| { | |
| "architectures": [ | |
| "ChessForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 1, | |
| "dropout": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "label_smoothing": 0.1, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "chess_trm", | |
| "n_ctx": 256, | |
| "n_embd": 192, | |
| "n_head": 4, | |
| "n_inner": 448, | |
| "n_layer": 2, | |
| "n_recursions": 4, | |
| "pad_token_id": 0, | |
| "rope_theta": 10000.0, | |
| "tie_weights": true, | |
| "transformers_version": "4.57.3", | |
| "use_rope": true, | |
| "vocab_size": 909 | |
| } | |