Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,93 @@
+---
+language:
+- en
+- ru
+- uk
+tags:
+- token-classification
+- ner
+- pii
+- xlm-roberta
+- transformers
+library_name: transformers
+license: apache-2.0
+base_model: xlm-roberta-large
+pipeline_tag: token-classification
+model-index:
+- name: pii-ner-nemotron
+  results:
+  - task:
+      type: token-classification
+      name: Named Entity Recognition
+    metrics:
+    - type: f1
+      value: 0.9768405285513023
+---
+
+# pii-ner-nemotron
+
+## Model summary
+
+PII NER model trained on nemotron dataset for multilingual PII entity extraction.
+
+- **Base model:** `xlm-roberta-large`
+- **Repository:** `scanpatch/pii-ner-nemotron`
+- **Training run name:** `pii-ner-nemotron`
+- **Export timestamp (UTC):** `2025-12-29T12:06:13.731145+00:00`
+
+## Labels
+
+### Entity types
+- `address`
+- `address_apartment`
+- `address_building`
+- `address_city`
+- `address_country`
+- `address_district`
+- `address_geolocation`
+- `address_house`
+- `address_postal_code`
+- `address_region`
+- `address_street`
+- `date`
+- `document_number`
+- `email`
+- `first_name`
+- `ip`
+- `last_name`
+- `middle_name`
+- `military_individual_number`
+- `mobile_phone`
+- `name`
+- `name_initials`
+- `nickname`
+- `organization`
+- `snils`
+- `tin`
+- `vehicle_number`
+
+## Evaluation
+
+| Metric | Value |
+|---|---:|
+| `test_f1` | `0.9768405285513023` |
+| `test_precision` | `0.9734942064790006` |
+| `test_recall` | `0.9802099354987895` |
+| `test_accuracy` | `0.9977181928808507` |
+| `train_runtime` | `1693.5057` |
+| `train_samples_per_second` | `238.116` |
+
+## How to use
+
+```python
+from transformers import pipeline
+
+ner = pipeline(
+    "token-classification",
+    model="scanpatch/pii-ner-nemotron",
+    aggregation_strategy="simple",
+)
+
+text = "Contact me at test@example.com and my phone is +380 67 123 45 67."
+print(ner(text))
+```

config.json

@@ -0,0 +1,141 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-address",
+    "2": "I-address",
+    "3": "B-address_apartment",
+    "4": "I-address_apartment",
+    "5": "B-address_building",
+    "6": "I-address_building",
+    "7": "B-address_city",
+    "8": "I-address_city",
+    "9": "B-address_country",
+    "10": "I-address_country",
+    "11": "B-address_district",
+    "12": "I-address_district",
+    "13": "B-address_geolocation",
+    "14": "I-address_geolocation",
+    "15": "B-address_house",
+    "16": "I-address_house",
+    "17": "B-address_postal_code",
+    "18": "I-address_postal_code",
+    "19": "B-address_region",
+    "20": "I-address_region",
+    "21": "B-address_street",
+    "22": "I-address_street",
+    "23": "B-date",
+    "24": "I-date",
+    "25": "B-document_number",
+    "26": "I-document_number",
+    "27": "B-email",
+    "28": "I-email",
+    "29": "B-first_name",
+    "30": "I-first_name",
+    "31": "B-ip",
+    "32": "I-ip",
+    "33": "B-last_name",
+    "34": "I-last_name",
+    "35": "B-middle_name",
+    "36": "I-middle_name",
+    "37": "B-military_individual_number",
+    "38": "I-military_individual_number",
+    "39": "B-mobile_phone",
+    "40": "I-mobile_phone",
+    "41": "B-name",
+    "42": "I-name",
+    "43": "B-name_initials",
+    "44": "I-name_initials",
+    "45": "B-nickname",
+    "46": "I-nickname",
+    "47": "B-organization",
+    "48": "I-organization",
+    "49": "B-snils",
+    "50": "I-snils",
+    "51": "B-tin",
+    "52": "I-tin",
+    "53": "B-vehicle_number",
+    "54": "I-vehicle_number"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-address": 1,
+    "B-address_apartment": 3,
+    "B-address_building": 5,
+    "B-address_city": 7,
+    "B-address_country": 9,
+    "B-address_district": 11,
+    "B-address_geolocation": 13,
+    "B-address_house": 15,
+    "B-address_postal_code": 17,
+    "B-address_region": 19,
+    "B-address_street": 21,
+    "B-date": 23,
+    "B-document_number": 25,
+    "B-email": 27,
+    "B-first_name": 29,
+    "B-ip": 31,
+    "B-last_name": 33,
+    "B-middle_name": 35,
+    "B-military_individual_number": 37,
+    "B-mobile_phone": 39,
+    "B-name": 41,
+    "B-name_initials": 43,
+    "B-nickname": 45,
+    "B-organization": 47,
+    "B-snils": 49,
+    "B-tin": 51,
+    "B-vehicle_number": 53,
+    "I-address": 2,
+    "I-address_apartment": 4,
+    "I-address_building": 6,
+    "I-address_city": 8,
+    "I-address_country": 10,
+    "I-address_district": 12,
+    "I-address_geolocation": 14,
+    "I-address_house": 16,
+    "I-address_postal_code": 18,
+    "I-address_region": 20,
+    "I-address_street": 22,
+    "I-date": 24,
+    "I-document_number": 26,
+    "I-email": 28,
+    "I-first_name": 30,
+    "I-ip": 32,
+    "I-last_name": 34,
+    "I-middle_name": 36,
+    "I-military_individual_number": 38,
+    "I-mobile_phone": 40,
+    "I-name": 42,
+    "I-name_initials": 44,
+    "I-nickname": 46,
+    "I-organization": 48,
+    "I-snils": 50,
+    "I-tin": 52,
+    "I-vehicle_number": 54,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c20b6ccba7df24973121e7e344e535f4eed9824d73f74dbc5d3a6a8d886771a
+size 2235637364

