{
  "architectures": [
    "KORMoForCausalLMWithMTP"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "modeling_kormo.KORMoConfig",
    "AutoModelForCausalLM": "modeling_kormo.KORMoForCausalLMWithMTP"
  },
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "mask_type": "full_causal",
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "kormo",
  "mtp_depth": 3,
  "mtp_loss_lambda": 0.3,
  "num_attention_heads": 16,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "post_ln_layer_end_idx": 0,
  "pretrain_tp": 1,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "tie_word_embeddins": false,
  "torch_dtype": "float32",
  "transformers_version": "4.52.4",
  "use_cache": true,
  "vocab_size": 128256
}