transformer/config.json

{
  "_class_name": "PixArtTransformer2DModel",
  "_commit_hash": null,
  "_diffusers_version": "0.31.0",
  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--PixArt-alpha--PixArt-XL-2-512x512/snapshots/50f702106901db6d0f8b67eb88e814c56ded2692/transformer",
  "_use_default_values": [
    "interpolation_scale",
    "use_additional_conditions"
  ],
  "activation_fn": "gelu-approximate",
  "attention_bias": true,
  "attention_head_dim": 72,
  "attention_type": "default",
  "caption_channels": 4096,
  "cross_attention_dim": 1152,
  "double_self_attention": false,
  "dropout": 0.0,
  "in_channels": 4,
  "interpolation_scale": null,
  "neuron": {
    "auto_cast": null,
    "auto_cast_type": null,
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.15.141.0+d3cfc8ca",
    "dynamic_batch_size": false,
    "inline_weights_to_neff": false,
    "input_names": [
      "sample",
      "encoder_hidden_states",
      "timestep",
      "encoder_attention_mask"
    ],
    "model_type": "pixart-transformer-2d",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "out_hidden_states"
    ],
    "static_batch_size": 1,
    "static_encoder_hidden_size": 4096,
    "static_height": 64,
    "static_num_channels": 4,
    "static_patch_size": 2,
    "static_sequence_length": 120,
    "static_vae_scale_factor": 8,
    "static_width": 64,
    "tensor_parallel_size": 1
  },
  "norm_elementwise_affine": false,
  "norm_eps": 1e-06,
  "norm_num_groups": 32,
  "norm_type": "ada_norm_single",
  "num_attention_heads": 16,
  "num_embeds_ada_norm": 1000,
  "num_layers": 28,
  "num_vector_embeds": null,
  "only_cross_attention": false,
  "out_channels": 8,
  "patch_size": 2,
  "sample_size": 64,
  "task": "semantic-segmentation",
  "transformers_version": null,
  "upcast_attention": false,
  "use_additional_conditions": null,
  "use_linear_projection": false
}