config.json
4.2 KB · 68 lines · json Raw
1 {
2 "architecture": "voxcpm2",
3 "lm_config": {
4 "bos_token_id": 1,
5 "eos_token_id": 2,
6 "hidden_size": 2048,
7 "intermediate_size": 6144,
8 "max_position_embeddings": 32768,
9 "num_attention_heads": 16,
10 "num_hidden_layers": 28,
11 "num_key_value_heads": 2,
12 "rms_norm_eps": 1e-05,
13 "rope_theta": 10000,
14 "kv_channels": 128,
15 "rope_scaling": {
16 "type": "longrope",
17 "long_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529],
18 "short_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529],
19 "original_max_position_embeddings": 32768
20 },
21 "vocab_size": 73448,
22 "use_mup": false,
23 "scale_emb": 12,
24 "dim_model_base": 256,
25 "scale_depth": 1.4
26 },
27 "patch_size": 4,
28 "feat_dim": 64,
29 "scalar_quantization_latent_dim": 512,
30 "scalar_quantization_scale": 9,
31 "residual_lm_num_layers": 8,
32 "residual_lm_no_rope": true,
33 "encoder_config": {
34 "hidden_dim": 1024,
35 "ffn_dim": 4096,
36 "num_heads": 16,
37 "num_layers": 12,
38 "kv_channels": 128
39 },
40 "dit_config": {
41 "hidden_dim": 1024,
42 "ffn_dim": 4096,
43 "num_heads": 16,
44 "num_layers": 12,
45 "kv_channels": 128,
46 "mean_mode": false,
47 "cfm_config": {
48 "sigma_min": 1e-06,
49 "solver": "euler",
50 "t_scheduler": "log-norm",
51 "inference_cfg_rate": 2.0
52 }
53 },
54 "audio_vae_config": {
55 "encoder_dim": 128,
56 "encoder_rates": [2, 5, 8, 8],
57 "latent_dim": 64,
58 "decoder_dim": 2048,
59 "decoder_rates": [8, 6, 5, 2, 2, 2],
60 "sr_bin_boundaries": [20000, 30000, 40000],
61 "sample_rate": 16000,
62 "out_sample_rate": 48000
63 },
64 "max_length": 8192,
65 "device": "cuda",
66 "dtype": "bfloat16"
67 }
68