Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+library_name: tedbench
+tags:
+  - protein
+  - structure-sequence
+  - fold-classification
+  - tedbench
+  - saprot
+pipeline_tag: other
+license: bsd-3-clause
+---
+
+# TEDBench — SaProt-650M fine-tuned on TEDBench
+
+Backbone: SaProt-650M (33 layers, hidden dim 1280). Requires [Foldseek](https://github.com/steineggerlab/foldseek) for structure-aware tokens.
+
+Fine-tuned on [TEDBench](https://github.com/BorgwardtLab/TEDBench) for protein
+fold classification into 965 CATH topology (T-level) classes (ICML 2026).
+
+## Usage
+
+```python
+import sys
+sys.path.insert(0, "baselines")  # from repo root
+
+from pathlib import Path
+import torch
+from models.saprot_classifier import SaProtClassifier
+from omegaconf import OmegaConf
+from huggingface_hub import snapshot_download
+
+local_dir = Path(snapshot_download("TEDBench/saprot-650M-ft"))
+with open(local_dir / "config.json") as f:
+    import json
+    cfg = OmegaConf.create(json.load(f))
+
+model = SaProtClassifier(cfg)
+sd = torch.load(local_dir / "pytorch_model.bin", map_location="cpu", weights_only=False)
+model.load_state_dict(sd)
+model.eval()
+```
+
+Or pass the repo ID directly to the test script:
+
+```bash
+python baselines/saprot_test_ted.py train.ckpt_path=TEDBench/saprot-650M-ft
+```
+
+## 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 +1,56 @@
+{
+  "seed": 42,
+  "wandb": true,
+  "truncation_seq_length": 512,
+  "batch_size": 16,
+  "foldseek_path": "/fs/gpfs41/lv11/fileset01/pool/pool-chen/softwares/micromamba/envs/foldseek/bin/foldseek",
+  "datamodule": {
+    "batch_size": 64,
+    "num_workers": 32,
+    "_target_": "foldmae.data.TEDLightningDataset",
+    "root": "./datasets/afdb_FS_plddt80",
+    "dataset_name": "ted"
+  },
+  "trainer": {
+    "_target_": "pytorch_lightning.Trainer",
+    "accelerator": "auto",
+    "max_steps": 18300,
+    "strategy": "ddp_find_unused_parameters_true",
+    "devices": "auto",
+    "default_root_dir": "${logs.path}",
+    "num_sanity_val_steps": 0,
+    "accumulate_grad_batches": 16
+  },
+  "model": {
+    "name": "SaProt_650M_AF2",
+    "path": "cache/torch/hub/checkpoints/${model.name}",
+    "num_classes": 965,
+    "avg_pool": false
+  },
+  "train": {
+    "optimizer": {
+      "_target_": "torch.optim.AdamW",
+      "lr": 0.0016,
+      "weight_decay": 0.1,
+      "betas": [
+        0.9,
+        0.95
+      ]
+    },
+    "lr_scheduler": {
+      "_target_": "foldmae.lr_schedulers.get_cosine_schedule_with_warmup",
+      "warmup_steps": 1830,
+      "max_steps": "${trainer.max_steps}"
+    },
+    "loss": {
+      "_target_": "torch.nn.CrossEntropyLoss"
+    },
+    "llrd": 0.8,
+    "ckpt_path": "logs/saprot/finetune/ted/42/runs/2026-01-20_22-15-11/model.ckpt"
+  },
+  "logs": {
+    "prefix": "logs/saprot/finetune/${datamodule.dataset_name}/${seed}",
+    "path": "${logs.prefix}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}"
+  },
+  "_model_class": "saprot"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c509e8549d7c01d950ae99a1637c92b43ae2e98a2937a68131203e500ff07b1d
+size 2611440279