config.json

{
  "architectures": [
    "OpenMoeForCausalLM"
  ],
  "attention_bias": false,
  "auto_map": {
    "AutoModelForCausalLM": "modeling_openmoe.OpenMoeForCausalLM"
  },
  "bos_token_id": 0,
  "dropout_rate": 0.0,
  "enable_comm_overlap": false,
  "enable_hierarchical_alltoall": false,
  "enable_kernel": false,
  "enable_load_balance": false,
  "eos_token_id": 1,
  "expert_parallel": null,
  "head_dim": 128,
  "hidden_act": "swiglu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "label_smoothing": 0.001,
  "layer_norm_epsilon": 1e-06,
  "load_balance_beam_width": 8,
  "load_balance_group_swap_factor": 0.4,
  "load_balance_tolerance": 0.1,
  "max_position_embeddings": 2048,
  "mlp_gated": true,
  "model_type": "llama",
  "moe_layer_interval": 6,
  "num_attention_heads": 24,
  "num_experts": 32,
  "num_hidden_layers": 24,
  "num_key_value_heads": 24,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "router_aux_loss_factor": 0.01,
  "router_capacity_factor_eval": 2.0,
  "router_capacity_factor_train": 1.25,
  "router_drop_tks": true,
  "router_min_capacity": 4,
  "router_noisy_policy": null,
  "router_topk": 2,
  "router_z_loss_factor": 0.0001,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.34.0",
  "use_cache": true,
  "vocab_size": 256384,
  "z_loss_factor": 0.01
}