DataSpires SDK¶
Train, fine-tune, and run models on DataSpires GPUs from any notebook.
Works in: Google Colab, Kaggle, Jupyter, VS Code, and any Python 3.9+ environment.
Quickstart¶
Fine-tune a model on a Hugging Face dataset in a few lines:
from dataspires import DataSpiresClient
client = DataSpiresClient()
client.authenticate()
job = client.finetune(
model="qwen2.5-0.5b",
training_mode="low",
data="tatsu-lab/alpaca",
gpus=1,
)
result = job.run(wait=True)
if result["status"] == "completed":
job.download("./my-model")
else:
print(result.get("error") or result.get("reason"))
pretrain() and generate() follow the same pattern: create a job, then call job.run().
Where to go next¶
- Authentication — get an API key and set
DATASPIRES_API_KEY. - Core concepts — the three entry points, and how jobs run.
- Models and data sources — pass a registry name, Hugging Face ID, URL, Google Drive file, or local data.
- Finetune, Pretrain, Generate — task guides.
- API reference — the
DataSpiresClientsurface.
Built-in help¶
Every install ships an offline user guide: