Adaptive Image Intelligence Architecture
Go to file
Falko Victor Habel 0d5e5688eb Merge pull request 'first_pip' (#4) from first_pip into develop
Reviewed-on: Fabel/AIIA#4
2025-01-29 21:33:31 +00:00
src/aiia fixed savings 2025-01-28 17:18:21 +01:00
.gitignore Initial commit 2025-01-07 10:56:41 +00:00
LICENSE Initial commit 2025-01-07 10:56:41 +00:00
MANIFEST.in added first pip install version 0.1 2025-01-28 10:58:33 +01:00
README.md improved pretraining 2025-01-28 11:27:42 +01:00
example.py updated pretrainer to handle multiple classes and configs. 2025-01-28 11:42:03 +01:00
pyproject.toml added first pip install version 0.1 2025-01-28 10:58:33 +01:00
requirements.txt added first pip install version 0.1 2025-01-28 10:58:33 +01:00
run.py fixed savings 2025-01-28 17:18:21 +01:00
setup.cfg added first pip install version 0.1 2025-01-28 10:58:33 +01:00
setup.py added first pip install version 0.1 2025-01-28 10:58:33 +01:00

README.md

AIIA

Example Usage:

from aiia.model import AIIABase
from aiia.model.config import AIIAConfig
from aiia.pretrain import Pretrainer

# Create your model
config = AIIAConfig(model_name="AIIA-Base-512x20k")
model = AIIABase(config)

# Initialize pretrainer with the model
pretrainer = Pretrainer(model, learning_rate=1e-4)

# List of dataset paths
dataset_paths = [
    "/path/to/dataset1.parquet",
    "/path/to/dataset2.parquet"
]

# Start training with multiple datasets
pretrainer.train(
    dataset_paths=dataset_paths,
    num_epochs=10,
    batch_size=2,
    sample_size=10000
)