{
  "architectures": [
    "DynamicMindMoEForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_dynamicmind_moe.DynamicMindMoEConfig",
    "AutoModelForCausalLM": "modeling_dynamicmind_moe.DynamicMindMoEForCausalLM"
  },
  "bos_token_id": 0,
  "dtype": "bfloat16",
  "eos_token_id": 0,
  "first_k_dense_layers": 0,
  "hidden_size": 256,
  "intermediate_size": 768,
  "max_position_embeddings": 1024,
  "model_type": "dynamicmind_moe",
  "moe_intermediate_size": 256,
  "norm_topk_prob": true,
  "num_attention_heads": 8,
  "num_experts_per_token": 2,
  "num_hidden_layers": 9,
  "num_key_value_heads": 2,
  "num_routed_experts": 14,
  "num_shared_experts": 1,
  "pad_token_id": 1,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "router_aux_loss_coef": 0.01,
  "router_bias_update_rate": 0.001,
  "router_z_loss_coef": 0.001,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.3",
  "use_aux_loss_free_balancing": true,
  "vocab_size": 8192
}