Add model card and license

LICENSE

@@ -0,0 +1,28 @@
+TabFM Non-Commercial License v1.0
+
+Google LLC ("we" or "our" or "Company") is pleased to make available the weights, parameters and inference code for the TabFM Model (as defined below) freely available for your non-commercial and non-production use as set forth in this TabFM Non-Commercial License ("License"). The "TabFM Model" means the TabFM AI models and models denoted as TabFM and their elements which includes algorithms, software, checkpoints, parameters, source code (inference code, evaluation code, and if applicable, fine-tuning code) and any other materials associated with the TabFM AI models made available by Company under this License, including, if any, the technical documentation, manuals and instructions for the use and operation thereof (collectively, "TabFM Model"). Note that we may also make available certain elements of what is included in the definition of "TabFM Model" under a separate license and nothing in this License will be deemed to restrict or limit any other licenses granted by us in such elements.
+
+By downloading, accessing, using, Distributing (as defined below), or creating a Derivative (as defined below) of the TabFM Model, you agree to be bound by the terms of this License. If you do not agree to this License, then you do not have any rights to access, use or create a Derivative of the TabFM Model and you must immediately cease using the TabFM Model. If you are agreeing to be bound by the terms of this License on behalf of your employer or other entity, you represent and warrant to us that you have full legal authority to bind your employer or such entity to this License. If you do not have the requisite authority, you may not accept the License or access the TabFM Model on behalf of your employer or other entity.
+
+This License applies only to individuals or entities who download the TabFM Model. For customers accessing the TabFM Model through our API, other terms and conditions may apply.
+1. Definitions
+a. "Derivative" means any (i) modified version of the TabFM Model (including but not limited to any customized, fine-tuned, retrained, or otherwise adapted version thereof); (ii) work that incorporates, utilizes, or is otherwise based on or derived from the TabFM Model, its logic, or parameters; or (iii) any other derivative work thereof, in each case whether or not such work constitutes a derivative work under applicable copyright law. For the avoidance of doubt, Outputs are not considered Derivatives under this License.
+b. "Distribution," "Distribute," or "Distributing" means providing or making available, by any means, a copy of the TabFM Model and/or the Derivatives as the case may be.
+c. "Non-Commercial Purpose" means use for testing, evaluation, or research not tied to commercial gain, production deployment, or revenue generation. This includes internal benchmarking, academic research, and experimentation on private or public datasets, provided the results are not used in commercial decision-making, client deliverables, or paid products/services. For clarity, use (a) for any revenue-generating activity, (b) in direct or indirect interactions with end users or production systems, or (c) to train, fine-tune, or distill other models for commercial use, in each case is not a Non-Commercial Purpose.
+d. "Outputs" means predictions, scores, probabilities, recommendations, explanations, or other results generated by operation of the TabFM Model or any Derivative from datasets or other inputs supplied by a user. For the avoidance of doubt, Outputs do not include any components of the TabFM Model, such as any fine-tuned versions of the TabFM Model, the weights, or parameters.
+e. "you" or "your" means the individual or entity entering into this License with Company.
+2. License Grant
+a. License. Subject to your compliance with this License, Company grants you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty-free and limited license to access, use and create Derivatives of the TabFM Model solely for your Non-Commercial Purposes. The foregoing license is personal to you, and you may not assign or sublicense this License or any other rights or obligations under this License without Company's prior written consent; any such assignment or sublicense will be void and will automatically and immediately terminate this License. Any restrictions set forth herein regarding the TabFM Model also apply to any Derivative you create or that are created on your behalf. 
+b. Non-Commercial Use Only. You may only access, use, or create Derivatives of the TabFM Model for Non-Commercial Purposes. If you want to use the TabFM Model or a Derivative for any purpose that is not expressly authorized under this License, such as for a commercial or production activity, you must obtain a commercial license from Company, which Company may grant in its sole discretion and which additional use may be subject to a fee, royalty or other revenue share.
+c. Reserved Rights. The grant of rights expressly set forth in this License are the complete grant of rights to you in the TabFM Model, and no other licenses are granted, whether by waiver, estoppel, implication, equity or otherwise. Company and its licensors reserve all rights not expressly granted by this License.
