{
  "architectures": [
    "StepAudio2ForCausalLM"
  ],
  "audio_encoder_config": {
    "adapter_stride": 2,
    "kernel_size": 3,
    "llm_dim": 3584,
    "model_type": "step_audio_2_encoder",
    "n_audio_ctx": 1500,
    "n_audio_head": 20,
    "n_audio_layer": 32,
    "n_audio_state": 1280,
    "n_codebook_size": 4096,
    "n_mels": 128
  },
  "auto_map": {
    "AutoConfig": "configuration_step_audio_2.StepAudio2Config",
    "AutoModelForCausalLM": "modeling_step_audio_2.StepAudio2ForCausalLM"
  },
  "dtype": "bfloat16",
  "max_window_layers": null,
  "model_type": "step_audio_2",
  "sliding_window": 2048,
  "text_config": {
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "hidden_act": "silu",
    "hidden_size": 3584,
    "initializer_range": 0.02,
    "intermediate_size": 18944,
    "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": 16384,
    "max_window_layers": 28,
    "model_type": "qwen2",
    "num_attention_heads": 28,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sliding_window": null,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 158720
  },
  "tie_word_embeddings": false,
  "transformers_version": "4.57.6",
  "use_sliding_window": false
}