config.json

{
  "architectures": [
    "LLaDAMoEModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "clip_qkv": null,
  "dense_intermediate_size": 8192,
  "eos_token_id": 156892,
  "expert_intermediate_size": 1024,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "max_position_embeddings": 8192,
  "model_type": "llada",
  "moe_layer_freq": [
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1
  ],
  "moe_router_enable_expert_bias": false,
  "moe_router_score_function": "softmax",
  "norm_topk_prob": null,
  "num_attention_heads": 16,
  "num_experts": 64,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 16,
  "num_key_value_heads": 16,
  "output_router_logits": false,
  "pad_token_id": 156892,
  "partial_rotary_factor": 1,
  "qk_layernorm": true,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 50000,
  "routed_scaling_factor": 1,
  "router_aux_loss_coef": 0.01,
  "router_num_group": null,
  "router_topk_group": null,
  "shared_expert_intermediate_size": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.2",
  "use_cache": false,
  "vocab_size": 157184,
  "auto_map": {
    "AutoConfig": "configuration_lladamoe.LLaDAConfig",
    "AutoModel": "modeling_lladamoe.LLaDAMoEModelLM",
    "AutoModelForCausalLM": "modeling_lladamoe.LLaDAMoEModelLM"
  }
}