{
  "architectures": [
    "MiDashengLMSpatialModel"
  ],
  "model_type": "midashenglm_spatial",
  "auto_map": {
    "AutoConfig": "configuration_midashenglm_spatial.MiDashengLMSpatialConfig",
    "AutoModelForCausalLM": "modeling_midashenglm_spatial.MiDashengLMSpatialModel"
  },
  "audio_encoder_config": {
    "embed_dim": 1280,
    "depth": 32,
    "num_heads": 16,
    "input_channels": 1,
    "outputdim": 527,
    "patch_size": [
      64,
      4
    ],
    "patch_stride": [
      64,
      4
    ],
    "target_length": 1008,
    "pooling": null,
    "eval_avg": "cat",
    "init_bn": false,
    "n_mels": 64,
    "n_fft": 512,
    "hop_size": 160,
    "win_size": 512,
    "f_min": 0.0,
    "f_max": 8000.0,
    "sample_rate": 16000,
    "center": true
  },
  "spatial_audio_encoder_config": {
    "embed_dim": 768,
    "depth": 12,
    "num_heads": 12,
    "input_channels": 1,
    "outputdim": 527,
    "patch_size": [
      64,
      4
    ],
    "patch_stride": [
      64,
      4
    ],
    "target_length": 1008,
    "pooling": null,
    "eval_avg": "cat",
    "init_bn": false,
    "n_mels": 64,
    "n_fft": 512,
    "hop_size": 160,
    "win_size": 512,
    "f_min": 0.0,
    "f_max": 8000.0,
    "sample_rate": 16000,
    "center": true
  },
  "text_config": {
    "return_dict": true,
    "output_hidden_states": false,
    "torchscript": false,
    "dtype": "float32",
    "pruned_heads": {},
    "tie_word_embeddings": false,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "is_decoder": false,
    "cross_attention_hidden_size": null,
    "add_cross_attention": false,
    "tie_encoder_decoder": false,
    "finetuning_task": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "task_specific_params": null,
    "problem_type": null,
    "tokenizer_class": null,
    "prefix": null,
    "bos_token_id": null,
    "pad_token_id": null,
    "eos_token_id": null,
    "sep_token_id": null,
    "decoder_start_token_id": null,
    "max_length": 20,
    "min_length": 0,
    "do_sample": false,
    "early_stopping": false,
    "num_beams": 1,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "encoder_no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "num_return_sequences": 1,
    "output_scores": false,
    "return_dict_in_generate": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": null,
    "begin_suppress_tokens": null,
    "num_beam_groups": 1,
    "diversity_penalty": 0.0,
    "transformers_version": "4.57.6",
    "model_type": "qwen2_5_omni_text",
    "init_std": 0.02,
    "tf_legacy_loss": false,
    "use_bfloat16": false,
    "vocab_size": 152064,
    "max_position_embeddings": 32768,
    "hidden_size": 3584,
    "intermediate_size": 18944,
    "num_hidden_layers": 28,
    "num_attention_heads": 28,
    "use_sliding_window": false,
    "sliding_window": null,
    "max_window_layers": 28,
    "num_key_value_heads": 4,
    "hidden_act": "silu",
    "initializer_range": 0.02,
    "rms_norm_eps": 1e-06,
    "use_cache": true,
    "rope_theta": 1000000.0,
    "rope_scaling": {
      "mrope_section": [
        16,
        24,
        24
      ],
      "rope_type": "default",
      "type": "default"
    },
    "attention_dropout": 0.0,
    "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",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "output_attentions": false
  },
  "subsample_factor": 5,
  "audio_channels": 2,
  "num_fusions": 4,
  "audio_token_id": 151646,
  "sem_feature": "MonoLogMel",
  "spa_feature": "LogMel",
  "min_audio_duration": 0.2,
  "model_class": "SpatialMiAudioLLM",
  "torch_dtype": "float32"
}