Hugging Face's logo

ibrazebra
/
csm-1b

Text-to-Speech
Safetensors
English
csm
model_hub_mixin
pytorch_model_hub_mixin
Model card Files
xet
Community
csm-1b
File size: 3,527 Bytes 
d8526f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
 
{
    "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": 1e-05,
      "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": 2048,
      "head_dim": 128,
      "hidden_act": "silu",
      "hidden_size": 1024,
      "initializer_range": 0.02,
      "intermediate_size": 8192,
      "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": 1e-05,
      "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": 64,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 8192,
    "max_position_embeddings": 2048,
    "mlp_bias": false,
    "model_type": "csm",
    "num_attention_heads": 32,
    "num_codebooks": 32,
    "num_hidden_layers": 16,
    "num_key_value_heads": 8,
    "pad_token_id": 128002,
    "rms_norm_eps": 1e-05,
    "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": 128256,
    "tie_codebooks_embeddings": true,
    "tie_word_embeddings": false,
    "torch_dtype": "float32",
    "transformers_version": "4.52.0.dev0",
    "use_cache": true,
    "vocab_size": 2051,
    "audio_num_codebooks": 32,
    "audio_vocab_size": 2051,
    "backbone_flavor": "llama-1B",
    "decoder_flavor": "llama-100M",
    "transformers_weights": "transformers.safetensors.index.json"
  }