{
  "architectures": [
    "KlearMoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_klear.KlearConfig",
    "AutoModel": "modeling_klear.KlearModel",
    "AutoModelForCausalLM": "modeling_klear.KlearMoeForCausalLM"
  },
  "decoder_sparse_step": 1,
  "dtype": "bfloat16",
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8064,
  "max_position_embeddings": 65536,
  "mlp_only_layers": [],
  "model_type": "Klear",
  "moe_aux_loss_coeff": 0.0001,
  "moe_intermediate_size": 896,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_experts": 256,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 32,
  "num_key_value_heads": 4,
  "output_router_logits": false,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "routed_scaling_factor": 2.5,
  "router_aux_loss_coef": 0.001,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "4.56.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}