config.json

{
    "architectures":
    [
        "CsmForConditionalGeneration"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "audio_eos_token_id": 128003,
    "audio_token_id": 128002,
    "bos_token_id": 128000,
    "codebook_eos_token_id": 0,
    "codebook_pad_token_id": 2050,
    "codec_config":
    {
        "_name_or_path": "kyutai/mimi",
        "architectures":
        [
            "MimiModel"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "audio_channels": 1,
        "codebook_dim": 256,
        "codebook_size": 2048,
        "compress": 2,
        "dilation_growth_rate": 2,
        "frame_rate": 12.5,
        "head_dim": 64,
        "hidden_act": "gelu",
        "hidden_size": 512,
        "initializer_range": 0.02,
        "intermediate_size": 2048,
        "kernel_size": 7,
        "last_kernel_size": 3,
        "layer_scale_initial_scale": 0.01,
        "max_position_embeddings": 8000,
        "model_type": "mimi",
        "norm_eps": 0.00001,
        "normalize": false,
        "num_attention_heads": 8,
        "num_filters": 64,
        "num_hidden_layers": 8,
        "num_key_value_heads": 8,
        "num_quantizers": 32,
        "num_residual_layers": 1,
        "num_semantic_quantizers": 1,
        "pad_mode": "constant",
        "residual_kernel_size": 3,
        "rope_theta": 10000.0,
        "sampling_rate": 24000,
        "sliding_window": 250,
        "torch_dtype": "float32",
        "trim_right_ratio": 1.0,
        "upsample_groups": 512,
        "upsampling_ratios":
        [
            8,
            6,
            5,
            4
        ],
        "use_cache": false,
        "use_causal_conv": true,
        "use_conv_shortcut": false,
        "vector_quantization_hidden_dimension": 256
    },
    "depth_decoder_config":
    {
        "attention_bias": false,
        "attention_dropout": 0.0,
        "backbone_hidden_size": 1536,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 1024,
        "initializer_range": 0.02,
        "intermediate_size": 4096,
        "max_position_embeddings": 33,
        "mlp_bias": false,
        "model_type": "csm_depth_decoder_model",
        "num_attention_heads": 8,
        "num_codebooks": 32,
        "num_hidden_layers": 4,
        "num_key_value_heads": 2,
        "rms_norm_eps": 0.00001,
        "rope_scaling":
        {
            "factor": 32.0,
            "high_freq_factor": 0.0078125,
            "low_freq_factor": 0.001953125,
            "original_max_position_embeddings": 16,
            "rope_type": "llama3"
        },
        "rope_theta": 500000,
        "use_cache": true,
        "vocab_size": 2051
    },
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 1536,
    "initializer_range": 0.02,
    "intermediate_size": 8192,
    "max_position_embeddings": 2048,
    "mlp_bias": false,
    "model_type": "csm",
    "num_attention_heads": 12,
    "num_codebooks": 32,
    "num_hidden_layers": 6,
    "num_key_value_heads": 3,
    "pad_token_id": 128002,
    "rms_norm_eps": 0.00001,
    "rope_scaling":
    {
        "factor": 32.0,
        "high_freq_factor": 0.5,
        "low_freq_factor": 0.125,
        "original_max_position_embeddings": 1024,
        "rope_type": "llama3"
    },
    "rope_theta": 500000,
    "text_vocab_size": 49152,
    "tie_codebooks_embeddings": true,
    "tie_word_embeddings": false,
    "use_cache": true,
    "vocab_size": 2051,
    "audio_num_codebooks": 32,
    "audio_vocab_size": 2051,
    "backbone_flavor": "llama-250M",
    "decoder_flavor": "llama-60M",
    "text_tokenizer": "Marvis-AI/marvis-tts-0.25b-expressive-preview"
}