| { | |
| "architecture": "voxcpm", | |
| "audio_vae_config": { | |
| "encoder_dim": 64, | |
| "encoder_rates": [ | |
| 2, | |
| 3, | |
| 6, | |
| 7, | |
| 7 | |
| ], | |
| "latent_dim": 64, | |
| "decoder_dim": 2048, | |
| "decoder_rates": [ | |
| 7, | |
| 7, | |
| 6, | |
| 3, | |
| 2 | |
| ], | |
| "sample_rate": 44100 | |
| }, | |
| "device": "cuda", | |
| "dit_config": { | |
| "hidden_dim": 1024, | |
| "ffn_dim": 4096, | |
| "num_heads": 16, | |
| "num_layers": 8, | |
| "cfm_config": { | |
| "sigma_min": 1e-06, | |
| "solver": "euler", | |
| "t_scheduler": "log-norm", | |
| "inference_cfg_rate": 2.0 | |
| } | |
| }, | |
| "dtype": "bfloat16", | |
| "encoder_config": { | |
| "hidden_dim": 1024, | |
| "ffn_dim": 4096, | |
| "num_heads": 16, | |
| "num_layers": 8 | |
| }, | |
| "feat_dim": 64, | |
| "lm_config": { | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_size": 1024, | |
| "intermediate_size": 4096, | |
| "max_position_embeddings": 32768, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000, | |
| "rope_scaling": { | |
| "type": "longrope", | |
| "long_factor": [ | |
| 1.0004360675811768, | |
| 1.0668443441390991, | |
| 1.1631425619125366, | |
| 1.3025742769241333, | |
| 1.5040205717086792, | |
| 1.7941505908966064, | |
| 2.2101221084594727, | |
| 2.802666664123535, | |
| 3.6389970779418945, | |
| 4.804192543029785, | |
| 6.39855432510376, | |
| 8.527148246765137, | |
| 11.277542114257812, | |
| 14.684998512268066, | |
| 18.69317054748535, | |
| 23.13019371032715, | |
| 27.72362518310547, | |
| 32.1606559753418, | |
| 36.168827056884766, | |
| 39.57627868652344, | |
| 42.32667541503906, | |
| 44.45526885986328, | |
| 46.04962921142578, | |
| 47.21482849121094, | |
| 48.05115509033203, | |
| 48.64370346069336, | |
| 49.05967712402344, | |
| 49.34980392456055, | |
| 49.551246643066406, | |
| 49.69068145751953, | |
| 49.78697967529297, | |
| 49.85338592529297 | |
| ], | |
| "short_factor": [ | |
| 1.0004360675811768, | |
| 1.0668443441390991, | |
| 1.1631425619125366, | |
| 1.3025742769241333, | |
| 1.5040205717086792, | |
| 1.7941505908966064, | |
| 2.2101221084594727, | |
| 2.802666664123535, | |
| 3.6389970779418945, | |
| 4.804192543029785, | |
| 6.39855432510376, | |
| 8.527148246765137, | |
| 11.277542114257812, | |
| 14.684998512268066, | |
| 18.69317054748535, | |
| 23.13019371032715, | |
| 27.72362518310547, | |
| 32.1606559753418, | |
| 36.168827056884766, | |
| 39.57627868652344, | |
| 42.32667541503906, | |
| 44.45526885986328, | |
| 46.04962921142578, | |
| 47.21482849121094, | |
| 48.05115509033203, | |
| 48.64370346069336, | |
| 49.05967712402344, | |
| 49.34980392456055, | |
| 49.551246643066406, | |
| 49.69068145751953, | |
| 49.78697967529297, | |
| 49.85338592529297 | |
| ], | |
| "original_max_position_embeddings": 32768 | |
| }, | |
| "vocab_size": 73448, | |
| "scale_emb": 12, | |
| "dim_model_base": 256, | |
| "scale_depth": 1.4, | |
| "use_mup": false | |
| }, | |
| "max_length": 8192, | |
| "patch_size": 4, | |
| "residual_lm_num_layers": 8, | |
| "scalar_quantization_latent_dim": 256, | |
| "scalar_quantization_scale": 9 | |
| } |