transformer/config.json

{
  "_class_name": "Cosmos3OmniTransformer",
  "_diffusers_version": "0.40.0.dev0",
  "action_dim": 64,
  "action_gen": true,
  "attention_bias": false,
  "attention_dropout": 0.0,
  "backbone_type": "cosmos3_edge_nemotron_dense",
  "base_fps": 24,
  "enable_fps_modulation": true,
  "head_dim": 128,
  "hidden_act": "relu2",
  "hidden_size": 2048,
  "intermediate_size": 9216,
  "latent_channel": 48,
  "latent_patch_size": 2,
  "num_attention_heads": 16,
  "num_embodiment_domains": 32,
  "num_hidden_layers": 28,
  "num_key_value_heads": 8,
  "patch_latent_dim": 192,
  "qk_norm_for_text": false,
  "rms_norm_eps": 1e-05,
  "rope_axes_dim": [
    24,
    20,
    20
  ],
  "rope_scaling": {
    "mrope_section": [
      24,
      20,
      20
    ]
  },
  "rope_theta": 100000000,
  "sound_dim": null,
  "sound_gen": false,
  "sound_latent_fps": 25,
  "temporal_compression_factor": 4,
  "timestep_scale": 0.001,
  "unified_3d_mrope_reset_spatial_ids": true,
  "unified_3d_mrope_temporal_modality_margin": 15000,
  "use_und_k_norm_for_gen": true,
  "vocab_size": 131072
}