phi-redact checkpoint + model card

README.md

@@ -0,0 +1,247 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- token-classification
+- named-entity-recognition
+- pii
+- phi
+- redaction
+- de-identification
+- ner
+- bert
+- knowledge-distillation
+- on-device
+pipeline_tag: token-classification
+---
+
+# phi-redact — compact English PII/PHI redaction model
+
+**phi-redact** is an 11M-parameter BERT-mini token classifier for detecting PII
+and PHI in English text. It covers 29 entity types with BIOES labels and is
+designed for on-device deployment (ONNX, Core ML, LiteRT) where data must not
+leave the device.
+
+It was knowledge-distilled from a 66M-parameter DistilBERT teacher and trained
+on ~157k documents spanning clinical notes, government benefits text, student
+essays, and Wikipedia-style prose.
+
+> **Not a certified de-identification solution.** This model assists redaction
+> workflows. It is **not** certified under HIPAA Expert Determination or Safe
+> Harbor methods. Evaluate it on your own data before relying on it in
+> compliance-sensitive contexts. English only.
+
+---
+
+## Model details
+
+| Property | Value |
+|---|---|
+| Architecture | BERT-mini (google/bert_uncased_L-4_H-256_A-4), 4L/256H/4A |
+| Parameters | 11.13M |
+| Labels | 121 BIOES tags (30 entity types × 4 positions + O) |
+| Max sequence length | 256 tokens |
+| Vocabulary | 30,522 WordPiece (bert-base-uncased) |
+| fp32 size | 44.5 MB |
+| fp16 size | 22.3 MB |
+| Est. 4-bit Core ML | ~5.6 MB |
+| Est. int8 LiteRT | ~11.2 MB |
+| Training method | Knowledge distillation (α=0.7) from distilbert-base-uncased teacher |
+| Language | English only |
+
+---
+
+## Entity types (30)
+
+`NAME_PATIENT` · `NAME_FAMILY` · `NAME_PROVIDER` · `DATE` · `ADDRESS` ·
+`PHONE` · `EMAIL` · `SSN` · `MRN` · `HEALTHPLAN` · `ACCOUNT` · `IDNUM` ·
+`LICENSE` · `EMPLOYER` · `PROFESSION` · `AGE` · `CITY` · `STATE` · `COUNTRY` ·
+`ZIP` · `URL` · `IP` · `DEVICE` · `ROUTING_NUMBER` · `IBAN` · `CREDITCARD` ·
+`HOSPITAL` · `FAX` · `PASSPORT` · `VIN`
+
+> **Note on TAX_ID:** included in the schema design but not in any commercial-safe
+> training source for v7 (ai4privacy excluded). TAX_ID predictions will be absent.
+> Fix queued for v8 (add EIN templates to `gen_synth.py`).
+
+---
+
+## Benchmark results (v7)
+
+Strict span-level scoring: a prediction counts only if both the character
+boundaries and the label match exactly.
+
+### Standard benchmarks
+
+| Benchmark | Recall | F1 | Notes |
+|---|---|---|---|
+| WikiANN (EN, name recall) | **84.3%** | 0.775 | CC-BY-SA 3.0; direct comparison with Desert Ant ✓ |
+| FewNERD (EN, name recall) | **85.9%** | 0.782 | CC-BY-SA 4.0; Wikipedia-prose names |
+| LA essays (Micro F1 / Recall) | 0.757 / **65.9%** | — | CC-BY 4.0; informal student prose |
+| govsynth (government benefits) | **100%** | 1.000 | Synthetic; primary deployment domain |
+| **Composite (5-benchmark recall avg)** | **86.1%** | — | See note below |
+
+Composite = (WikiANN + FewNERD + LA essays recall + govsynth + MultiNERD†) / 5.
+
+†MultiNERD (CC-BY-NC-SA 4.0) is included for completeness: v7 recall = 94.3%,
+within −0.6 pt of Desert Ant's 94.9% on the same dataset.
+
+### Nemotron-PII structured benchmark (CC-BY 4.0)
+
+First valid run — 13,134 entities across 25 entity types in 2,000 test
+documents. MICRO F1 = **0.860**, Recall = 0.843.
+
+Selected per-entity F1 scores:
+
+| Entity | F1 | Entity | F1 |
+|---|---|---|---|
+| NAME_PATIENT | 0.944 | SSN | 0.908 |
+| NAME_FAMILY | 0.937 | EMAIL | 0.905 |
+| MRN | 0.951 | CREDITCARD | 0.905 |
+| ADDRESS | 0.949 | IDNUM | 0.908 |
+| LICENSE | 0.920 | DATE | 0.859 |
+| COUNTRY | 0.919 | URL | 0.828 |
+| CITY | 0.904 | DEVICE | 0.791 |
+| ROUTING_NUMBER | 0.876 | **PROFESSION** | **0.494** |
+
+**Known weak spot — PROFESSION (F1=0.494, Precision=0.413):** the model
+over-fires on job-title nouns in non-PII context ("She saw a doctor" vs
+"Occupation: Doctor"). Not a concern for most PHI/PII redaction use cases where
+PROFESSION is rarely the sensitive entity, but flag it if your data is
+occupation-heavy.
+
+**URL in informal prose:** Nemotron URL F1=0.828 (formal text) but LA essays
+URL recall=0.318 (informal prose). The model handles URLs well in structured
+documents; it misses them in casual first-person writing.
+
+### Comparison to Desert Ant Redact v0.4.0 (English)
+
+| Metric | phi-redact v7 | Desert Ant (EN) |
+|---|---|---|
+| WikiANN name recall | **84.3%** | 69.5% |
+| MultiNERD name recall | 94.3% | **94.9%** |
+| Composite (5 benchmarks) | **86.1%** | **86.5%** |
+| Parameters | **11.13M** | 23M |
+| Est. 4-bit on-device size | **~5.6 MB** | 11.6 MB |
