{
  "_entry_class": "MultiModelCacheEntry",
  "_model_id": "PixArt-alpha/PixArt-XL-2-512x512",
  "_task": null,
  "text_encoder": {
    "architectures": [
      "T5EncoderModel"
    ],
    "classifier_dropout": 0.0,
    "d_ff": 10240,
    "d_kv": 64,
    "d_model": 4096,
    "decoder_start_token_id": 0,
    "dense_act_fn": "gelu_new",
    "dropout_rate": 0.1,
    "feed_forward_proj": "gated-gelu",
    "initializer_factor": 1.0,
    "is_encoder_decoder": true,
    "is_gated_act": true,
    "layer_norm_epsilon": 1e-06,
    "model_type": "t5",
    "neuron": {
      "auto_cast": null,
      "auto_cast_type": null,
      "compiler_type": "neuronx-cc",
      "compiler_version": "2.17.194.0+d312836f",
      "dynamic_batch_size": false,
      "inline_weights_to_neff": false,
      "optlevel": "2",
      "output_attentions": false,
      "output_hidden_states": false,
      "static_batch_size": 1,
      "static_sequence_length": 120,
      "task": "feature-extraction",
      "tensor_parallel_size": 1
    },
    "num_decoder_layers": 24,
    "num_heads": 64,
    "num_layers": 24,
    "output_past": true,
    "relative_attention_max_distance": 128,
    "relative_attention_num_buckets": 32,
    "tie_word_embeddings": false,
    "use_cache": true,
    "vocab_size": 32128
  },
  "transformer": {
    "_class_name": "PixArtTransformer2DModel",
    "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": "2.17.194.0+d312836f",
      "dynamic_batch_size": false,
      "inline_weights_to_neff": false,
      "optlevel": "2",
      "output_attentions": false,
      "output_hidden_states": false,
      "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,
      "task": "semantic-segmentation",
      "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,
    "upcast_attention": false,
    "use_additional_conditions": null,
    "use_linear_projection": false
  }
}