atharvavdeo commited on
Commit ·
2f9a13d
1
Parent(s): 68f889f
Document TabFM runtime behavior
Browse files
README.md
CHANGED
|
@@ -46,6 +46,13 @@ Model choices include Logistic, Linear Regression, Ridge, Bayesian Ridge, Naive
|
|
| 46 |
|
| 47 |
TabFM is always represented in the leaderboard: it appears as skipped until **Run TabFM live** is enabled, then reports live metrics when the run completes.
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
Note: TabFM's weights use their own non-commercial license. Review the upstream model license before using this Space commercially.
|
| 50 |
|
| 51 |
Links:
|
|
|
|
| 46 |
|
| 47 |
TabFM is always represented in the leaderboard: it appears as skipped until **Run TabFM live** is enabled, then reports live metrics when the run completes.
|
| 48 |
|
| 49 |
+
## Operational notes
|
| 50 |
+
|
| 51 |
+
- The Space is pinned to Python 3.11 because TabFM's upstream package requires Python >= 3.11 and downloads weights from Hugging Face Hub.
|
| 52 |
+
- TabFM is loaded with the correct checkpoint for the selected task: `model_type="classification"` for classification and `model_type="regression"` for regression.
|
| 53 |
+
- Uploaded CSV runs coerce numeric regression targets, drop invalid target rows, and sanitize TabFM feature inputs before fitting.
|
| 54 |
+
- The first live TabFM run can take a couple of minutes on CPU Basic while the model dependency and weights are loaded; later runs are faster while the Space remains warm.
|
| 55 |
+
|
| 56 |
Note: TabFM's weights use their own non-commercial license. Review the upstream model license before using this Space commercially.
|
| 57 |
|
| 58 |
Links:
|