{
  "vocab_size": 151936,
  "hidden_size": 5120,
  "intermediate_size": 20480,
  "num_hidden_layers": 52,
  "num_attention_heads": 48,
  "num_key_value_heads": 8,
  "hidden_act": "silu",
  "max_position_embeddings": 1048576,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "use_cache": true,
  "tie_word_embeddings": false,
  "rope_parameters": {
    "sliding_attention": {
      "rope_type": "default",
      "rope_theta": 10000.0
    },
    "full_attention": null
  },
  "attention_bias": false,
  "sliding_window": 512,
  "attention_dropout": 0.0,
  "moe_intermediate_size": 2560,
  "num_experts_per_tok": 8,
  "num_experts": 256,
  "norm_topk_prob": true,
  "output_router_logits": false,
  "pad_token_id": null,
  "bos_token_id": null,
  "eos_token_id": null,
  "head_dim": 128,
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "mlp_layer_types": [
    "dense",
    "dense",
    "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",
    "sparse",
    "sparse"
  ],
  "n_group": 8,
  "topk_group": 4,
  "routed_scaling_factor": 2.5,
  "final_logit_softcapping": 30.0,
  "model_type": "beam",
  "architectures": [
    "BeamForCausalLM"
  ]
}