| {"dim": 4096, "n_layers": 32, "head_dim": 128, "hidden_dim": 14336, "n_heads": 32, "n_kv_heads": 8, "norm_eps": 1e-05, "vocab_size": 32000, "moe": {"num_experts_per_tok": 2, "num_experts": 8}} | |
| {"dim": 4096, "n_layers": 32, "head_dim": 128, "hidden_dim": 14336, "n_heads": 32, "n_kv_heads": 8, "norm_eps": 1e-05, "vocab_size": 32000, "moe": {"num_experts_per_tok": 2, "num_experts": 8}} | |