| { | |
| "_name_or_path": "my_model_gpu_full/final_model", | |
| "architectures": [ | |
| "ChessForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "model.ChessConfig", | |
| "AutoModelForCausalLM": "model.ChessForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "dropout": 0.05, | |
| "eos_token_id": 2, | |
| "layer_norm_epsilon": 1e-06, | |
| "mlp_type": "swiglu", | |
| "model_type": "chess_transformer", | |
| "n_ctx": 256, | |
| "n_embd": 128, | |
| "n_head": 8, | |
| "n_inner": 248, | |
| "n_layer": 6, | |
| "pad_token_id": 0, | |
| "rope_theta": 10000.0, | |
| "tie_weights": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.39.3", | |
| "use_rmsnorm": true, | |
| "use_rope": true, | |
| "vocab_size": 148 | |
| } | |