Add v3 OOD checkpoints + README
Browse filesAdds tabpfn-v3-{classifier,regressor}-v3_ood.ckpt.
Built from the v3 release defaults (identical state_dict) with only PREPROCESS_TRANSFORMS swapped to OOD-robust recipes:
- classifier: squashing_scaler_max10 + none (200 features)
- regressor: quantile_uni_extrapolate + squashing_scaler_max10 (500 features)
All other inference_config fields inherited from the defaults unchanged. The regressor depends on the quantile_uni_extrapolate preset added in PriorLabs/TabPFN#971 (merged); a TabPFN release that contains that merge is required to load it.
- README.md +7 -7
- tabpfn-v3-classifier-v3_ood.ckpt +3 -0
- tabpfn-v3-regressor-v3_ood.ckpt +3 -0
README.md
CHANGED
|
@@ -26,7 +26,7 @@ tags:
|
|
| 26 |
### Model Overview
|
| 27 |
TabPFN-3 is a transformer-based foundation model that uses in-context-learning to solve tabular prediction problems in a forward pass.
|
| 28 |
Inference code can be found at [https://github.com/PriorLabs/TabPFN](https://github.com/PriorLabs/TabPFN).
|
| 29 |
-
More details can be found in the [Model Report](https://
|
| 30 |
|
| 31 |
### Getting started
|
| 32 |
First, install the inference package:
|
|
@@ -65,6 +65,8 @@ The following specialized checkpoints are available:
|
|
| 65 |
| [`tabpfn-v3-classifier-v3_20260417_multiclass.ckpt`](https://huggingface.co/Prior-Labs/tabpfn_3/blob/main/tabpfn-v3-classifier-v3_20260417_multiclass.ckpt) | Classification | Specialized for multiclass classification for datasets with <200k rows |
|
| 66 |
| [`tabpfn-v3-regressor-v3_20260417_mediumdata.ckpt`](https://huggingface.co/Prior-Labs/tabpfn_3/blob/main/tabpfn-v3-regressor-v3_20260417_mediumdata.ckpt) | Regression | Specialized for regression for datasets with <100k rows and with alternative preprocessing |
|
| 67 |
| [`tabpfn-v3-regressor-v3_20260506_timeseries.ckpt`](https://huggingface.co/Prior-Labs/tabpfn_3/blob/main/tabpfn-v3-regressor-v3_20260506_timeseries.ckpt) | Regression / Time-series forecasting | Fine-tuned on synthetic time-series data; used by default in TabPFN-TS-3 |
|
|
|
|
|
|
|
| 68 |
|
| 69 |
To use one of these checkpoints, pass its filename via `model_path`:
|
| 70 |
|
|
@@ -115,12 +117,10 @@ v1.0: initial release.
|
|
| 115 |
|
| 116 |
### Citation
|
| 117 |
```
|
| 118 |
-
@misc{
|
| 119 |
-
title={TabPFN-3
|
| 120 |
-
author={
|
| 121 |
year={2026},
|
| 122 |
-
|
| 123 |
-
archivePrefix={arXiv},
|
| 124 |
-
url={https://arxiv.org/abs/2605.13986},
|
| 125 |
}
|
| 126 |
```
|
|
|
|
| 26 |
### Model Overview
|
| 27 |
TabPFN-3 is a transformer-based foundation model that uses in-context-learning to solve tabular prediction problems in a forward pass.
|
| 28 |
Inference code can be found at [https://github.com/PriorLabs/TabPFN](https://github.com/PriorLabs/TabPFN).
|
| 29 |
+
More details can be found in the [Model Report](https://storage.googleapis.com/prior-labs-tabpfn-public/reports/TabPFN_3_model_report.pdf).
|
| 30 |
|
| 31 |
### Getting started
|
| 32 |
First, install the inference package:
|
|
|
|
| 65 |
| [`tabpfn-v3-classifier-v3_20260417_multiclass.ckpt`](https://huggingface.co/Prior-Labs/tabpfn_3/blob/main/tabpfn-v3-classifier-v3_20260417_multiclass.ckpt) | Classification | Specialized for multiclass classification for datasets with <200k rows |
|
| 66 |
| [`tabpfn-v3-regressor-v3_20260417_mediumdata.ckpt`](https://huggingface.co/Prior-Labs/tabpfn_3/blob/main/tabpfn-v3-regressor-v3_20260417_mediumdata.ckpt) | Regression | Specialized for regression for datasets with <100k rows and with alternative preprocessing |
|
| 67 |
| [`tabpfn-v3-regressor-v3_20260506_timeseries.ckpt`](https://huggingface.co/Prior-Labs/tabpfn_3/blob/main/tabpfn-v3-regressor-v3_20260506_timeseries.ckpt) | Regression / Time-series forecasting | Fine-tuned on synthetic time-series data; used by default in TabPFN-TS-3 |
|
| 68 |
+
| [`tabpfn-v3-classifier-v3_ood.ckpt`](https://huggingface.co/Prior-Labs/tabpfn_3/blob/main/tabpfn-v3-classifier-v3_ood.ckpt) | Classification | Same weights as the default classifier but with OOD-robust preprocessors bundled (`squashing_scaler_max10` + `none`). Useful when test inputs may fall outside the training distribution. |
|
| 69 |
+
| [`tabpfn-v3-regressor-v3_ood.ckpt`](https://huggingface.co/Prior-Labs/tabpfn_3/blob/main/tabpfn-v3-regressor-v3_ood.ckpt) | Regression | Same weights as the default regressor but with OOD-robust preprocessors bundled (`quantile_uni_extrapolate` + `squashing_scaler_max10`). Linearly extrapolates past the training range instead of clamping. Requires `tabpfn` from the public main branch (post-#971 merge). |
|
| 70 |
|
| 71 |
To use one of these checkpoints, pass its filename via `model_path`:
|
| 72 |
|
|
|
|
| 117 |
|
| 118 |
### Citation
|
| 119 |
```
|
| 120 |
+
@misc{TabPFN3,
|
| 121 |
+
title={TabPFN-3},
|
| 122 |
+
author={Prior Labs},
|
| 123 |
year={2026},
|
| 124 |
+
note={Coming soon}
|
|
|
|
|
|
|
| 125 |
}
|
| 126 |
```
|
tabpfn-v3-classifier-v3_ood.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f973d994ece09f9e28e9319d644bcff3cb0bec9c3170e67e14e71f53df92d18b
|
| 3 |
+
size 212815699
|
tabpfn-v3-regressor-v3_ood.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe1a5aa90cdd7f06e8736a68015b1bb570a413bd302de2d1038364272a8c24d6
|
| 3 |
+
size 233300137
|