config.json

{
  "architectures": [
    "Qwen3PseudoMoEModelModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "modeling_qwen3_pseudo_moe.Qwen3PseudoMoEConfig",
    "AutoModel": "modeling_qwen3_pseudo_moe.Qwen3PseudoMoEModelModel"
  },
  "bos_token_id": 151643,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "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"
  ],
  "max_position_embeddings": 40960,
  "max_window_layers": 12,
  "model_type": "qwen3_pseudo_moe",
  "num_attention_heads": 16,
  "num_hidden_layers": 12,
  "num_key_value_heads": 8,
  "proj_dim": 4096,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.1",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 151936,
  "lora_rank": 32,
  "lora_alpha": 64.0,
  "lora_target_modules": [
    "o_proj",
    "proj_linear",
    "k_proj",
    "v_proj",
    "q_proj",
    "up_proj",
    "gate_proj",
    "down_proj"
  ],
  "domain_names": [
    "coding",
    "reasoning"
  ]
}