Upload folder using huggingface_hub

README.md

@@ -0,0 +1,129 @@
+---
+language:
+  - en
+  - fr
+  - de
+  - it
+license: apache-2.0
+library_name: transformers
+tags:
+  - pii
+  - ner
+  - token-classification
+  - privacy
+  - deberta-v3
+datasets:
+  - ai4privacy/pii-masking-200k
+  - nvidia/Nemotron-PII
+metrics:
+  - f1
+  - precision
+  - recall
+pipeline_tag: token-classification
+model-index:
+  - name: pii-deberta-v3-base-multi
+    results:
+      - task:
+          type: token-classification
+          name: PII Detection (NER)
+        metrics:
+          - type: f1
+            value: 0.9766
+            name: Entity-level F1
+          - type: precision
+            value: 0.9703
+            name: Entity-level Precision
+          - type: recall
+            value: 0.9830
+            name: Entity-level Recall
+---
+
+# PII Detection — DeBERTa-v3-base (Multi-Dataset)
+
+A token classification (NER) model for **Personally Identifiable Information (PII) detection**, fine-tuned on a combination of [ai4privacy/pii-masking-200k](https://huggingface.co/datasets/ai4privacy/pii-masking-200k) and [nvidia/Nemotron-PII](https://huggingface.co/datasets/nvidia/Nemotron-PII) datasets.
+
+## Model Description
+
+- **Base model**: [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base)
+- **Task**: Token Classification (BIO tagging)
+- **Loss**: Focal Loss (alpha=1.0, gamma=2.0)
+- **Parameters**: 183M
+
+## Supported Entity Types (7 types, Kaggle PII standard)
+
+| Entity | Description | F1 |
+|--------|-------------|-----|
+| `NAME_STUDENT` | Person names | 0.979 |
+| `EMAIL` | Email addresses | 0.992 |
+| `USERNAME` | Usernames | 0.980 |
+| `ID_NUM` | ID numbers (SSN, credit card, passport, etc.) | 0.980 |
+| `PHONE_NUM` | Phone numbers | 0.992 |
+| `URL_PERSONAL` | Personal URLs | 0.992 |
+| `STREET_ADDRESS` | Street addresses | 0.958 |
+
+## Usage
+
+```python
+from transformers import AutoModelForTokenClassification, AutoTokenizer
+import torch
+
+model_name = "seongyeon1/pii-deberta-v3-base-multi"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForTokenClassification.from_pretrained(model_name)
+
+text = "My name is John Smith and my email is john@example.com"
+inputs = tokenizer(text, return_tensors="pt", return_offsets_mapping=True)
+offset_mapping = inputs.pop("offset_mapping")
+
+with torch.no_grad():
+    outputs = model(**inputs)
+    predictions = torch.argmax(outputs.logits, dim=-1)[0]
+
+for idx, (pred, (start, end)) in enumerate(zip(predictions, offset_mapping[0])):
+    label = model.config.id2label[pred.item()]
+    if label != "O" and start != 0 and end != 0:
+        print(f"{text[start:end]} -> {label}")
+```
+
+## Training Details
+
+| Setting | Value |
+|---------|-------|
+| Epochs | 3 |
+| Learning Rate | 2e-5 |
+| Batch Size | 8 |
+| Max Length | 256 |
+| Warmup Steps | 200 |
+| Optimizer | AdamW |
+| Training Data | ~9,000 samples (ai4privacy 5K + Nemotron 5K) |
+| Training Time | ~29 minutes (Apple MPS) |
+
+### Label Merge Strategy
+
+54+ entity types from source datasets are merged into 7 standard Kaggle PII types:
+- `FIRSTNAME`, `LASTNAME`, `GIVENNAME`, `SURNAME` → `NAME_STUDENT`
+- `SSN`, `CREDITCARDNUMBER`, `IBAN`, `PASSPORT`, ... → `ID_NUM`
+- `PHONENUMBER`, `TEL`, `TELEPHONENUM` → `PHONE_NUM`
+- `CITY`, `STATE`, `ZIPCODE`, `STREET` → `STREET_ADDRESS`
+
+## Evaluation Results
+
+| Metric | Score |
+|--------|-------|
+| **F1 (entity-level)** | **0.9766** |
+| Precision | 0.9703 |
+| Recall | 0.9830 |
+| F5 (recall-weighted) | 0.9825 |
+| Eval Loss | 0.0014 |
+
+## Training Loss Curve
+
+| Epoch | Train Loss | Eval F1 | Eval F5 |
+|-------|-----------|---------|---------|
+| 1 | 0.0039 | 0.9434 | 0.9560 |
+| 2 | 0.0023 | 0.9738 | 0.9777 |
+| 3 | 0.0012 | 0.9766 | 0.9825 |
+
+## Framework
+
+Built with [PolyBed-Pipeline](https://github.com/teddynote-lab/PolyBed-Pipeline) PII Channel.

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-NAME_STUDENT",
+    "2": "I-NAME_STUDENT",
+    "3": "B-EMAIL",
+    "4": "I-EMAIL",
+    "5": "B-USERNAME",
+    "6": "I-USERNAME",
+    "7": "B-ID_NUM",
+    "8": "I-ID_NUM",
+    "9": "B-PHONE_NUM",
+    "10": "I-PHONE_NUM",
+    "11": "B-URL_PERSONAL",
+    "12": "I-URL_PERSONAL",
+    "13": "B-STREET_ADDRESS",
+    "14": "I-STREET_ADDRESS"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EMAIL": 3,
+    "B-ID_NUM": 7,
+    "B-NAME_STUDENT": 1,
+    "B-PHONE_NUM": 9,
+    "B-STREET_ADDRESS": 13,
+    "B-URL_PERSONAL": 11,
+    "B-USERNAME": 5,
+    "I-EMAIL": 4,
+    "I-ID_NUM": 8,
+    "I-NAME_STUDENT": 2,
+    "I-PHONE_NUM": 10,
+    "I-STREET_ADDRESS": 14,
+    "I-URL_PERSONAL": 12,
+    "I-USERNAME": 6,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b29afa36ae49d95cb49f6593446f5b1d9391b4cf3e1e196ab95af2978dd149
+size 735396724

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d40987a7feeea80402039315e6f3712bf13c8d003305d6bd97f639807b80d03
+size 5777