{
  "config": {
    "architecture_version": 1,
    "dimensions": 32,
    "foundation_config": {
      "_name_or_path": "openai/clip-vit-base-patch32",
      "architectures": [
        "CLIPModel"
      ],
      "chunk_size_feed_forward": 0,
      "dtype": "float32",
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "initializer_factor": 1.0,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "logit_scale_init_value": 2.6592,
      "model_type": "clip",
      "output_attentions": false,
      "output_hidden_states": false,
      "problem_type": null,
      "projection_dim": 512,
      "return_dict": true,
      "text_config": {
        "_name_or_path": "",
        "add_cross_attention": false,
        "architectures": null,
        "attention_dropout": 0.0,
        "bos_token_id": 0,
        "chunk_size_feed_forward": 0,
        "cross_attention_hidden_size": null,
        "decoder_start_token_id": null,
        "dropout": 0.0,
        "dtype": "float32",
        "eos_token_id": 2,
        "finetuning_task": null,
        "hidden_act": "quick_gelu",
        "hidden_size": 512,
        "id2label": {
          "0": "LABEL_0",
          "1": "LABEL_1"
        },
        "initializer_factor": 1.0,
        "initializer_range": 0.02,
        "intermediate_size": 2048,
        "is_decoder": false,
        "is_encoder_decoder": false,
        "label2id": {
          "LABEL_0": 0,
          "LABEL_1": 1
        },
        "layer_norm_eps": 1e-05,
        "max_position_embeddings": 77,
        "model_type": "clip_text_model",
        "num_attention_heads": 8,
        "num_hidden_layers": 12,
        "output_attentions": false,
        "output_hidden_states": false,
        "pad_token_id": 1,
        "prefix": null,
        "problem_type": null,
        "projection_dim": 512,
        "pruned_heads": {},
        "return_dict": true,
        "sep_token_id": null,
        "task_specific_params": null,
        "tie_encoder_decoder": false,
        "tie_word_embeddings": true,
        "tokenizer_class": null,
        "torchscript": false,
        "use_bfloat16": false,
        "vocab_size": 49408
      },
      "transformers_version": "5.17.0",
      "vision_config": {
        "_name_or_path": "",
        "add_cross_attention": false,
        "architectures": null,
        "attention_dropout": 0.0,
        "bos_token_id": null,
        "chunk_size_feed_forward": 0,
        "cross_attention_hidden_size": null,
        "decoder_start_token_id": null,
        "dropout": 0.0,
        "dtype": "float32",
        "eos_token_id": null,
        "finetuning_task": null,
        "hidden_act": "quick_gelu",
        "hidden_size": 768,
        "id2label": {
          "0": "LABEL_0",
          "1": "LABEL_1"
        },
        "image_size": 224,
        "initializer_factor": 1.0,
        "initializer_range": 0.02,
        "intermediate_size": 3072,
        "is_decoder": false,
        "is_encoder_decoder": false,
        "label2id": {
          "LABEL_0": 0,
          "LABEL_1": 1
        },
        "layer_norm_eps": 1e-05,
        "model_type": "clip_vision_model",
        "num_attention_heads": 12,
        "num_channels": 3,
        "num_hidden_layers": 12,
        "output_attentions": false,
        "output_hidden_states": false,
        "pad_token_id": null,
        "patch_size": 32,
        "prefix": null,
        "problem_type": null,
        "projection_dim": 512,
        "pruned_heads": {},
        "return_dict": true,
        "sep_token_id": null,
        "task_specific_params": null,
        "tie_encoder_decoder": false,
        "tie_word_embeddings": true,
        "tokenizer_class": null,
        "torchscript": false,
        "use_bfloat16": false
      }
    },
    "foundation_source": {
      "repo_id": "openai/clip-vit-base-patch32",
      "revision": "3d74acf9a28c67741b2f4f2ea7635f0aaf6f0268"
    },
    "image_mean": [
      0.48145466,
      0.4578275,
      0.40821073
    ],
    "image_std": [
      0.26862954,
      0.26130258,
      0.27577711
    ],
    "in_channels": 3,
    "max_candidates": 64,
    "max_image_size": 256,
    "max_tokens": 256,
    "patch_size": 32,
    "preprocessing": "bicubic-antialiased-square-resize",
    "slots": 4,
    "steps": 2,
    "tokenizer_sha256": "4a07de0310c7cbeac0fd1ae3193c8240ee7ea16dd0ab94b119d8fd597169feec",
    "vocabulary": [
      "<foundation>"
    ]
  },
  "format": "tensorcode.pretrained",
  "tool": "tensorcode.tools.scene.Scene",
  "version": 1
}