51 lines
1.1 KiB
Markdown
51 lines
1.1 KiB
Markdown
# AIIA
|
|
|
|
## Installation
|
|
|
|
### Install via pip
|
|
|
|
To install the package directly from the Git repository using `pip`, run:
|
|
```sh
|
|
pip install git+https://gitea.fabelous.app/Machine-Learning/AIIA.git
|
|
```
|
|
|
|
This command will clone the repository and install the package along with its dependencies.
|
|
|
|
### Additional Notes
|
|
|
|
- Ensure you have `git` installed on your system.
|
|
- Make sure `pip` is up-to-date. You can update it using:
|
|
```sh
|
|
pip install --upgrade pip
|
|
```
|
|
|
|
That's it! You should now have the AIIA package installed and ready to use.
|
|
|
|
|
|
## Example Usage:
|
|
```Python
|
|
from aiia.model import AIIABase
|
|
from aiia.model 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
|
|
)
|
|
``` |