config.json

{
  "architectures": [
    "Siglip2HierForDocClassification"
  ],
  "auto_map": {
    "AutoConfig": "configuration_siglip2_hier.Siglip2HierConfig",
    "AutoModel": "modeling_siglip2_hier.Siglip2HierForDocClassification"
  },
  "base_model_id": "google/siglip2-base-patch16-naflex",
  "default_scope": "flat",
  "dtype": "bfloat16",
  "flat_l2_classes": [
    "letter",
    "other_document",
    "scan_interpretation",
    "lab_diagnostic_report",
    "opd_consultation_record",
    "discharge_summary",
    "insurance_document",
    "form",
    "invoice_bill",
    "certificate",
    "other_miscellaneous",
    "medication_image",
    "ultrasound",
    "x_ray",
    "mri",
    "ct",
    "other_diagnostic_imaging",
    "abha_card",
    "voter_id",
    "aadhaar_card",
    "insurance_e_card",
    "pan_card",
    "pmjay_ayushman",
    "other_card",
    "headshot",
    "skin_wound",
    "other_body_images"
  ],
  "flat_l2_to_l1": {
    "aadhaar_card": "Card / credential",
    "abha_card": "Card / credential",
    "certificate": "Document",
    "ct": "Diagnostic imaging",
    "discharge_summary": "Document",
    "form": "Document",
    "headshot": "Body images",
    "insurance_document": "Document",
    "insurance_e_card": "Card / credential",
    "invoice_bill": "Document",
    "lab_diagnostic_report": "Document",
    "letter": "Document",
    "medication_image": "Miscellaneous",
    "mri": "Diagnostic imaging",
    "opd_consultation_record": "Document",
    "other_body_images": "Body images",
    "other_card": "Card / credential",
    "other_diagnostic_imaging": "Diagnostic imaging",
    "other_document": "Document",
    "other_miscellaneous": "Miscellaneous",
    "pan_card": "Card / credential",
    "pmjay_ayushman": "Card / credential",
    "scan_interpretation": "Document",
    "skin_wound": "Body images",
    "ultrasound": "Diagnostic imaging",
    "voter_id": "Card / credential",
    "x_ray": "Diagnostic imaging"
  },
  "hand_classes": [
    "printed",
    "handwritten"
  ],
  "head_hidden": 512,
  "hidden_size": 768,
  "l1_classes": [
    "Document",
    "Miscellaneous",
    "Diagnostic imaging",
    "Card / credential",
    "Body images"
  ],
  "l2_by_l1": {
    "Body images": [
      "headshot",
      "skin_wound",
      "other_body_images"
    ],
    "Card / credential": [
      "abha_card",
      "voter_id",
      "aadhaar_card",
      "insurance_e_card",
      "pan_card",
      "pmjay_ayushman",
      "other_card"
    ],
    "Diagnostic imaging": [
      "ultrasound",
      "x_ray",
      "mri",
      "ct",
      "other_diagnostic_imaging"
    ],
    "Document": [
      "letter",
      "other_document",
      "scan_interpretation",
      "lab_diagnostic_report",
      "opd_consultation_record",
      "discharge_summary",
      "insurance_document",
      "form",
      "invoice_bill",
      "certificate"
    ],
    "Miscellaneous": [
      "other_miscellaneous",
      "medication_image"
    ]
  },
  "l2_display": {
    "aadhaar_card": "Aadhaar card",
    "abha_card": "ABHA card",
    "certificate": "Certificate",
    "ct": "CT",
    "discharge_summary": "Discharge summary",
    "form": "Form",
    "headshot": "Headshot",
    "insurance_document": "Insurance document",
    "insurance_e_card": "Insurance e-card",
    "invoice_bill": "Invoice / bill",
    "lab_diagnostic_report": "Lab / diagnostic report",
    "letter": "Letter",
    "medication_image": "Medication image",
    "mri": "MRI",
    "opd_consultation_record": "OPD Consultation Record",
    "other_body_images": "Other (Body images)",
    "other_card": "Other card",
    "other_diagnostic_imaging": "Other (Diagnostic imaging)",
    "other_document": "Other document",
    "other_miscellaneous": "Other (Miscellaneous)",
    "pan_card": "PAN card",
    "pmjay_ayushman": "PMJAY / Ayushman",
    "scan_interpretation": "Scan interpretation",
    "skin_wound": "Skin / wound",
    "ultrasound": "Ultrasound",
    "voter_id": "Voter ID",
    "x_ray": "X-ray"
  },
  "max_num_patches": 1024,
  "med_classes": [
    "non_medical",
    "medical"
  ],
  "model_type": "siglip2_hier_doc",
  "qual_classes": [
    "poor",
    "good"
  ],
  "quality_score_label": "good",
  "quality_score_max": 100,
  "quality_score_min": 1,
  "sigmoid_heads": [
    "med",
    "hand",
    "qual"
  ],
  "transformers_version": "5.10.2",
  "vision_config": {
    "_name_or_path": "",
    "architectures": null,
    "attention_dropout": 0.0,
    "chunk_size_feed_forward": 0,
    "dtype": null,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "intermediate_size": 3072,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-06,
    "model_type": "siglip2_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "num_patches": 256,
    "output_attentions": false,
    "output_hidden_states": false,
    "patch_size": 16,
    "problem_type": null,
    "return_dict": true,
    "transformers_version": "5.10.2"
  }
}