{
  "architectures": [
    "LagunaForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_laguna.LagunaConfig",
    "AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM"
  },
  "model_type": "laguna",
  "vocab_size": 100352,
  "hidden_size": 3072,
  "intermediate_size": 12288,
  "num_hidden_layers": 48,
  "num_attention_heads": 48,
  "num_key_value_heads": 8,
  "head_dim": 128,
  "max_position_embeddings": 1048576,
  "attention_bias": false,
  "attention_dropout": 0.0,
  "rms_norm_eps": 1e-06,
  "num_experts": 256,
  "num_experts_per_tok": 10,
  "moe_intermediate_size": 1024,
  "shared_expert_intermediate_size": 1024,
  "norm_topk_prob": true,
  "router_aux_loss_coef": 0.0,
  "decoder_sparse_step": 1,
  "mlp_only_layers": [
    0
  ],
  "bos_token_id": 2,
  "eos_token_id": [
    2,
    24
  ],
  "pad_token_id": 9,
  "tie_word_embeddings": false,
  "use_cache": true,
  "torch_dtype": "bfloat16",
  "gating": "per-head",
  "sliding_window": 512,
  "rope_parameters": {
    "full_attention": {
      "rope_theta": 500000.0,
      "rope_type": "yarn",
      "factor": 128.0,
      "original_max_position_embeddings": 8192,
      "beta_slow": 1.0,
      "beta_fast": 32.0,
      "attention_factor": 1.4852030263919618,
      "partial_rotary_factor": 0.5
    },
    "sliding_attention": {
      "rope_type": "default",
      "rope_theta": 10000.0,
      "partial_rotary_factor": 1.0
    }
  },
  "layer_types": [
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention"
  ],
  "moe_apply_router_weight_on_input": false,
  "mlp_layer_types": [
    "dense",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse"
  ],
  "gating_types": [
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head",
    "per_head"
  ],
  "moe_routed_scaling_factor": 2.5,
  "num_attention_heads_per_layer": [
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72,
    48,
    72,
    72,
    72
  ],
  "moe_router_logit_softcapping": 0.0
}