| { | |
| "dim": 6144, | |
| "n_layers": 56, | |
| "head_dim": 128, | |
| "hidden_dim": 16384, | |
| "n_heads": 48, | |
| "n_kv_heads": 8, | |
| "rope_theta": 1000000, | |
| "norm_eps": 1e-05, | |
| "vocab_size": 32000, | |
| "moe": { | |
| "num_experts": 8, | |
| "num_experts_per_tok": 2 | |
| }, | |
| "max_seq_len": 65536 | |
| } | |
| { | |
| "dim": 6144, | |
| "n_layers": 56, | |
| "head_dim": 128, | |
| "hidden_dim": 16384, | |
| "n_heads": 48, | |
| "n_kv_heads": 8, | |
| "rope_theta": 1000000, | |
| "norm_eps": 1e-05, | |
| "vocab_size": 32000, | |
| "moe": { | |
| "num_experts": 8, | |
| "num_experts_per_tok": 2 | |
| }, | |
| "max_seq_len": 65536 | |
| } | |