Mitra-v2 classifier weights and model card

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+pipeline_tag: tabular-classification
+---
+
+# Mitra-v2 Classifier
+
+Mitra-v2 classifier is a tabular foundation model that is pre-trained on purely synthetic datasets sampled from a mix of random classifiers, including the new Hybrid SCM prior. It is the second generation of the Mitra classifier ([autogluon/mitra-classifier](https://huggingface.co/autogluon/mitra-classifier)), pre-trained with a 10x longer context, three times as many features, and an improved optimizer. On the TabArena and TALENT benchmarks it delivers state-of-the-art accuracy at the level of TabFM and EXAONE Tabular, while surpassing TabPFN-3 by a wide margin. The regression model is at [autogluon/mitra-regressor-2](https://huggingface.co/autogluon/mitra-regressor-2), and the inference and fine-tuning code with our evaluation results is at [autogluon/mitra-finetune](https://huggingface.co/autogluon/mitra-finetune).
+
+## Architecture
+
+Mitra-v2 is based on a 12-layer 2D Transformer of 75.7 M parameters (attention across rows and across columns), pre-trained by incorporating an in-context learning paradigm. The architecture is unchanged from Mitra-v1; the gains come from the scaled-up synthetic pre-training distribution and the optimizer.
+
+## Usage
+
+To use Mitra-v2 classifier, install AutoGluon and the `mitra-finetune` package by running:
+
+```sh
+pip install uv
+uv pip install "autogluon.tabular[mitra]>=1.6" "tabarena>=0.1.0"
+uv pip install git+https://huggingface.co/autogluon/mitra-finetune
+```
+
+A minimal example showing how to fine-tune and predict with the Mitra-v2 classifier using the same recipe as our reported results (50-step fine-tuning with 8-fold bagging). The recipe fine-tunes and bags eight copies of the model and requires a CUDA GPU; each `predict_proba` or `predict` call runs one bagged fine-tune:
+
+```python
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.datasets import load_wine
+from huggingface_hub import snapshot_download
+from mitra_finetune import MitraFinetune
+
+# Load dataset
+wine_data = load_wine()
+X = pd.DataFrame(wine_data.data, columns=wine_data.feature_names)
+y = pd.Series(wine_data.target, name="target")
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
+
+# Download the Mitra-v2 classifier weights
+ckpt_dir = snapshot_download("autogluon/mitra-classifier-2")
+
+# Fine-tune and predict
+model = MitraFinetune(checkpoint_dir=ckpt_dir, problem_type="classification")
+model.fit(X_train, y_train)
+proba = model.predict_proba(X_test)
+pred = proba.argmax(axis=1)
+print("Accuracy:", (pred == y_test.values).mean())
+```
+
+A minimal example showing how to perform inference with the Mitra-v2 classifier directly in AutoGluon (the weights are a drop-in replacement for the Mitra-v1 classifier):
+
+```python
+from autogluon.tabular import TabularDataset, TabularPredictor
+
+train_data = TabularDataset(pd.concat([X_train, y_train], axis=1))
+test_data = TabularDataset(pd.concat([X_test, y_test], axis=1))
+
+mitra_predictor = TabularPredictor(label="target")
+mitra_predictor.fit(
+    train_data,
+    hyperparameters={
+        "MITRA": {"hf_model": "autogluon/mitra-classifier-2", "fine_tune": False}
+    },
+)
+
+mitra_predictor.leaderboard(test_data)
+```
+
+Set `"fine_tune": True` to fine-tune inside AutoGluon. Note that AutoGluon's stock defaults differ from the `mitra-finetune` recipe used for the reported benchmark numbers.
+
+## License
+
+This project is licensed under the Apache-2.0 License.
+
+## Reference
+
+Mitra-v2 Technical Report (Amazon, 2026). The arXiv link will be added once the report is public.
+
+```
+@article{zhang2025mitra,
+  title={Mitra: Mixed synthetic priors for enhancing tabular foundation models},
+  author={Zhang, Xiyuan and Maddix, Danielle C and Yin, Junming and Erickson, Nick and Ansari, Abdul Fatir and Han, Boran and Zhang, Shuai and Akoglu, Leman and Faloutsos, Christos and Mahoney, Michael W and others},
+  journal={arXiv preprint arXiv:2510.21204},
+  year={2025}
+}
+```
+
+Amazon Science blog: [Mitra: Mixed synthetic priors for enhancing tabular foundation models](https://www.amazon.science/blog/mitra-mixed-synthetic-priors-for-enhancing-tabular-foundation-models)

config.json

@@ -0,0 +1 @@
+{"dim": 512, "dim_output": 10, "n_layers": 12, "n_heads": 4, "task": "CLASSIFICATION"}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ffab0e2cf52f61c5b7c7eb1e8542996736d1023a0212190cc09abc2119a1e09
+size 302717904