transformer/config.json

{
  "_class_name": "MiniMaxH3Transformer3DModel",
  "_diffusers_version": "0.36.0.dev0",
  "num_attention_heads": 56,
  "attention_head_dim": 128,
  "hidden_size": 5376,
  "num_layers": 42,
  "num_refiner_layers": 2,
  "ffn_dim": 14336,
  "in_channels": 24,
  "audio_in_channels": 32,
  "patch_size": [
    1,
    2,
    2
  ],
  "text_dim": 5120,
  "freq_dim": 256,
  "time_embed_hidden_dim": 5376,
  "time_embed_dim": 2688,
  "rope_freq_dim": 16,
  "rope_theta": 10000.0,
  "norm_eps": 1e-05,
  "qk_norm_eps": 1e-05,
  "final_norm_eps": 1e-05,
  "adaln_rank": 16,
  "source_num_layers": 50,
  "kept_block_indices": [
    0,
    1,
    2,
    3,
    4,
    5,
    8,
    10,
    11,
    12,
    14,
    17,
    18,
    19,
    20,
    21,
    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
  ]
}