Skip to content
Databricks Blog·· 3 h agoAI score36

Tabular Foundation Models on Databricks AI Runtime: How TFMs Work and When to Adopt Them

Tabular foundation models on Databricks AI Runtime

AI summary

Databricks examines tabular foundation models (TFMs), pretrained transformers that predict on new tables via in-context learning without task-specific training. It compares TabICLv2 (~28M parameters, BSD 3-Clause), TabFM (~400M, non-commercial license) and TabPFNv3.5 (~220M), and shows how Databricks AI Runtime supports TFM experimentation and fine-tuning with managed GPU infrastructure.

Source:Databricks Blog · databricks.com