Auto-Mode (Coming Soon)
Roadmap — not yet available
Auto-Mode is a planned feature. There is no Auto-Mode endpoint today; nothing on this page works yet. Use the manual model-selection workflow below in the meantime.
When released, Auto-Mode will automatically select the best model and hyperparameters for your dataset — no ML expertise required.
What Auto-Mode Will Do
- Analyze your dataset (size, feature types, target distribution)
- Recommend the best model for your task
- Auto-configure hyperparameters based on data characteristics
- Provide training time and accuracy estimates
In the Meantime
Until Auto-Mode is available, use these resources to choose your model:
- Choosing a Model — heuristics by task type, dataset size, and hardware
- Model Catalog — full list of available models with descriptions
- Hyperparameter Tuning — per-model parameter reference
You can also list available model configs programmatically:
from colabhive import ColabHive
client = ColabHive(api_key="...", account_id="...")
configs = client.training.model_configs(active_only=True)
for c in configs:
print(c.model_id, c.display_name, c.framework)
Or via REST:
curl "https://api.colabhive.com/api/builder/v1/training/model-configs" \
-H "X-Account-ID: YOUR_ACCOUNT_ID" \
-H "X-API-Key: YOUR_API_KEY"
Roadmap
Auto-Mode is part of the Developer Experience phase of ColabHive's roadmap. If you have feedback on what you'd like from Auto-Mode, reach out on Discord.