+| Languages | English only | 27 languages |
+| License | **Apache-2.0** | Source-available |
+
+phi-redact v7 is essentially tied with Desert Ant's English composite at half
+the parameters and half the on-device footprint.
+
+---
+
+## Training data
+
+All sources are commercial-safe (CC-BY 4.0 or CC-BY-SA 4.0). No real patient
+data was used.
+
+| Source | Size | License | Entity coverage |
+|---|---|---|---|
+| Synthetic clinical notes (gen_synth.py) | 20k | Synthetic (ours) | Full 29-type schema, clinical PHI |
+| Learning Agency Lab PII (Kaggle) | ~5,400 | CC-BY 4.0 | Names, emails, URLs in student essays |
+| govsynth (synthetic govt. benefits) | ~20k | Synthetic (ours) | SNAP/Medicaid/WIC case management PII |
+| essay_names.jsonl (synthetic prose) | 10k | Synthetic (ours) | Names in biography, news, legal, informal prose |
+| FewNERD train split (DFKI-SLT/few-nerd) | 50k | CC-BY-SA 4.0 | Wikipedia person entities |
+| WikiANN train split (EN) | ~20k | CC-BY-SA 3.0 | Wikipedia person, location, org |
+| WNUT-17 train split | ~3.4k | CC-BY 4.0 | Emerging entities in social media |
+| Nemotron-PII train split (nvidia) | 50k | CC-BY 4.0 | 30 PII/PHI types in synthetic documents |
+
+**Excluded:** ai4privacy/pii-masking-400k (non-commercial license — not used in
+training or evaluation). MultiNERD (CC-BY-NC-SA 4.0 — evaluation only, not in
+training corpus).
+
+---
+
+## Training procedure
+
+**Teacher** (distilbert-base-uncased, 66M params):
+```
+epochs 10, batch 32, lr 3e-5, cosine LR, label-smoothing 0.05, device A100
+```
+
+**Student** (this model — BERT-mini, 11.13M params):
+```
+epochs 60, batch 64, lr 5e-5, cosine LR, label-smoothing 0.05,
+distill-alpha 0.7, device A100 SXM4-40GB (~6h)
+```
+
+Knowledge distillation loss = 0.7 × KL(teacher logits ∥ student logits) + 0.3 × cross-entropy.
+
+---
+
+## How to use
+
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("CDT5058/phi-redact")
+model = AutoModelForTokenClassification.from_pretrained("CDT5058/phi-redact")
+model.eval()
+
+text = "Patient Maria Garcia, DOB 1985-03-22, MRN 4471829, called 415-555-0189."
+
+enc = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
+with torch.no_grad():
+    logits = model(**enc).logits          # [1, seq, 117]
+
+pred_ids = logits.argmax(-1)[0].tolist()  # [seq]
+id2label = model.config.id2label
+
+# Decode BIOES tags to character spans
+tokens    = tokenizer.convert_ids_to_tokens(enc["input_ids"][0])
+offsets   = enc.encodings[0].offsets      # (char_start, char_end) per token
+
+spans = []
+span_start, span_label = None, None
+for i, tag_id in enumerate(pred_ids):
+    tag = id2label[tag_id]
+    prefix, *label_parts = tag.split("-") if "-" in tag else (tag, [])
+    label = "-".join(label_parts)
+    if prefix == "S":
+        spans.append((offsets[i][0], offsets[i][1], label))
+    elif prefix == "B":
+        span_start, span_label = offsets[i][0], label
+    elif prefix == "E" and span_start is not None:
+        spans.append((span_start, offsets[i][1], span_label))
+        span_start = None
+    elif prefix in ("O", "B"):
+        span_start = None  # reset on unexpected transition
+
+for start, end, label in spans:
+    print(f"[{start}:{end}] {label!r:20s}  {text[start:end]!r}")
+```
+
+For production use, layer the deterministic `rules.py` (Luhn, ABA routing
+checksum, SSN, IBAN, regex patterns) on top — it wins on structured identifiers
+regardless of model confidence.
+
+---
+
+## Limitations
+
+- **English only.** The bert-base-uncased WordPiece vocabulary has no meaningful
+  cross-lingual representations. French, Spanish, or other languages will produce
+  silent misses — not safe degradation.
+- **PROFESSION over-fires** (F1=0.494 on Nemotron). Treat PROFESSION predictions
+  with lower confidence or disable the entity type if not needed.
+- **URL in informal prose** (recall=0.318 on student essays vs 0.828 on formal
+  text). Check URL recall on your specific document type.
+- **Trained on synthetic data.** Real-world typos, OCR noise, and unusual
+  formatting will degrade performance relative to the benchmarks above.
+- **Not a certified de-identification system.** Does not satisfy HIPAA Expert
+  Determination or Safe Harbor. Use as a detection aid alongside human review.
+
+---
+
+## License
+
+Apache-2.0. Training data licenses: CC-BY 4.0 (Nemotron-PII, LA essays,
+WNUT-17), CC-BY-SA 4.0 (FewNERD), CC-BY-SA 3.0 (WikiANN). CC-BY-SA ShareAlike
+requirements apply to the datasets, not the model weights, but consult your
+legal counsel for commercial deployment.
+
+---
+
+*Card generated 2026-09-25 · Repo: CDT5058/phi-redact*

