Add model weights

Checkpoint: 231024222007-famous-alligator/checkpoints/ckpt-0999.pt

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,31 @@
 ---
 license: cc-by-nc-4.0
 ---
+
+# Model card for `boldgpt_small_patch10.cont`
+
+A Vision Transformer (ViT) model trained on BOLD activation maps from [NSD-Flat](https://huggingface.co/datasets/clane9/NSD-Flat). The training objective was to auto-regressively predict the next patch with shuffled patch order and MSE loss. This model was trained using `shared1000` as the held out validation set.
+
+## Dependencies
+
+- [boldGPT](https://github.com/clane9/boldGPT)
+
+## Usage
+
+```python
+from boldgpt.data import ActivityTransform
+from boldgpt.models import create_model
+from datasets import load_dataset
+
+model = create_model("boldgpt_small_patch10.cont", pretrained=True)
+
+dataset = load_dataset("clane9/NSD-Flat", split="train")
+dataset.set_format("torch")
+
+transform = ActivityTransform()
+batch = dataset[:1]
+batch["activity"] = transform(batch["activity"])
+
+# output: (B, N + 1, D) predicted next patches
+output, state = model(batch)
+```

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2358e17ce3e0266e1167ad359659702dd7dd3068f3fabe67523370830c9984
+size 87874460