| { | |
| "model_type": "caca", | |
| "model_name": "Caca-Tiny", | |
| "version": "1.0.0", | |
| "vocab_size": 8000, | |
| "embedding_dim": 256, | |
| "num_layers": 4, | |
| "num_heads": 4, | |
| "ffn_hidden_dim": 512, | |
| "max_seq_length": 512, | |
| "dropout": 0.1, | |
| "head_dim": 64 | |
| } |
| { | |
| "model_type": "caca", | |
| "model_name": "Caca-Tiny", | |
| "version": "1.0.0", | |
| "vocab_size": 8000, | |
| "embedding_dim": 256, | |
| "num_layers": 4, | |
| "num_heads": 4, | |
| "ffn_hidden_dim": 512, | |
| "max_seq_length": 512, | |
| "dropout": 0.1, | |
| "head_dim": 64 | |
| } |