Merge branch 'main' of https://huggingface.co/Prior-Labs/tabpfn_3
Browse files- README.md +2 -1
- config.json +3 -0
- tabpfn-v3-classifier-20260506.ckpt → tabpfn-v3-classifier-v3_20260417_binary.ckpt +1 -1
- tabpfn-v3-classifier-v3_20260417_multiclass.ckpt +3 -0
- tabpfn-v3-classifier-v3_default.ckpt +3 -0
- tabpfn-v3-regressor-20260506.ckpt → tabpfn-v3-regressor-v3_20260417_mediumdata.ckpt +1 -1
- tabpfn-v3-regressor-v3_20260506_timeseries.ckpt +3 -0
- tabpfn-v3-regressor-v3_default.ckpt +3 -0
README.md
CHANGED
|
@@ -26,6 +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 |
|
| 30 |
### Getting started
|
| 31 |
First, install the inference package:
|
|
@@ -91,7 +92,7 @@ TabPFN-3 is trained purely on synthetic tabular tasks.
|
|
| 91 |
|
| 92 |
### Performance Benchmarks
|
| 93 |
Evaluated on public benchmarks such as TabArena and TALENT, the model yields SOTA results.
|
| 94 |
-
On proprietary benchmark collections, it yields SOTA results for <100k
|
| 95 |
|
| 96 |
|
| 97 |
### Ethical Considerations
|
|
|
|
| 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:
|
|
|
|
| 92 |
|
| 93 |
### Performance Benchmarks
|
| 94 |
Evaluated on public benchmarks such as TabArena and TALENT, the model yields SOTA results.
|
| 95 |
+
On proprietary benchmark collections, it yields SOTA results for datasets with <100k rows and datasets with 100k-1M rows and <200 features.
|
| 96 |
|
| 97 |
|
| 98 |
### Ethical Considerations
|
config.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "TabPFN-v3"
|
| 3 |
+
}
|
tabpfn-v3-classifier-20260506.ckpt → tabpfn-v3-classifier-v3_20260417_binary.ckpt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 212804803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f9949fd52e20b6ed8ece20b3b37242d2abbbf337d14b461a4244f9318031a88
|
| 3 |
size 212804803
|
tabpfn-v3-classifier-v3_20260417_multiclass.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:517c40ca21e0e1b1fa6629ded4b0412ffb7b2e577eb6cb96e5be5c487fadfb03
|
| 3 |
+
size 212804803
|
tabpfn-v3-classifier-v3_default.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0d865d54dfbc524f5703104be90620182dca7e5fb2c16de72e9959ea18f3988
|
| 3 |
+
size 212804803
|
tabpfn-v3-regressor-20260506.ckpt → tabpfn-v3-regressor-v3_20260417_mediumdata.ckpt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 233289807
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06a1daeebbc19f8d9478bd6fdf8753859c68abc9abfe53e8216b1067b7e0bc21
|
| 3 |
size 233289807
|
tabpfn-v3-regressor-v3_20260506_timeseries.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48ca82019fec74f08e15d56a157bbe728d6ec25c221f2ff2d4fd22fd4e09ec6e
|
| 3 |
+
size 233289807
|
tabpfn-v3-regressor-v3_default.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:311ce18d97e9533d8585eaadafe040fbdd8070533209ed8696641dadc97a7301
|
| 3 |
+
size 233289807
|