from the command line by specifying dataset, epochs, batch size, optimization strategy, and metrics. ([source](https://maestro.roboflow.com))
- [Training Execution CLI Commands](https://awesome-repositories.com/f/development-tools-productivity/cli-training-toolkits/training-execution-cli-commands.md) — Start a fine-tuning job from the command line by specifying dataset, epochs, batch size, optimization strategy, and metrics. ([source](https://cdn.jsdelivr.net/gh/roboflow/maestro@develop/README.md))
- [Pipeline Configurations](https://awesome-repositories.com/f/development-tools-productivity/configuration-dictionaries/pipeline-configurations.md) — Passes a single Python dictionary through the entire training lifecycle, from setup to execution.
- [Training Execution APIs](https://awesome-repositories.com/f/development-tools-productivity/python-api-integrations/training-execution-apis.md) — Run fine-tuning programmatically by passing a configuration dictionary to a model-specific training function. ([source](https://cdn.jsdelivr.net/gh/roboflow/maestro@develop/README.md))

### Web Development

- [Unified Interfaces](https://awesome-repositories.com/f/web-development/extension-support/model-architecture-adapters/multimodal-adapters/unified-interfaces.md) — Wraps distinct vision-language model architectures behind a unified fine-tuning interface.

### Part of an Awesome List

- [Dispatch Mechanisms](https://awesome-repositories.com/f/awesome-lists/ai/model-training-and-fine-tuning/dispatch-mechanisms.md) — Routes fine-tuning jobs to model-specific training functions based on a configuration dictionary key.