| { | |
| "dim": 5120, | |
| "n_layers": 40, | |
| "head_dim": 128, | |
| "hidden_dim": 32768, | |
| "n_heads": 32, | |
| "n_kv_heads": 8, | |
| "norm_eps": 1e-05, | |
| "vocab_size": 131072, | |
| "rope_theta": 100000000.0, | |
| "max_seq_len": 32768 | |
| } | |
| { | |
| "dim": 5120, | |
| "n_layers": 40, | |
| "head_dim": 128, | |
| "hidden_dim": 32768, | |
| "n_heads": 32, | |
| "n_kv_heads": 8, | |
| "norm_eps": 1e-05, | |
| "vocab_size": 131072, | |
| "rope_theta": 100000000.0, | |
| "max_seq_len": 32768 | |
| } | |