HumanChess 1450-1550 Blitz Checkmates is a human-move policy model trained from
scratch by imitation on Lichess blitz games where both players were rated
1450-1550. The dataset contains complete games ending in checkmate. This is a
policy-only network without search or a value head.
This archival release contains the epoch-4 FP32 PyTorch training checkpoint.
The INT8 version is intentionally not included because it underperformed the
1250-1350 INT8 model in direct matches. This model is published for continuity
of the rating-band series and is not the hosted serving model.
The checkpoint is approximately 525 MB because it includes optimizer state.
In a 30-game candidate round robin, epoch 4 ranked first among epochs 4, 5, 6,
and 8, scoring 55%. That small tournament is candidate-selection evidence, not
an absolute strength rating.
1human-chess-uci \
2 --checkpoint checkpoints/cnn-128x6-1450-1550-blitz-checkmates-epoch004.pt \
3 --device cpu
