Skip to content

maestro

VLM fine-tuning for everyone


Hello

maestro is a streamlined tool to accelerate the fine-tuning of multimodal models. By encapsulating best practices from our core modules, maestro handles configuration, data loading, reproducibility, and training loop setup. It currently offers ready-to-use recipes for popular vision-language models such as Florence-2, PaliGemma 2, and Qwen2.5-VL.

Quickstart

Install

To begin, install the model-specific dependencies. Since some models may have clashing requirements, we recommend creating a dedicated Python environment for each model.

pip install "maestro[florence_2]"

pip install "maestro[paligemma_2]"

pip install "maestro[qwen_2_5_vl]"

CLI

Kick off fine-tuning with our command-line interface, which leverages the configuration and training routines defined in each model’s core module. Simply specify key parameters such as the dataset location, number of epochs, batch size, optimization strategy, and metrics.

maestro florence_2 train \
  --dataset "dataset/location" \
  --epochs 10 \
  --batch-size 4 \
  --optimization_strategy "lora" \
  --metrics "edit_distance"

maestro paligemma_2 train \
  --dataset "dataset/location" \
  --epochs 10 \
  --batch-size 4 \
  --optimization_strategy "qlora" \
  --metrics "edit_distance"

maestro qwen_2_5_vl train \
  --dataset "dataset/location" \
  --epochs 10 \
  --batch-size 4 \
  --optimization_strategy "qlora" \
  --metrics "edit_distance"

Python

For greater control, use the Python API to fine-tune your models. Import the train function from the corresponding module and define your configuration in a dictionary. The core modules take care of reproducibility, data preparation, and training setup.

from maestro.trainer.models.florence_2.core import train

config = {
    "dataset": "dataset/location",
    "epochs": 10,
    "batch_size": 4,
    "optimization_strategy": "qlora",
    "metrics": ["edit_distance"],
}

train(config)

from maestro.trainer.models.paligemma_2.core import train

config = {
    "dataset": "dataset/location",
    "epochs": 10,
    "batch_size": 4,
    "optimization_strategy": "qlora",
    "metrics": ["edit_distance"],
}

train(config)

from maestro.trainer.models.qwen_2_5_vl.core import train

config = {
    "dataset": "dataset/location",
    "epochs": 10,
    "batch_size": 4,
    "optimization_strategy": "qlora",
    "metrics": ["edit_distance"],
}

train(config)

Comments