transformer/config.json

{
  "_class_name": "CosmosTransformer3DModel",
  "_diffusers_version": "0.38.0",
  "adaln_lora_dim": 256,
  "attention_head_dim": 128,
  "concat_padding_mask": true,
  "controlnet_block_every_n": null,
  "crossattn_proj_in_channels": 1024,
  "encoder_hidden_states_channels": 1024,
  "extra_pos_embed_type": null,
  "img_context_dim_in": null,
  "img_context_dim_out": 2048,
  "img_context_num_tokens": 256,
  "in_channels": 16,
  "max_size": [
    128,
    240,
    240
  ],
  "mlp_ratio": 4.0,
  "num_attention_heads": 16,
  "num_layers": 28,
  "out_channels": 16,
  "patch_size": [
    1,
    2,
    2
  ],
  "quantization_config": {
    "add_skip_keys": false,
    "dequantize_fp32": false,
    "dynamic_loss_threshold": null,
    "group_size": 0,
    "is_integer": true,
    "is_training": false,
    "modules_dtype_dict": {},
    "modules_quant_config": {},
    "modules_to_not_convert": [
      "crossattn_proj",
      "patch_embed",
      "transformer_blocks.0.norm*",
      "norm_out",
      "proj_out",
      "learnable_pos_embed",
      "time_embed"
    ],
    "non_blocking": false,
    "quant_conv": false,
    "quant_embedding": false,
    "quant_method": "sdnq",
    "quantization_device": null,
    "quantized_matmul_dtype": null,
    "return_device": null,
    "sdnq_version": "0.1.8",
    "svd_rank": 32,
    "svd_steps": 8,
    "use_dynamic_quantization": false,
    "use_grad_ckpt": true,
    "use_quantized_matmul": true,
    "use_quantized_matmul_conv": false,
    "use_static_quantization": true,
    "use_stochastic_rounding": false,
    "use_svd": false,
    "weights_dtype": "uint4"
  },
  "rope_scale": [
    1.0,
    4.0,
    4.0
  ],
  "text_embed_dim": 1024,
  "use_crossattn_projection": false,
  "_name_or_path": null
}