{
  "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": 262144,
  "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,
  "moe_router_logit_softcapping": 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": 32.0,
      "original_max_position_embeddings": 8192,
      "beta_slow": 1.0,
      "beta_fast": 32.0,
      "attention_factor": 1.3465735902799727,
      "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
  ],
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "nvfp4-pack-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": "local",
          "group_size": 16,
          "num_bits": 4,
          "observer": "static_minmax",
          "observer_kwargs": {},
          "scale_dtype": "torch.float8_e4m3fn",
          "strategy": "tensor_group",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        },
        "output_activations": null,
        "targets": [
          "re:.*experts\\.[0-9]+\\.(gate_proj|up_proj|down_proj)$"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 16,
          "num_bits": 4,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": "torch.float8_e4m3fn",
          "strategy": "tensor_group",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      }
    },
    "format": "nvfp4-pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head",
      "re:.*\\.self_attn\\.q_proj$",
      "re:.*\\.self_attn\\.k_proj$",
      "re:.*\\.self_attn\\.v_proj$",
      "re:.*\\.self_attn\\.o_proj$",
      "re:.*\\.self_attn\\.g_proj$",
      "re:.*\\.mlp\\.gate$",
      "model.layers.0.mlp.gate_proj",
      "model.layers.0.mlp.up_proj",
      "model.layers.0.mlp.down_proj",
      "re:.*\\.mlp\\.shared_expert\\.gate_proj$",
      "re:.*\\.mlp\\.shared_expert\\.up_proj$",
      "re:.*\\.mlp\\.shared_expert\\.down_proj$"
    ],
    "kv_cache_scheme": {
      "actorder": null,
      "block_structure": null,
      "dynamic": false,
      "group_size": null,
      "num_bits": 8,
      "observer": "minmax",
      "observer_kwargs": {},
      "scale_dtype": null,
      "strategy": "tensor",
      "symmetric": true,
      "type": "float",
      "zp_dtype": null
    },
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.14.1.dev11+gf2ee47b"
  }
}