Update README.md

README.md

@@ -18,15 +18,23 @@ results:
 ---
 # Model Card for gpt2-stockfish-debug
 
-## Details
+## Training Details
 
-Simple completion tuning using an equivalent of:
+The model was trained during 1 epoch on the `Xmaster6y/stockfish-debug` dataset (no hyperparameter tuning done). The samples are:
 
 ```json
 {"prompt":"FEN: {fen}\nMOVE:", "completion": " {move}"}
 ```
 
-## Use
+Two possible simple extensions:
+
+- Expand the FEN string: `r2qk3/...` -> `r11qk111/...` or equivalent
+- Condition with the result (ELO not available in the dataset):
+```json
+{"prompt":"RES: {res}\nFEN: {fen}\nMOVE:", "completion": " {move}"}
+```
+
+## Use the Model
 
 ```python
 import chess