+d. Compliance and Safeguards. You must ensure that any use of the TabFM Model, Derivatives, and Outputs complies with applicable data protection, privacy, export control, and AI regulations (including, where applicable, GDPR and the EU Artificial Intelligence Act), and that you implement reasonable technical and organizational measures appropriate to the data and risks involved.
+3. Restrictions
+You will not, and will not permit, assist or cause any third party to:
+a. use, modify, copy, reproduce, create Derivatives of, or Distribute the TabFM Model (or any Derivative thereof, or any Outputs and data produced by the TabFM Model), in whole or in part for any commercial or production purposes; or
+b. Distribute the TabFM Model or a Derivative.
+4. Disclaimer of Warranties
+THE TABFM MODEL IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NON-INFRINGEMENT. IN NO EVENT WILL COMPANY BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT, OR OTHERWISE, ARISING FROM, OUT OF, OR IN CONNECTION WITH THE TABFM MODEL OR THE USE OR OTHER DEALINGS IN THE TABFM MODEL.
+5. Limitation of Liability
+TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT WILL COMPANY BE LIABLE FOR ANY SPECIAL, INCIDENTAL, INDIRECT, OR CONSEQUENTIAL DAMAGES WHATSOEVER (INCLUDING, WITHOUT LIMITATION, DAMAGES FOR LOSS OF BUSINESS PROFITS, BUSINESS INTERRUPTION, LOSS OF BUSINESS INFORMATION, OR ANY OTHER PECUNIARY LOSS) ARISING OUT OF THE USE OF OR INABILITY TO USE THE TABFM MODEL, EVEN IF YOU HAVE BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+6. Trademarks
+You have not been granted any trademark license as part of this License and may not use any name, logo or trademark associated with Company without the prior written permission of Company.

README.md

@@ -0,0 +1,169 @@
+---
+license: other
+license_name: tabfm-non-commercial-v1.0
+license_link: https://huggingface.co/google/tabfm-1.1.0-pytorch/blob/main/LICENSE
+library_name: tabfm
+pipeline_tag: tabular-classification
+tags:
+- tabular
+- tabular-regression
+- zero-shot
+- in-context-learning
+- pytorch
+- foundation-model
+---
+
+# TabFM 1.1.0 (PyTorch)
+
+TabFM is a zero-shot tabular foundation model from Google Research. It supports
+classification and regression on structured/tabular data with mixed numerical and
+categorical columns, requiring no fine-tuning or hyperparameter search - training
+examples are passed as context and predictions are made in a single forward pass.
+
+This repository contains the **PyTorch** weights. For the JAX/Flax weights see
+[google/tabfm-1.1.0-jax](https://huggingface.co/google/tabfm-1.1.0-jax).
+
+## Getting Started
+
+```bash
+pip install tabfm[pytorch]
+```
+
+**Classification:**
+
+```python
+from tabfm import TabFMClassifier, tabfm_v1_1_0_pytorch as tabfm_v1_1_0
+
+model = tabfm_v1_1_0.load(model_type="classification")
+clf = TabFMClassifier(model=model)
+clf.fit(X_train, y_train)
+probs = clf.predict_proba(X_test)
+```
+
+**Regression:**
+
+```python
+from tabfm import TabFMRegressor, tabfm_v1_1_0_pytorch as tabfm_v1_1_0
+
+model = tabfm_v1_1_0.load(model_type="regression")
+reg = TabFMRegressor(model=model)
+reg.fit(X_train, y_train)
+preds = reg.predict(X_test)
+```
+
+You can also load directly using the HuggingFace Hub API:
+
+```python
+from tabfm.src.pytorch.tabfm_v1_1_0 import TabFM_HF
+
+clf_model = TabFM_HF.from_pretrained("google/tabfm-1.1.0-pytorch", subfolder="classification")
+reg_model = TabFM_HF.from_pretrained("google/tabfm-1.1.0-pytorch", subfolder="regression")
+```
+
+### Available Checkpoints
+
+| Subfolder | Task | `is_classifier` |
+|-----------|------|-----------------|
+| `classification/` | Classification (up to 10 classes) | `True` |
+| `regression/` | Regression | `False` |
+
+## Developers and Affiliations
+
+Developed by the [Google Research](https://research.google) team.