checkpoint-157825/config.json

@@ -0,0 +1,274 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "O",
+    "1": "B-ACCOUNT",
+    "2": "I-ACCOUNT",
+    "3": "E-ACCOUNT",
+    "4": "S-ACCOUNT",
+    "5": "B-ADDRESS",
+    "6": "I-ADDRESS",
+    "7": "E-ADDRESS",
+    "8": "S-ADDRESS",
+    "9": "B-AGE",
+    "10": "I-AGE",
+    "11": "E-AGE",
+    "12": "S-AGE",
+    "13": "B-CITY",
+    "14": "I-CITY",
+    "15": "E-CITY",
+    "16": "S-CITY",
+    "17": "B-COUNTRY",
+    "18": "I-COUNTRY",
+    "19": "E-COUNTRY",
+    "20": "S-COUNTRY",
+    "21": "B-CREDITCARD",
+    "22": "I-CREDITCARD",
+    "23": "E-CREDITCARD",
+    "24": "S-CREDITCARD",
+    "25": "B-DATE",
+    "26": "I-DATE",
+    "27": "E-DATE",
+    "28": "S-DATE",
+    "29": "B-DEVICE",
+    "30": "I-DEVICE",
+    "31": "E-DEVICE",
+    "32": "S-DEVICE",
+    "33": "B-EMAIL",
+    "34": "I-EMAIL",
+    "35": "E-EMAIL",
+    "36": "S-EMAIL",
+    "37": "B-EMPLOYER",
+    "38": "I-EMPLOYER",
+    "39": "E-EMPLOYER",
+    "40": "S-EMPLOYER",
+    "41": "B-FAX",
+    "42": "I-FAX",
+    "43": "E-FAX",
+    "44": "S-FAX",
+    "45": "B-HEALTHPLAN",
+    "46": "I-HEALTHPLAN",
+    "47": "E-HEALTHPLAN",
+    "48": "S-HEALTHPLAN",
+    "49": "B-HOSPITAL",
+    "50": "I-HOSPITAL",
+    "51": "E-HOSPITAL",
+    "52": "S-HOSPITAL",
+    "53": "B-IBAN",
+    "54": "I-IBAN",
+    "55": "E-IBAN",
+    "56": "S-IBAN",
+    "57": "B-IDNUM",
+    "58": "I-IDNUM",
+    "59": "E-IDNUM",
+    "60": "S-IDNUM",
+    "61": "B-IP",
+    "62": "I-IP",
+    "63": "E-IP",
+    "64": "S-IP",
+    "65": "B-LICENSE",
+    "66": "I-LICENSE",
+    "67": "E-LICENSE",
+    "68": "S-LICENSE",
+    "69": "B-MRN",
+    "70": "I-MRN",
+    "71": "E-MRN",
+    "72": "S-MRN",
+    "73": "B-NAME_FAMILY",
+    "74": "I-NAME_FAMILY",
+    "75": "E-NAME_FAMILY",
+    "76": "S-NAME_FAMILY",
+    "77": "B-NAME_PATIENT",
+    "78": "I-NAME_PATIENT",
+    "79": "E-NAME_PATIENT",
+    "80": "S-NAME_PATIENT",
+    "81": "B-NAME_PROVIDER",
+    "82": "I-NAME_PROVIDER",
+    "83": "E-NAME_PROVIDER",
+    "84": "S-NAME_PROVIDER",
+    "85": "B-PASSPORT",
+    "86": "I-PASSPORT",
+    "87": "E-PASSPORT",
+    "88": "S-PASSPORT",
+    "89": "B-PHONE",
+    "90": "I-PHONE",
+    "91": "E-PHONE",
+    "92": "S-PHONE",
+    "93": "B-PROFESSION",
+    "94": "I-PROFESSION",
+    "95": "E-PROFESSION",
+    "96": "S-PROFESSION",
+    "97": "B-ROUTING_NUMBER",
+    "98": "I-ROUTING_NUMBER",
+    "99": "E-ROUTING_NUMBER",
+    "100": "S-ROUTING_NUMBER",
+    "101": "B-SSN",
+    "102": "I-SSN",
+    "103": "E-SSN",
+    "104": "S-SSN",
+    "105": "B-STATE",
+    "106": "I-STATE",
+    "107": "E-STATE",
+    "108": "S-STATE",
+    "109": "B-URL",
+    "110": "I-URL",
+    "111": "E-URL",
+    "112": "S-URL",
+    "113": "B-VIN",
+    "114": "I-VIN",
+    "115": "E-VIN",
+    "116": "S-VIN",
+    "117": "B-ZIP",
+    "118": "I-ZIP",
+    "119": "E-ZIP",
+    "120": "S-ZIP"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "is_decoder": false,
+  "label2id": {
+    "B-ACCOUNT": 1,
+    "B-ADDRESS": 5,
+    "B-AGE": 9,
+    "B-CITY": 13,
+    "B-COUNTRY": 17,
+    "B-CREDITCARD": 21,
+    "B-DATE": 25,
+    "B-DEVICE": 29,
+    "B-EMAIL": 33,
+    "B-EMPLOYER": 37,
+    "B-FAX": 41,
+    "B-HEALTHPLAN": 45,
+    "B-HOSPITAL": 49,
+    "B-IBAN": 53,
+    "B-IDNUM": 57,
+    "B-IP": 61,
+    "B-LICENSE": 65,
+    "B-MRN": 69,
+    "B-NAME_FAMILY": 73,
+    "B-NAME_PATIENT": 77,
+    "B-NAME_PROVIDER": 81,
+    "B-PASSPORT": 85,
+    "B-PHONE": 89,
+    "B-PROFESSION": 93,
+    "B-ROUTING_NUMBER": 97,
+    "B-SSN": 101,
+    "B-STATE": 105,
+    "B-URL": 109,
+    "B-VIN": 113,
+    "B-ZIP": 117,
+    "E-ACCOUNT": 3,
+    "E-ADDRESS": 7,
+    "E-AGE": 11,
+    "E-CITY": 15,
+    "E-COUNTRY": 19,
+    "E-CREDITCARD": 23,
+    "E-DATE": 27,
+    "E-DEVICE": 31,
+    "E-EMAIL": 35,
+    "E-EMPLOYER": 39,
+    "E-FAX": 43,
+    "E-HEALTHPLAN": 47,
+    "E-HOSPITAL": 51,
+    "E-IBAN": 55,
+    "E-IDNUM": 59,
+    "E-IP": 63,
+    "E-LICENSE": 67,
+    "E-MRN": 71,
+    "E-NAME_FAMILY": 75,
+    "E-NAME_PATIENT": 79,
+    "E-NAME_PROVIDER": 83,
+    "E-PASSPORT": 87,
+    "E-PHONE": 91,
+    "E-PROFESSION": 95,
+    "E-ROUTING_NUMBER": 99,
+    "E-SSN": 103,
+    "E-STATE": 107,
+    "E-URL": 111,
+    "E-VIN": 115,
+    "E-ZIP": 119,
+    "I-ACCOUNT": 2,
+    "I-ADDRESS": 6,
+    "I-AGE": 10,
+    "I-CITY": 14,
+    "I-COUNTRY": 18,
+    "I-CREDITCARD": 22,
+    "I-DATE": 26,
+    "I-DEVICE": 30,
+    "I-EMAIL": 34,
+    "I-EMPLOYER": 38,
+    "I-FAX": 42,
+    "I-HEALTHPLAN": 46,
+    "I-HOSPITAL": 50,
+    "I-IBAN": 54,
+    "I-IDNUM": 58,
+    "I-IP": 62,
+    "I-LICENSE": 66,
+    "I-MRN": 70,
+    "I-NAME_FAMILY": 74,
+    "I-NAME_PATIENT": 78,
+    "I-NAME_PROVIDER": 82,
+    "I-PASSPORT": 86,
+    "I-PHONE": 90,
+    "I-PROFESSION": 94,
+    "I-ROUTING_NUMBER": 98,
+    "I-SSN": 102,
+    "I-STATE": 106,
+    "I-URL": 110,
+    "I-VIN": 114,
+    "I-ZIP": 118,
+    "O": 0,
+    "S-ACCOUNT": 4,
+    "S-ADDRESS": 8,
+    "S-AGE": 12,
+    "S-CITY": 16,
+    "S-COUNTRY": 20,
+    "S-CREDITCARD": 24,
+    "S-DATE": 28,
+    "S-DEVICE": 32,
+    "S-EMAIL": 36,
+    "S-EMPLOYER": 40,
+    "S-FAX": 44,
+    "S-HEALTHPLAN": 48,
+    "S-HOSPITAL": 52,
+    "S-IBAN": 56,
+    "S-IDNUM": 60,
+    "S-IP": 64,
+    "S-LICENSE": 68,
+    "S-MRN": 72,
+    "S-NAME_FAMILY": 76,
+    "S-NAME_PATIENT": 80,
+    "S-NAME_PROVIDER": 84,
+    "S-PASSPORT": 88,
+    "S-PHONE": 92,
+    "S-PROFESSION": 96,
+    "S-ROUTING_NUMBER": 100,
+    "S-SSN": 104,
+    "S-STATE": 108,
+    "S-URL": 112,
+    "S-VIN": 116,
+    "S-ZIP": 120
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

