config.json

{
  "model_type": "moss_tts_realtime",
  "architectures": [
    "MossTTSRealtime"
  ],
  "auto_map": {
    "AutoConfig": "configuration_mossttsrealtime.MossTTSRealtimeConfig",
    "AutoModel": "modeling_mossttsrealtime.MossTTSRealtime",
    "AutoProcessor": "processing_mossttsrealtime.MossTTSRealtimeProcessor"
  },
  "processor_class": "MossTTSRealtimeProcessor",
  "audio_pad_token": 1024,
  "audio_vocab_size": 1027,
  "dtype": "bfloat16",
  "initializer_range": 0.02,
  "language_config": {
    "_name_or_path": ".",
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "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"
    ],
    "max_position_embeddings": 40960,
    "max_window_layers": 28,
    "model_type": "qwen3",
    "num_attention_heads": 16,
    "num_hidden_layers": 28,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "sliding_window": null,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151936
  },
  "local_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "audio_pad_token": 1024,
    "audio_vocab_size": 1027,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "max_position_embeddings": 33,
    "model_type": "MossTTSRealtimeLocalTransformer",
    "num_attention_heads": 16,
    "num_hidden_layers": 4,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000,
    "rvq": 16,
    "tie_word_embeddings": false,
    "use_cache": true
  },
  "reference_audio_pad": 151654,
  "rvq": 16,
  "text_pad": 151655,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.1",
  "vocab_size": 151936
}