{
  "align_transformer_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "apply_layernorm": true,
    "architectures": [
      "AlignTransformer"
    ],
    "attention_probs_dropout_prob": 0.0,
    "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": 0.0,
    "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,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-06,
    "layerscale_value": 1.0,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "mlp_ratio": 4,
    "model_type": "align_transformer",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_hidden_layers": 2,
    "num_return_sequences": 1,
    "out_features": [
      "stage2"
    ],
    "out_indices": [
      2
    ],
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 16,
    "prefix": null,
    "problem_type": null,
    "projector_config": null,
    "pruned_heads": {},
    "qkv_bias": true,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "reshape_hidden_states": true,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "stage_names": [
      "stem",
      "stage1",
      "stage2"
    ],
    "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_layer_norm": false,
    "use_swiglu_ffn": false
  },
  "architectures": [
    "CxrAlignModel"
  ],
  "compute_logits_type": "key_phrase_alignment",
  "kwargs": {
    "compute_logits_type": "key_phrase_alignment",
    "loss": {
      "KeyPhraseAlignmentLoss": {
        "attn_temperature": null,
        "compute_i2t_loss": false,
        "hidden_dim": 768,
        "loss_temperature": 0.07,
        "mpnce_col_sum": false,
        "mpnce_row_sum": false,
        "sim_op": "cos",
        "text_features_l2_norm": false,
        "use_attn_layers": false
      },
      "MPClipLoss": null,
      "NegKeyPhraseAlignmentLoss": {
        "compute_i2t_loss": false,
        "hidden_dim": 768
      },
      "OpenClipLoss": {
        "local_loss": false
      },
      "OpenSigLipLoss": {
        "dist_impl": "gather"
      },
      "apply": [
        "KeyPhraseAlignmentLoss"
      ],
      "ratio": [
        1.0
      ]
    },
    "module_to_update": [
      "align_transformer",
      "text_model",
      "loss_fns"
    ],
    "pretrained_dir": "/data/advanced_tech/pretrained"
  },
  "loss": {
    "KeyPhraseAlignmentLoss": {
      "attn_temperature": null,
      "compute_i2t_loss": false,
      "hidden_dim": 768,
      "loss_temperature": 0.07,
      "mpnce_col_sum": false,
      "mpnce_row_sum": false,
      "sim_op": "cos",
      "text_features_l2_norm": false,
      "use_attn_layers": false
    },
    "MPClipLoss": null,
    "NegKeyPhraseAlignmentLoss": {
      "compute_i2t_loss": false,
      "hidden_dim": 768
    },
    "OpenClipLoss": {
      "local_loss": false
    },
    "OpenSigLipLoss": {
      "dist_impl": "gather"
    },
    "apply": [
      "KeyPhraseAlignmentLoss"
    ],
    "ratio": [
      1.0
    ]
  },
  "module_to_update": [
    "align_transformer",
    "text_model",
    "loss_fns"
  ],
  "pretrained_dir": "/data/advanced_tech/pretrained",
  "text_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "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,
    "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,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "mpnet",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "pretrained_name_or_path": "sentence-transformers/all-mpnet-base-v2",
    "pretrained_tokenizer_name_or_path": "sentence-transformers/all-mpnet-base-v2",
    "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,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cls_token": false,
    "use_text_projection": false
  },
  "torch_dtype": "float32",
  "transformers_version": "4.39.3",
  "vision_config": {
    "_name_or_path": "StanfordAIMI/dinov2-base-xray-224",
    "add_cross_attention": false,
    "apply_layernorm": true,
    "architectures": [
      "Dinov2Model"
    ],
    "attention_probs_dropout_prob": 0.0,
    "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": 0.0,
    "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,
    "img_size": 518,
    "initializer_range": 0.02,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-06,
    "layerscale_value": 1.0,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "mlp_ratio": 4,
    "model_type": "dinov2",
    "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": [
      "stage12"
    ],
    "out_indices": [
      12
    ],
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 14,
    "prefix": null,
    "pretrained_dir": "/data/advanced_tech/pretrained",
    "pretrained_name_or_path": "StanfordAIMI/dinov2-base-xray-224",
    "problem_type": null,
    "pruned_heads": {},
    "qkv_bias": true,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "reshape_hidden_states": true,
    "return_dict": true,
    "return_dict_in_generate": false,
    "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_bfloat16": false,
    "use_swiglu_ffn": false
  },
  "auto_map": {
    "AutoConfig": "configuration_radzero.CxrAlignConfig",
    "AutoModel": "modeling_radzero.CxrAlignModel"
  }
}