checkpoint-157825/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcc916ab600a5005769c76ab02985962deab46b0ef491c4e6728bab8af9788d
+size 44551588

checkpoint-157825/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a74d89e0275c674e7f723ba8da133b8e84963820c54fb275206b4c1868d3704
+size 89147979

checkpoint-157825/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51013594253d661525f3cdcddcfc62db68fa3bcc51d355ec11cf1c4bbe009cff
+size 14645

checkpoint-157825/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac71a7f583a3fa4e3cb9e59c51d971b2c74789c36d13772ef35b330d403978f
+size 1465

checkpoint-157825/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc669100425ef5f78a4f7dbbc79c856016c321d168c0591c764af1be51490906
+size 5265

checkpoint-160500/config.json

@@ -0,0 +1,274 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "O",
+    "1": "B-ACCOUNT",
+    "2": "I-ACCOUNT",
+    "3": "E-ACCOUNT",
+    "4": "S-ACCOUNT",
+    "5": "B-ADDRESS",
+    "6": "I-ADDRESS",
+    "7": "E-ADDRESS",
+    "8": "S-ADDRESS",
+    "9": "B-AGE",
+    "10": "I-AGE",
+    "11": "E-AGE",
+    "12": "S-AGE",
+    "13": "B-CITY",
+    "14": "I-CITY",
+    "15": "E-CITY",
+    "16": "S-CITY",
+    "17": "B-COUNTRY",
+    "18": "I-COUNTRY",
+    "19": "E-COUNTRY",
+    "20": "S-COUNTRY",
+    "21": "B-CREDITCARD",
+    "22": "I-CREDITCARD",
+    "23": "E-CREDITCARD",
+    "24": "S-CREDITCARD",
+    "25": "B-DATE",
+    "26": "I-DATE",
+    "27": "E-DATE",
+    "28": "S-DATE",
+    "29": "B-DEVICE",
+    "30": "I-DEVICE",
+    "31": "E-DEVICE",
+    "32": "S-DEVICE",
+    "33": "B-EMAIL",
+    "34": "I-EMAIL",
+    "35": "E-EMAIL",
+    "36": "S-EMAIL",
+    "37": "B-EMPLOYER",
+    "38": "I-EMPLOYER",
+    "39": "E-EMPLOYER",
+    "40": "S-EMPLOYER",
+    "41": "B-FAX",
+    "42": "I-FAX",
+    "43": "E-FAX",
+    "44": "S-FAX",
+    "45": "B-HEALTHPLAN",
+    "46": "I-HEALTHPLAN",
+    "47": "E-HEALTHPLAN",
+    "48": "S-HEALTHPLAN",
+    "49": "B-HOSPITAL",
+    "50": "I-HOSPITAL",
+    "51": "E-HOSPITAL",
+    "52": "S-HOSPITAL",
+    "53": "B-IBAN",
+    "54": "I-IBAN",
+    "55": "E-IBAN",
+    "56": "S-IBAN",
+    "57": "B-IDNUM",
+    "58": "I-IDNUM",
+    "59": "E-IDNUM",
+    "60": "S-IDNUM",
+    "61": "B-IP",
+    "62": "I-IP",
+    "63": "E-IP",
+    "64": "S-IP",
+    "65": "B-LICENSE",
+    "66": "I-LICENSE",
+    "67": "E-LICENSE",
+    "68": "S-LICENSE",
+    "69": "B-MRN",
+    "70": "I-MRN",
+    "71": "E-MRN",
+    "72": "S-MRN",
+    "73": "B-NAME_FAMILY",
+    "74": "I-NAME_FAMILY",
+    "75": "E-NAME_FAMILY",
+    "76": "S-NAME_FAMILY",
+    "77": "B-NAME_PATIENT",
+    "78": "I-NAME_PATIENT",
+    "79": "E-NAME_PATIENT",
+    "80": "S-NAME_PATIENT",
+    "81": "B-NAME_PROVIDER",
+    "82": "I-NAME_PROVIDER",
+    "83": "E-NAME_PROVIDER",
+    "84": "S-NAME_PROVIDER",
+    "85": "B-PASSPORT",
+    "86": "I-PASSPORT",
+    "87": "E-PASSPORT",
+    "88": "S-PASSPORT",
+    "89": "B-PHONE",
+    "90": "I-PHONE",
+    "91": "E-PHONE",
+    "92": "S-PHONE",
+    "93": "B-PROFESSION",
+    "94": "I-PROFESSION",
+    "95": "E-PROFESSION",
+    "96": "S-PROFESSION",
+    "97": "B-ROUTING_NUMBER",
+    "98": "I-ROUTING_NUMBER",
+    "99": "E-ROUTING_NUMBER",