+
+## Intended Use
+
+- Tabular data with numerical and/or categorical columns
+- Binary and multiclass classification (up to 10 classes)
+- Regression on continuous targets
+- Zero-shot inference: no dataset-specific training or hyperparameter tuning
+- Works with DataFrames (pandas) or numpy arrays
+
+## Not Intended For
+
+- Images, audio, video, or raw text
+- More than 10 output classes (hard model limit)
+- Tasks requiring task-specific fine-tuning
+- Non-tabular structured data (graphs, sequences)
+- Commercial use (see License below)
+
+## Model Architecture
+
+TabFM uses alternating row and column attention to capture both feature interactions
+and row-level patterns:
+
+1. **Column attention** (Set Transformer): embeds each cell using Fourier features and
+   a per-group linear projection, then aggregates across rows via induced self-attention
+2. **Row compression**: CLS tokens summarise each row into a dense vector via row-level
+   attention with Rotary Position Embedding (RoPE)
+3. **ICL Transformer**: a 24-block causal transformer operates over the compressed row
+   vectors, treating training rows as context and outputting predictions for test rows
+
+Key hyperparameters:
+
+| Parameter | Value |
+|-----------|-------|
+| Embedding dim | 256 |
+| Column attention blocks | 3 (4 heads, 256 induced points) |
+| Row attention blocks | 3 (8 heads, 8 CLS tokens) |
+| ICL transformer blocks | 24 (8 heads) |
+| Feed-forward factor | 4 |
+| Max classes | 10 |
+| Activation | SwiGLU |
+| Fourier features | 32 frequencies |
+
+## Training Data and Priors
+
+TabFM was trained on hundreds of millions of **synthetic** datasets generated
+dynamically using structural causal models (SCMs). Synthetic data was chosen due to
+the scarcity of diverse, high-quality open-source tabular datasets and to avoid
+privacy/licensing concerns with real-world industrial data. The SCM prior encodes
+inductive biases about causal structure and feature relationships typical in tabular
+tasks.
+
+## Performance
+
+TabFM was evaluated on [TabArena](https://tabarena.ai) across 51 datasets
+(38 classification, 13 regression). In zero-shot mode - a single forward pass with no
+hyperparameter search - TabFM outperforms heavily-tuned supervised baselines including
+gradient-boosted trees. The `TabFMClassifier.ensemble()` preset (feature crosses,
+SVD features, NNLS blending) yields further improvements.
+
+See the [Google Research blog post](https://research.google/blog/introducing-tabfm-a-zero-shot-foundation-model-for-tabular-data/) for full benchmark details.
+
+## Ethical Considerations
+
+TabFM was trained entirely on synthetic data. Performance on specific real-world
+domains, minority groups, or edge distributions is not fully characterised. Users
+should evaluate the model on held-out data representative of their use case before
+deploying in high-stakes settings.
+
+## Limitations
+
+- **Max 10 classes** for classification (hard architectural limit)
+- Memory usage scales with the number of training rows (all rows are passed as context)
+- Optimised for tables up to 500 features; behaviour on very wide tables may degrade
+- Performance is not guaranteed to match task-specific, fine-tuned models on all datasets
+- Not an officially supported Google product
+
+## License
+
+The model weights in this repository are released under the
+**TabFM Non-Commercial License v1.0** - see [LICENSE](https://huggingface.co/google/tabfm-1.1.0-pytorch/blob/main/LICENSE). The source code is
+Apache 2.0 licensed via [google-research/tabfm](https://github.com/google-research/tabfm).
+
+## Version
+
+1.1.0
+
+## Citation
+
+```bibtex
+@article{tabfm2026,
+  title  = {TabFM: A Zero-Shot Foundation Model for Tabular Data},
+  author = {Google Research},
+  year   = {2026},
+  url    = {https://research.google/blog/introducing-tabfm-a-zero-shot-foundation-model-for-tabular-data/}
+}
+```
+