{
  "architectures": [
    "Glm4MoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "dtype": "float32",
  "first_k_dense_replace": 1,
  "hidden_act": "silu",
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 128,
  "max_position_embeddings": 256,
  "model_type": "glm4_moe",
  "moe_intermediate_size": 32,
  "n_group": 1,
  "n_routed_experts": 4,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 4,
  "num_experts_per_tok": 2,
  "num_hidden_layers": 2,
  "num_key_value_heads": 4,
  "partial_rotary_factor": 0.5,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000,
  "routed_scaling_factor": 1.8,
  "tie_word_embeddings": false,
  "topk_group": 1,
  "topk_method": "noaux_tc",
  "transformers_version": "4.57.6",
  "use_cache": true,
  "use_qk_norm": false,
  "vocab_size": 1000
}