Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+library_name: tedbench
+tags:
+  - protein
+  - structure
+  - fold-classification
+  - tedbench
+pipeline_tag: feature-extraction
+license: bsd-3-clause
+---
+
+# TEDBench — Pretrained autoencoder (structure only)
+
+**Variant:** `miae_l`  |  **Parameters:** 339M  |  **Layers:** 24  |  **Hidden dim:** 1024  |  **Attn heads:** 16
+
+This is a **pretrained MiAE** checkpoint. Use it as a feature extractor or as the starting point for fine-tuning.
+
+Part of the [TEDBench](https://github.com/BorgwardtLab/TEDBench) benchmark for
+protein fold classification (ICML 2026). MiAE is an SE(3)-invariant masked
+autoencoder that masks up to 90% of backbone frames and reconstructs the full
+structure with a lightweight decoder.
+
+## Architecture sizes
+
+| Variant | Params | Layers | Hidden dim | Attn heads |
+|---------|-------:|-------:|-----------:|-----------:|
+| `miae_s` | 29 M | 6 | 512 | 8 |
+| `miae_b` | 102 M | 12 | 768 | 12 |
+| `miae_l` | 339 M | 24 | 1 024 | 16 |
+
+Append `+model.use_seq_input=true` to `miae_b` for the **+seq** variant.
+
+## Usage
+
+### Load from the HuggingFace Hub
+
+```python
+from tedbench.utils.io import load_from_hf
+
+model = load_from_hf("TEDBench/miae-l")
+model.eval()
+```
+
+### From a Lightning checkpoint
+
+```python
+from tedbench.model import MiAE
+
+model = MiAE.load_from_checkpoint("model.ckpt", weights_only=False)
+model.eval()
+```
+
+## Citation
+
+```bibtex
+@inproceedings{chen2026tedbench,
+  title={Protein Fold Classification at Scale: Benchmarking and Pretraining},
+  author={Chen, Dexiong and Manolache, Andrei and Niepert, Mathias and Borgwardt, Karsten},
+  booktitle={Proceedings of the 43rd International Conference on Machine Learning},
+  year={2026}
+}
+```

config.json

@@ -0,0 +1,60 @@
+{
+  "seed": 42,
+  "debug": false,
+  "wandb": true,
+  "mask_ratio": 0.9,
+  "noise": 0.0,
+  "datamodule": {
+    "batch_size": 32,
+    "pin_memory": true,
+    "num_workers": 12,
+    "_target_": "tedbench.data.LightningStructureDataset",
+    "root": "./datasets/ted",
+    "dataset_name": "afdb_stream"
+  },
+  "trainer": {
+    "_target_": "pytorch_lightning.Trainer",
+    "accelerator": "auto",
+    "max_steps": 100000,
+    "strategy": "auto",
+    "devices": "auto",
+    "default_root_dir": "${logs.path}",
+    "num_sanity_val_steps": 0,
+    "val_check_interval": 1000,
+    "check_val_every_n_epoch": null,
+    "accumulate_grad_batches": 4,
+    "num_nodes": 4
+  },
+  "train": {
+    "optimizer": {
+      "_target_": "torch.optim.AdamW",
+      "lr": 0.0024,
+      "weight_decay": 0.05,
+      "betas": [
+        0.9,
+        0.95
+      ]
+    },
+    "lr_scheduler": {
+      "_target_": "tedbench.lr_schedulers.get_cosine_schedule_with_warmup",
+      "warmup_steps": 5000,
+      "max_steps": "${eval:0.99 * ${trainer.max_steps}}",
+      "min_factor": 0.1
+    },
+    "ckpt_path": null,
+    "compile": false
+  },
+  "model": {
+    "_target_": "tedbench.model.miae_model",
+    "name": "miae_l",
+    "use_seq_input": false,
+    "masking_strategy": "fixed",
+    "use_inverse_folding_loss": true
+  },
+  "logs": {
+    "prefix": "logs/pretrain/${datamodule.dataset_name}/${seed}",
+    "path": "${logs.prefix}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}"
+  },
+  "mode": {},
+  "_model_class": "miae"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45395b639fe4e7743d5e48244d8ed3a63f82b6054d02cf528b6bd77f6697ecc5
+size 1385553415