config.json

{
  "architectures": [
    "ChessForCausalLM"
  ],
  "attention_dropout": 0.1,
  "auxiliary_loss_weight": 0.1,
  "bos_token_id": 1,
  "dropout": 0.1,
  "dtype": "float32",
  "eos_token_id": 2,
  "halting_threshold": 0.9,
  "label_smoothing": 0.1,
  "latent_dim": 64,
  "layer_norm_epsilon": 1e-05,
  "model_type": "chess_transformer",
  "n_ctx": 256,
  "n_embd": 128,
  "n_head": 4,
  "n_inner": 298,
  "n_layer": 5,
  "n_recursions": 6,
  "pad_token_id": 0,
  "rope_theta": 10000.0,
  "tie_weights": true,
  "transformers_version": "4.57.3",
  "use_adaptive_depth": true,
  "use_rope": true,
  "vocab_size": 88,
  "auto_map": {
    "AutoConfig": "model1.ChessConfig",
    "AutoModelForCausalLM": "model1.ChessForCausalLM"
  }
}