{
  "model_type": "deep",
  "architectures": ["DeepForCausalLM"],
  "hidden_size": 1024,
  "num_hidden_layers": 20,
  "intermediate_size": 3200,
  "vocab_size": 32000,
  "num_attention_heads": 16,
  "num_key_value_heads": 4,
  "attention_type": "gqa",
  "attention_dropout": 0.0,
  "use_qk_norm": true,
  "sliding_window": null,
  "max_position_embeddings": 4096,
  "rope_theta": 10000.0,
  "rope_type": "standard",
  "mlp_type": "token_routed",
  "hidden_act": "silu",
  "num_experts": 4,
  "shared_expert": true,
  "shared_intermediate_size": 800,
  "use_mu_guidance": true,
  "use_mu_projection": false,
  "disable_mu_guidance": false,
  "norm_type": "rmsnorm",
  "norm_eps": 1e-06,
  "tie_word_embeddings": true,
  "use_sdpa": true,
  "use_cache": true,
  "initializer_range": 0.02,
  "extra_config": {}
}