+    "100": "S-ROUTING_NUMBER",
+    "101": "B-SSN",
+    "102": "I-SSN",
+    "103": "E-SSN",
+    "104": "S-SSN",
+    "105": "B-STATE",
+    "106": "I-STATE",
+    "107": "E-STATE",
+    "108": "S-STATE",
+    "109": "B-URL",
+    "110": "I-URL",
+    "111": "E-URL",
+    "112": "S-URL",
+    "113": "B-VIN",
+    "114": "I-VIN",
+    "115": "E-VIN",
+    "116": "S-VIN",
+    "117": "B-ZIP",
+    "118": "I-ZIP",
+    "119": "E-ZIP",
+    "120": "S-ZIP"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "is_decoder": false,
+  "label2id": {
+    "B-ACCOUNT": 1,
+    "B-ADDRESS": 5,
+    "B-AGE": 9,
+    "B-CITY": 13,
+    "B-COUNTRY": 17,
+    "B-CREDITCARD": 21,
+    "B-DATE": 25,
+    "B-DEVICE": 29,
+    "B-EMAIL": 33,
+    "B-EMPLOYER": 37,
+    "B-FAX": 41,
+    "B-HEALTHPLAN": 45,
+    "B-HOSPITAL": 49,
+    "B-IBAN": 53,
+    "B-IDNUM": 57,
+    "B-IP": 61,
+    "B-LICENSE": 65,
+    "B-MRN": 69,
+    "B-NAME_FAMILY": 73,
+    "B-NAME_PATIENT": 77,
+    "B-NAME_PROVIDER": 81,
+    "B-PASSPORT": 85,
+    "B-PHONE": 89,
+    "B-PROFESSION": 93,
+    "B-ROUTING_NUMBER": 97,
+    "B-SSN": 101,
+    "B-STATE": 105,
+    "B-URL": 109,
+    "B-VIN": 113,
+    "B-ZIP": 117,
+    "E-ACCOUNT": 3,
+    "E-ADDRESS": 7,
+    "E-AGE": 11,
+    "E-CITY": 15,
+    "E-COUNTRY": 19,
+    "E-CREDITCARD": 23,
+    "E-DATE": 27,
+    "E-DEVICE": 31,
+    "E-EMAIL": 35,
+    "E-EMPLOYER": 39,
+    "E-FAX": 43,
+    "E-HEALTHPLAN": 47,
+    "E-HOSPITAL": 51,
+    "E-IBAN": 55,
+    "E-IDNUM": 59,
+    "E-IP": 63,
+    "E-LICENSE": 67,
+    "E-MRN": 71,
+    "E-NAME_FAMILY": 75,
+    "E-NAME_PATIENT": 79,
+    "E-NAME_PROVIDER": 83,
+    "E-PASSPORT": 87,
+    "E-PHONE": 91,
+    "E-PROFESSION": 95,
+    "E-ROUTING_NUMBER": 99,
+    "E-SSN": 103,
+    "E-STATE": 107,
+    "E-URL": 111,
+    "E-VIN": 115,
+    "E-ZIP": 119,
+    "I-ACCOUNT": 2,
+    "I-ADDRESS": 6,
+    "I-AGE": 10,
+    "I-CITY": 14,
+    "I-COUNTRY": 18,
+    "I-CREDITCARD": 22,
+    "I-DATE": 26,
+    "I-DEVICE": 30,
+    "I-EMAIL": 34,
+    "I-EMPLOYER": 38,
+    "I-FAX": 42,
+    "I-HEALTHPLAN": 46,
+    "I-HOSPITAL": 50,
+    "I-IBAN": 54,
+    "I-IDNUM": 58,
+    "I-IP": 62,
+    "I-LICENSE": 66,
+    "I-MRN": 70,
+    "I-NAME_FAMILY": 74,
+    "I-NAME_PATIENT": 78,
+    "I-NAME_PROVIDER": 82,
+    "I-PASSPORT": 86,
+    "I-PHONE": 90,
+    "I-PROFESSION": 94,
+    "I-ROUTING_NUMBER": 98,
+    "I-SSN": 102,
+    "I-STATE": 106,
+    "I-URL": 110,
+    "I-VIN": 114,
+    "I-ZIP": 118,
+    "O": 0,
+    "S-ACCOUNT": 4,
+    "S-ADDRESS": 8,
+    "S-AGE": 12,
+    "S-CITY": 16,
+    "S-COUNTRY": 20,
+    "S-CREDITCARD": 24,
+    "S-DATE": 28,
+    "S-DEVICE": 32,
+    "S-EMAIL": 36,
+    "S-EMPLOYER": 40,
+    "S-FAX": 44,
+    "S-HEALTHPLAN": 48,
+    "S-HOSPITAL": 52,
+    "S-IBAN": 56,
+    "S-IDNUM": 60,
+    "S-IP": 64,
+    "S-LICENSE": 68,
+    "S-MRN": 72,
+    "S-NAME_FAMILY": 76,
+    "S-NAME_PATIENT": 80,
+    "S-NAME_PROVIDER": 84,
+    "S-PASSPORT": 88,
+    "S-PHONE": 92,
+    "S-PROFESSION": 96,
+    "S-ROUTING_NUMBER": 100,
+    "S-SSN": 104,
+    "S-STATE": 108,
+    "S-URL": 112,
+    "S-VIN": 116,
+    "S-ZIP": 120
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

