Update README.md

README.md

@@ -7,4 +7,10 @@ sdk: gradio
 pinned: false
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+# Leela Chess Zero
+
+All transformer models here are "Chessformers" — encoder-only transformers with the Geometric Attention Bias described in the paper *Chessformer: A Unified Architecture for Chess Modeling*.
+
+They are written in the internal Lc0 format, which is compatible with the training code and the engine. They can be converted to ONNX through the `leela2onnx` command in releases of the Lc0 engine.
+
+**BT4** is our largest model at 190M and corresponds to Leela-CF. BT4 and BT3 were trained with SFT on a prior RL run, and the T1 models were distilled from a larger transformer.