config.json

{
  "architectures": [
    "MiDashengLMModel"
  ],
  "audio_encoder_config": {
    "attn_drop_rate": 0.0,
    "center": true,
    "depth": 32,
    "drop_rate": 0.0,
    "embed_dim": 1280,
    "f_max": 8000.0,
    "f_min": 0.0,
    "hop_length": 160,
    "init_values": null,
    "input_channels": 1,
    "mlp_ratio": 4.0,
    "model_type": "midashenglm_dasheng_encoder",
    "n_fft": 512,
    "n_mels": 64,
    "num_heads": 16,
    "outputdim": 527,
    "patch_size": [
      64,
      4
    ],
    "patch_stride": [
      64,
      4
    ],
    "qkv_bias": true,
    "sample_rate": 16000,
    "target_length": 1008,
    "win_length": 512
  },
  "audio_token_id": 151646,
  "auto_map": {
    "AutoConfig": "configuration_midashenglm.MiDashengLMConfig",
    "AutoModelForCausalLM": "modeling_midashenglm.MiDashengLMModel"
  },
  "model_type": "midashenglm",
  "subsample_factor": 5,
  "text_config": {
    "attention_dropout": 0.0,
    "hidden_act": "silu",
    "hidden_size": 3584,
    "init_std": 0.02,
    "initializer_range": 0.02,
    "intermediate_size": 18944,
    "max_position_embeddings": 32768,
    "max_window_layers": 28,
    "model_type": "qwen2_5_omni_text",
    "num_attention_heads": 28,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "rms_norm_eps": 1e-06,
    "rope_scaling": {
      "mrope_section": [
        16,
        24,
        24
      ],
      "rope_type": "default",
      "type": "default"
    },
    "rope_theta": 1000000.0,
    "sliding_window": 32768,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 152064
  },
  "torch_dtype": "float32",
  "transformers_version": "4.52.4"
}