{
  "acoustic_dim": 512,
  "acoustic_from_nth_hidden_state": -1,
  "acoustic_mean": 0.0,
  "acoustic_std": 1.5,
  "add_semantic_to_condition": 0.0,
  "architectures": [
    "TadaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "bottleneck_dim": null,
  "context_window": 8,
  "diffusion_head_type": "vibevoice",
  "dist_type": "fixed",
  "dtype": "bfloat16",
  "eos_token_id": 128001,
  "head_dim": 64,
  "head_ffn_ratio": 4.0,
  "head_layers": 6,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "latent_dropout": 0.0,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "num_time_classes": 256,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "shift_acoustic": 5,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "vocab_size": 128256
}