run_summary.json

@@ -0,0 +1,71 @@
+{
+  "run_name": "pii-ner-nemotron",
+  "base_model": "xlm-roberta-large",
+  "output_dir": "./pii_ner_outputs/nemotron",
+  "label_list": [
+    "O",
+    "B-address",
+    "I-address",
+    "B-address_apartment",
+    "I-address_apartment",
+    "B-address_building",
+    "I-address_building",
+    "B-address_city",
+    "I-address_city",
+    "B-address_country",
+    "I-address_country",
+    "B-address_district",
+    "I-address_district",
+    "B-address_geolocation",
+    "I-address_geolocation",
+    "B-address_house",
+    "I-address_house",
+    "B-address_postal_code",
+    "I-address_postal_code",
+    "B-address_region",
+    "I-address_region",
+    "B-address_street",
+    "I-address_street",
+    "B-date",
+    "I-date",
+    "B-document_number",
+    "I-document_number",
+    "B-email",
+    "I-email",
+    "B-first_name",
+    "I-first_name",
+    "B-ip",
+    "I-ip",
+    "B-last_name",
+    "I-last_name",
+    "B-middle_name",
+    "I-middle_name",
+    "B-military_individual_number",
+    "I-military_individual_number",
+    "B-mobile_phone",
+    "I-mobile_phone",
+    "B-name",
+    "I-name",
+    "B-name_initials",
+    "I-name_initials",
+    "B-nickname",
+    "I-nickname",
+    "B-organization",
+    "I-organization",
+    "B-snils",
+    "I-snils",
+    "B-tin",
+    "I-tin",
+    "B-vehicle_number",
+    "I-vehicle_number"
+  ],
+  "metrics": {
+    "train_runtime": 1693.5057,
+    "train_samples_per_second": 238.116,
+    "test_f1": 0.9768405285513023,
+    "test_precision": 0.9734942064790006,
+    "test_recall": 0.9802099354987895,
+    "test_accuracy": 0.9977181928808507
+  },
+  "timestamp_utc": "2025-12-29T12:06:13.731145+00:00"
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c4016d8a8bd86269ac4af33cd40b85f148d2ffcc4f5fd5ad35225a007cf4c2
+size 17082833

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e54f0d4c1a5b4d7460337789cf28ffb6bcd506d6d8374c066a1aace9b0e288a7
+size 5841