{
  "architectures": [
    "DogeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "hidden_act": "silu",
  "hidden_dropout": 0.0,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "is_moe": true,
  "keep_window_size": 2048,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "model_type": "doge",
  "norm_topk_prob": false,
  "num_attention_heads": 4,
  "num_experts": 4096,
  "num_experts_per_tok": 16,
  "num_hidden_layers": 16,
  "num_key_value_heads": 2,
  "output_router_logits": true,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "router_aux_loss_coef": 0.001,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.54.0.dev0",
  "use_cache": true,
  "vocab_size": 128256
}