Chess GPT-2 124M
Fine-tuned GPT-2 (124M parameters) for chess move prediction.
Training Details
- Base model: gpt2 (124M parameters)
- Dataset: Lichess/chess-position-evaluations (Stockfish depth≥20)
- Training examples: 490,000
- Epochs: 2
- Batch size: 16
- Learning rate: 5e-05
- Max sequence length: 80
- Format:
FEN: <fen_string> MOVE: <uci_move>
Usage
The model predicts the best UCI move given a FEN position. Use with constrained decoding (lm-format-enforcer) for 100% legal move rate.
Inference
prompt = "FEN: rnbqkbnr/pppppppp/8/8/8/8/PPPPPPPP/RNBQKBNR w KQkq - 0 1 MOVE: "
- Downloads last month
- 88
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support