checkpoint-160500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b529a930350998569b94a7d91cbed0d15044c80aa1de8e4e14b510c4b1f73dda
+size 44551588

checkpoint-160500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a982dae60de5e7f162c45c2d02a70dc35843c9730dd9885749fec9e58715b541
+size 89147979

checkpoint-160500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8271d07da952d20e0256cec5c7ef7f90405baeb50ce63a34a1f0cb3372702e20
+size 14645

checkpoint-160500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd04f3d55fbb7adbc872265954bdfc22cf8a1687de20ce85512a057d295a9c7
+size 1465

checkpoint-160500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc669100425ef5f78a4f7dbbc79c856016c321d168c0591c764af1be51490906
+size 5265

config.json

@@ -0,0 +1,274 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "O",
+    "1": "B-ACCOUNT",
+    "2": "I-ACCOUNT",
+    "3": "E-ACCOUNT",
+    "4": "S-ACCOUNT",
+    "5": "B-ADDRESS",
+    "6": "I-ADDRESS",
+    "7": "E-ADDRESS",
+    "8": "S-ADDRESS",
+    "9": "B-AGE",
+    "10": "I-AGE",
+    "11": "E-AGE",
+    "12": "S-AGE",
+    "13": "B-CITY",
+    "14": "I-CITY",
+    "15": "E-CITY",
+    "16": "S-CITY",
+    "17": "B-COUNTRY",
+    "18": "I-COUNTRY",
+    "19": "E-COUNTRY",
+    "20": "S-COUNTRY",
+    "21": "B-CREDITCARD",
+    "22": "I-CREDITCARD",
+    "23": "E-CREDITCARD",
+    "24": "S-CREDITCARD",
+    "25": "B-DATE",
+    "26": "I-DATE",
+    "27": "E-DATE",
+    "28": "S-DATE",
+    "29": "B-DEVICE",
+    "30": "I-DEVICE",
+    "31": "E-DEVICE",
+    "32": "S-DEVICE",
+    "33": "B-EMAIL",
+    "34": "I-EMAIL",
+    "35": "E-EMAIL",
+    "36": "S-EMAIL",
+    "37": "B-EMPLOYER",
+    "38": "I-EMPLOYER",
+    "39": "E-EMPLOYER",
+    "40": "S-EMPLOYER",
+    "41": "B-FAX",
+    "42": "I-FAX",
+    "43": "E-FAX",
+    "44": "S-FAX",
+    "45": "B-HEALTHPLAN",
+    "46": "I-HEALTHPLAN",
+    "47": "E-HEALTHPLAN",
+    "48": "S-HEALTHPLAN",
+    "49": "B-HOSPITAL",
+    "50": "I-HOSPITAL",
+    "51": "E-HOSPITAL",
+    "52": "S-HOSPITAL",
+    "53": "B-IBAN",
+    "54": "I-IBAN",
+    "55": "E-IBAN",
+    "56": "S-IBAN",
+    "57": "B-IDNUM",
+    "58": "I-IDNUM",
+    "59": "E-IDNUM",
+    "60": "S-IDNUM",
+    "61": "B-IP",
+    "62": "I-IP",
+    "63": "E-IP",
+    "64": "S-IP",
+    "65": "B-LICENSE",
+    "66": "I-LICENSE",
+    "67": "E-LICENSE",
+    "68": "S-LICENSE",
+    "69": "B-MRN",
+    "70": "I-MRN",
+    "71": "E-MRN",
+    "72": "S-MRN",
+    "73": "B-NAME_FAMILY",
+    "74": "I-NAME_FAMILY",
+    "75": "E-NAME_FAMILY",
+    "76": "S-NAME_FAMILY",
+    "77": "B-NAME_PATIENT",
+    "78": "I-NAME_PATIENT",
+    "79": "E-NAME_PATIENT",
+    "80": "S-NAME_PATIENT",
+    "81": "B-NAME_PROVIDER",
+    "82": "I-NAME_PROVIDER",
+    "83": "E-NAME_PROVIDER",
+    "84": "S-NAME_PROVIDER",
+    "85": "B-PASSPORT",
+    "86": "I-PASSPORT",
+    "87": "E-PASSPORT",
+    "88": "S-PASSPORT",
+    "89": "B-PHONE",
+    "90": "I-PHONE",
+    "91": "E-PHONE",
+    "92": "S-PHONE",
+    "93": "B-PROFESSION",
+    "94": "I-PROFESSION",
+    "95": "E-PROFESSION",
+    "96": "S-PROFESSION",
+    "97": "B-ROUTING_NUMBER",
+    "98": "I-ROUTING_NUMBER",
+    "99": "E-ROUTING_NUMBER",
+    "100": "S-ROUTING_NUMBER",
+    "101": "B-SSN",
