Create README.md

README.md

@@ -0,0 +1,14 @@
+After the installation of FlashAttention2, the model can be loaded using:
+```python
+from scooby.modeling import Scooby
+flooby_neurips = Scooby.from_pretrained(
+    'johahi/flash-scooby-neurips',
+    cell_emb_dim=14,
+    embedding_dim=1920,
+    n_tracks=3,
+    return_center_bins_only=True,
+    disable_cache=False,
+    use_transform_borzoi_emb=False,
+)
+```
+Since the transform_borzoi_emb is not used, the models performance is slightly (0.52 vs 0.54 across cell types) worse than neurips-scooby.