Nebium
Causal Transformer for self-supervised next-move prediction on chess games.
Architecture
- d_model: 64
- n_heads: 4
- n_layers: 1
- vocab_size: 136
- max_seq_len: 128
- positional_encoding: rope
- activation: swiglu
- norm: rmsnorm
Last validation metrics
val/loss: 8.162410736083984val/accuracy: 0.10000000149011612val/top5_accuracy: 0.15000000596046448val/perplexity: 3506.629981726336
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support