{
  "model_type": "mobilemoe",
  "architectures": [
    "MobileMoEForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_mobilemoe.MobileMoEConfig",
    "AutoModel": "modeling_mobilemoe.MobileMoETextModel",
    "AutoModelForCausalLM": "modeling_mobilemoe.MobileMoEForCausalLM"
  },
  "vocab_size": 128256,
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "hidden_size": 768,
  "intermediate_size": 384,
  "intermediate_size_mlp": 1536,
  "num_hidden_layers": 20,
  "num_attention_heads": 12,
  "num_key_value_heads": 4,
  "head_dim": 64,
  "hidden_act": "silu",
  "max_position_embeddings": 8192,
  "rms_norm_eps": 1e-05,
  "rope_theta": 500000.0,
  "rope_scaling": {
    "rope_type": "llama3",
    "factor": 16,
    "original_max_position_embeddings": 8192,
    "low_freq_factor": 1.0,
    "high_freq_factor": 1.0
  },
  "num_local_experts": 60,
  "num_experts_per_tok": 4,
  "interleave_moe_layer_step": 1,
  "no_rope_layers": [
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1
  ],
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "use_qk_norm": true,
  "attn_temperature_tuning": false,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "attention_bias": false,
  "attention_dropout": 0.0,
  "routed_scaling_factor": 2.5,
  "norm_topk_prob": true
}