config.json

{
  "architectures": [
    "VisionTextDualEncoderModel"
  ],
  "logit_scale_init_value": 2.6592,
  "model_type": "vision-text-dual-encoder",
  "projection_dim": 1024,
  "text_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "FacebookAI/xlm-roberta-large",
    "add_cross_attention": false,
    "architectures": [
      "XLMRobertaForMaskedLM"
    ],
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": null,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 514,
    "min_length": 0,
    "model_type": "xlm-roberta",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 24,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_past": true,
    "output_scores": false,
    "pad_token_id": 1,
    "position_embedding_type": "absolute",
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "type_vocab_size": 1,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 250002
  },
  "torch_dtype": "float32",
  "transformers_version": "4.48.3",
  "vision_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "facebook/hiera-huge-224-hf",
    "add_cross_attention": false,
    "architectures": [
      "HieraModel"
    ],
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_depth": null,
    "decoder_hidden_size": null,
    "decoder_num_heads": null,
    "decoder_start_token_id": null,
    "depths": [
      2,
      6,
      36,
      4
    ],
    "diversity_penalty": 0.0,
    "do_sample": false,
    "drop_path_rate": 0.0,
    "early_stopping": false,
    "embed_dim": 256,
    "embed_dim_multiplier": 2.0,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_size": 2048,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": [
      224,
      224
    ],
    "initializer_range": 0.02,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-06,
    "layer_norm_init": 1.0,
    "length_penalty": 1.0,
    "mask_ratio": 0.6,
    "masked_unit_attention": [
      true,
      true,
      false,
      false
    ],
    "masked_unit_size": [
      8,
      8
    ],
    "max_length": 20,
    "min_length": 0,
    "mlp_ratio": 4.0,
    "model_type": "hiera",
    "no_repeat_ngram_size": 0,
    "norm_pix_loss": true,
    "normalize_pixel_loss": true,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_heads": [
      4,
      8,
      16,
      32
    ],
    "num_layers": 4,
    "num_query_pool": 3,
    "num_return_sequences": 1,
    "out_features": [
      "stage4"
    ],
    "out_indices": [
      4
    ],
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_padding": [
      3,
      3
    ],
    "patch_size": [
      7,
      7
    ],
    "patch_stride": [
      4,
      4
    ],
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "query_stride": [
      2,
      2
    ],
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4"
    ],
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "float32",
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_separate_position_embedding": false
  }
}