+    "102": "I-SSN",
+    "103": "E-SSN",
+    "104": "S-SSN",
+    "105": "B-STATE",
+    "106": "I-STATE",
+    "107": "E-STATE",
+    "108": "S-STATE",
+    "109": "B-URL",
+    "110": "I-URL",
+    "111": "E-URL",
+    "112": "S-URL",
+    "113": "B-VIN",
+    "114": "I-VIN",
+    "115": "E-VIN",
+    "116": "S-VIN",
+    "117": "B-ZIP",
+    "118": "I-ZIP",
+    "119": "E-ZIP",
+    "120": "S-ZIP"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "is_decoder": false,
+  "label2id": {
+    "B-ACCOUNT": 1,
+    "B-ADDRESS": 5,
+    "B-AGE": 9,
+    "B-CITY": 13,
+    "B-COUNTRY": 17,
+    "B-CREDITCARD": 21,
+    "B-DATE": 25,
+    "B-DEVICE": 29,
+    "B-EMAIL": 33,
+    "B-EMPLOYER": 37,
+    "B-FAX": 41,
+    "B-HEALTHPLAN": 45,
+    "B-HOSPITAL": 49,
+    "B-IBAN": 53,
+    "B-IDNUM": 57,
+    "B-IP": 61,
+    "B-LICENSE": 65,
+    "B-MRN": 69,
+    "B-NAME_FAMILY": 73,
+    "B-NAME_PATIENT": 77,
+    "B-NAME_PROVIDER": 81,
+    "B-PASSPORT": 85,
+    "B-PHONE": 89,
+    "B-PROFESSION": 93,
+    "B-ROUTING_NUMBER": 97,
+    "B-SSN": 101,
+    "B-STATE": 105,
+    "B-URL": 109,
+    "B-VIN": 113,
+    "B-ZIP": 117,
+    "E-ACCOUNT": 3,
+    "E-ADDRESS": 7,
+    "E-AGE": 11,
+    "E-CITY": 15,
+    "E-COUNTRY": 19,
+    "E-CREDITCARD": 23,
+    "E-DATE": 27,
+    "E-DEVICE": 31,
+    "E-EMAIL": 35,
+    "E-EMPLOYER": 39,
+    "E-FAX": 43,
+    "E-HEALTHPLAN": 47,
+    "E-HOSPITAL": 51,
+    "E-IBAN": 55,
+    "E-IDNUM": 59,
+    "E-IP": 63,
+    "E-LICENSE": 67,
+    "E-MRN": 71,
+    "E-NAME_FAMILY": 75,
+    "E-NAME_PATIENT": 79,
+    "E-NAME_PROVIDER": 83,
+    "E-PASSPORT": 87,
+    "E-PHONE": 91,
+    "E-PROFESSION": 95,
+    "E-ROUTING_NUMBER": 99,
+    "E-SSN": 103,
+    "E-STATE": 107,
+    "E-URL": 111,
+    "E-VIN": 115,
+    "E-ZIP": 119,
+    "I-ACCOUNT": 2,
+    "I-ADDRESS": 6,
+    "I-AGE": 10,
+    "I-CITY": 14,
+    "I-COUNTRY": 18,
+    "I-CREDITCARD": 22,
+    "I-DATE": 26,
+    "I-DEVICE": 30,
+    "I-EMAIL": 34,
+    "I-EMPLOYER": 38,
+    "I-FAX": 42,
+    "I-HEALTHPLAN": 46,
+    "I-HOSPITAL": 50,
+    "I-IBAN": 54,
+    "I-IDNUM": 58,
+    "I-IP": 62,
+    "I-LICENSE": 66,
+    "I-MRN": 70,
+    "I-NAME_FAMILY": 74,
+    "I-NAME_PATIENT": 78,
+    "I-NAME_PROVIDER": 82,
+    "I-PASSPORT": 86,
+    "I-PHONE": 90,
+    "I-PROFESSION": 94,
+    "I-ROUTING_NUMBER": 98,
+    "I-SSN": 102,
+    "I-STATE": 106,
+    "I-URL": 110,
+    "I-VIN": 114,
+    "I-ZIP": 118,
+    "O": 0,
+    "S-ACCOUNT": 4,
+    "S-ADDRESS": 8,
+    "S-AGE": 12,
+    "S-CITY": 16,
+    "S-COUNTRY": 20,
+    "S-CREDITCARD": 24,
+    "S-DATE": 28,
+    "S-DEVICE": 32,
+    "S-EMAIL": 36,
+    "S-EMPLOYER": 40,
+    "S-FAX": 44,
+    "S-HEALTHPLAN": 48,
+    "S-HOSPITAL": 52,
+    "S-IBAN": 56,
+    "S-IDNUM": 60,
+    "S-IP": 64,
+    "S-LICENSE": 68,
+    "S-MRN": 72,
+    "S-NAME_FAMILY": 76,
+    "S-NAME_PATIENT": 80,
+    "S-NAME_PROVIDER": 84,
+    "S-PASSPORT": 88,
+    "S-PHONE": 92,
+    "S-PROFESSION": 96,
+    "S-ROUTING_NUMBER": 100,
+    "S-SSN": 104,
+    "S-STATE": 108,
+    "S-URL": 112,
+    "S-VIN": 116,
+    "S-ZIP": 120
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b529a930350998569b94a7d91cbed0d15044c80aa1de8e4e14b510c4b1f73dda
+size 44551588

