| { | |
| "model_type": "aetherstory", | |
| "architectures": [ | |
| "AetherStoryModel" | |
| ], | |
| "library_name": "custom", | |
| "language": "en", | |
| "license": "mit", | |
| "tags": [ | |
| "from-scratch", | |
| "storytelling", | |
| "cpu-trained", | |
| "transformer" | |
| ], | |
| "vocab_size": 516, | |
| "d_model": 128, | |
| "n_layers": 4, | |
| "n_heads": 4, | |
| "ffn_dim": 512, | |
| "max_seq_len": 64, | |
| "dropout": 0.1, | |
| "tie_embeddings": true, | |
| "pad_token_id": 0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "unk_token_id": 3, | |
| "total_parameters": 863492 | |
| } |