Remove reference to source repo script

README.md

@@ -110,7 +110,7 @@ for score, idx in zip(top5.values, top5.indices):
 - The model has seen 47 % of the planned training budget (120K / 255K steps) — the loss is still decreasing.
 - It has no access to board state: all chess knowledge is inferred from move sequences.
 - No RLHF or self-play refinement — this is a pure next-token prediction model.
-- Predictions can include illegal moves; use `python-chess` to filter at inference time (see `scripts/generate.py` in the source repo).
+- Predictions can include illegal moves; use `python-chess` to filter at inference time.
 
 ## Citation