phi-redact-v7.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d16493517fc9fbe3839a0f18ff4ba934d3e3beba6043bf493bbf95961b1f394
+size 41967

tags.json

@@ -0,0 +1 @@
+["O", "B-ACCOUNT", "I-ACCOUNT", "E-ACCOUNT", "S-ACCOUNT", "B-ADDRESS", "I-ADDRESS", "E-ADDRESS", "S-ADDRESS", "B-AGE", "I-AGE", "E-AGE", "S-AGE", "B-CITY", "I-CITY", "E-CITY", "S-CITY", "B-COUNTRY", "I-COUNTRY", "E-COUNTRY", "S-COUNTRY", "B-CREDITCARD", "I-CREDITCARD", "E-CREDITCARD", "S-CREDITCARD", "B-DATE", "I-DATE", "E-DATE", "S-DATE", "B-DEVICE", "I-DEVICE", "E-DEVICE", "S-DEVICE", "B-EMAIL", "I-EMAIL", "E-EMAIL", "S-EMAIL", "B-EMPLOYER", "I-EMPLOYER", "E-EMPLOYER", "S-EMPLOYER", "B-FAX", "I-FAX", "E-FAX", "S-FAX", "B-HEALTHPLAN", "I-HEALTHPLAN", "E-HEALTHPLAN", "S-HEALTHPLAN", "B-HOSPITAL", "I-HOSPITAL", "E-HOSPITAL", "S-HOSPITAL", "B-IBAN", "I-IBAN", "E-IBAN", "S-IBAN", "B-IDNUM", "I-IDNUM", "E-IDNUM", "S-IDNUM", "B-IP", "I-IP", "E-IP", "S-IP", "B-LICENSE", "I-LICENSE", "E-LICENSE", "S-LICENSE", "B-MRN", "I-MRN", "E-MRN", "S-MRN", "B-NAME_FAMILY", "I-NAME_FAMILY", "E-NAME_FAMILY", "S-NAME_FAMILY", "B-NAME_PATIENT", "I-NAME_PATIENT", "E-NAME_PATIENT", "S-NAME_PATIENT", "B-NAME_PROVIDER", "I-NAME_PROVIDER", "E-NAME_PROVIDER", "S-NAME_PROVIDER", "B-PASSPORT", "I-PASSPORT", "E-PASSPORT", "S-PASSPORT", "B-PHONE", "I-PHONE", "E-PHONE", "S-PHONE", "B-PROFESSION", "I-PROFESSION", "E-PROFESSION", "S-PROFESSION", "B-ROUTING_NUMBER", "I-ROUTING_NUMBER", "E-ROUTING_NUMBER", "S-ROUTING_NUMBER", "B-SSN", "I-SSN", "E-SSN", "S-SSN", "B-STATE", "I-STATE", "E-STATE", "S-STATE", "B-URL", "I-URL", "E-URL", "S-URL", "B-VIN", "I-VIN", "E-VIN", "S-VIN", "B-ZIP", "I-ZIP", "E-ZIP", "S-ZIP"]

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 256,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc669100425ef5f78a4f7dbbc79c856016c321d168c0591c764af1be51490906
+size 5265