config.json

{
  "architectures": [
    "VisionTextDualEncoderModel"
  ],
  "cache_dir": null,
  "logit_scale_init_value": 2.6592,
  "model_type": "vision-text-dual-encoder",
  "projection_dim": 512,
  "revision": "main",
  "text_config": {
    "_name_or_path": "ckiplab/bert-base-chinese",
    "add_cross_attention": false,
    "architectures": [
      "BertForMaskedLM"
    ],
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": null,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "directionality": "bidi",
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "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,
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "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-12,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 512,
    "min_length": 0,
    "model_type": "bert",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "pooler_fc_size": 768,
    "pooler_num_attention_heads": 12,
    "pooler_num_fc_layers": 3,
    "pooler_size_per_head": 128,
    "pooler_type": "first_token_transform",
    "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": "BertTokenizerFast",
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "type_vocab_size": 2,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 21128
  },
  "token": null,
  "torch_dtype": "float32",
  "transformers_version": "4.42.3",
  "trust_remote_code": false,
  "vision_config": {
    "_name_or_path": "microsoft/dit-base",
    "add_cross_attention": false,
    "add_fpn": false,
    "architectures": [
      "BeitForMaskedImageModeling"
    ],
    "attention_probs_dropout_prob": 0.0,
    "auxiliary_channels": 256,
    "auxiliary_concat_input": false,
    "auxiliary_loss_weight": 0.4,
    "auxiliary_num_convs": 1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "drop_path_rate": 0.1,
    "early_stopping": false,
    "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_dropout_prob": 0.0,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 224,
    "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-12,
    "layer_scale_init_value": 0.1,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "beit",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "out_features": [
      "stage3",
      "stage5",
      "stage7",
      "stage11"
    ],
    "out_indices": [
      3,
      5,
      7,
      11
    ],
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 16,
    "pool_scales": [
      1,
      2,
      3,
      6
    ],
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "reshape_hidden_states": true,
    "return_dict": true,
    "return_dict_in_generate": false,
    "semantic_loss_ignore_index": 255,
    "sep_token_id": null,
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4",
      "stage5",
      "stage6",
      "stage7",
      "stage8",
      "stage9",
      "stage10",
      "stage11",
      "stage12"
    ],
    "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_absolute_position_embeddings": true,
    "use_auxiliary_head": true,
    "use_bfloat16": false,
    "use_mask_token": true,
    "use_mean_pooling": true,
    "use_relative_position_bias": false,
    "use_shared_relative_position_bias": false,
    "vocab_size": 8192
  }
}