{ "vocab_size": 16384, "max_seq_len": 2048, "dim": 512, "n_layers": 8, "n_dense_layers": 2, "dense_hidden_dim": 1408, "norm_eps": 1e-06, "init_std": 0.02, "tie_embeddings": true, "n_heads": 8, "q_lora_rank": 256, "kv_lora_rank": 128, "qk_nope_head_dim": 64, "qk_rope_head_dim": 32, "v_head_dim": 64, "rope_theta": 10000.0, "rope_original_seq_len": 0, "rope_factor": 1.0, "rope_beta_fast": 32.0, "rope_beta_slow": 1.0, "rope_mscale": 1.0, "n_routed_experts": 240, "n_shared_experts": 2, "n_activated_experts": 8, "moe_hidden_dim": 128, "n_expert_groups": 8, "n_limited_groups": 4, "route_scale": 1.0, "bias_update_speed": 0.001, "seq_aux_loss_alpha": 0.0001, "moe_backend": "capacity", "capacity_factor": 2.0 }