Duplicate from vicgalle/gliner-small-pii

Co-authored-by: Victor Gallego <vicgalle@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+datasets:
+- urchade/synthetic-pii-ner-mistral-v1
+language:
+- en
+- fr
+- de
+- es
+- pt
+- it
+tags:
+- gliner
+- ner
+- pii
+pipeline_tag: token-classification
+---
+
+# GLiNER-small-PII
+
+This model has been trained by fine-tuning gliner-community/gliner_small-v2.5 on the urchade/synthetic-pii-ner-mistral-v1 dataset.
+
+This model is capable of recognizing various types of personally identifiable information (PII), including but not limited to these entity types: person, organization, phone number, address, passport number, email, credit card number, social security number, health insurance id number, date of birth, mobile phone number, bank account number, medication, cpf, driver's license number, tax identification number, medical condition, identity card number, national id number, ip address, email address, iban, credit card expiration date, username, health insurance number, registration number, student id number, insurance number, flight number, landline phone number, blood type, cvv, reservation number, digital signature, social media handle, license plate number, cnpj, postal code, passport_number, serial number, vehicle registration number, credit card brand, fax number, visa number, insurance company, identity document number, transaction number, national health insurance number, cvc, birth certificate number, train ticket number, passport expiration date, and social_security_number.
+
+## Usage
+
+```python
+model = GLiNER.from_pretrained("vicgalle/gliner-small-pii", load_tokenizer=True)
+
+text = """
+Harilala Rasoanaivo, un homme d'affaires local d'Antananarivo, a enregistré une nouvelle société nommée "Rasoanaivo Enterprises" au Lot II M 92 Antohomadinika. Son numéro est le +261 32 22 345 67, et son adresse électronique est harilala.rasoanaivo@telma.mg. Il a fourni son numéro de sécu 501-02-1234 pour l'enregistrement.
+"""
+
+labels = [
+    "work",
+    "booking number",
+    "personally identifiable information",
+    "driver licence",
+    "person",
+    "book",
+    "postal address",
+    "company",
+    "actor",
+    "character",
+    "email",
+    "passport number",
+    "SSN",
+    "phone number",
+]
+entities = model.predict_entities(text, labels, threshold=0.1)
+
+for entity in entities:
+    print(entity["text"], "=>", entity["label"])
+```
+
+```
+Harilala Rasoanaivo => person
+Rasoanaivo Enterprises => company
+Lot II M 92 Antohomadinika => postal address
++261 32 22 345 67 => phone number
+harilala.rasoanaivo@telma.mg => email
+501-02-1234 => SSN
+```
+
+**Note**: it may be beneficial to lower the threshold (see the previous example), to extract all related entities.

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<<ENT>>": 128001,
+  "<<SEP>>": 128002,
+  "[MASK]": 128000
+}

gliner_config.json

@@ -0,0 +1,28 @@
+{
+  "class_token_index": 128001,
+  "dropout": 0.4,
+  "encoder_config": null,
+  "ent_token": "<<ENT>>",
+  "fine_tune": true,
+  "has_rnn": true,
+  "hidden_size": 768,
+  "label_smoothing": 0.0,
+  "loss_alpha": 0.8,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
+  "max_len": 768,
+  "max_neg_type_ratio": 1,
+  "max_types": 30,
+  "max_width": 12,
+  "model_name": "microsoft/deberta-v3-small",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "random_drop": true,
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "span_mode": "markerV0",
+  "subtoken_pooling": "first",
+  "transformers_version": "4.42.3",
+  "vocab_size": 128003,
+  "words_splitter_type": "whitespace"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e903260db4c96347f7c9a4836a261e8babf898c668927b9a469f14fe5ac83700
+size 664113304

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9845a63133a53e2b2772ac057ed1aa4c693fa29e2ed8df535e7a4d5503fe307f
+size 1328293882

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a62c3af9a59ea93a22de7c132f7e09774e062c0f3cdac005c885bb91d1566fc
+size 664139970

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e5046621aff56178d1914809ed07fddbfbd2b50eb2d1d3380dbc1405ef699b
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78797c1fcbe9fd70b280d27e68851b8e8c92af669f7d85da298346afc6d2720
+size 1064

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 +1,74 @@
+{
+  "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
+    },
+    "128001": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128002": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "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"
+}

trainer_state.json

@@ -0,0 +1,165 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.716161158895428,
+  "eval_steps": 1000,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22634676324128564,
+      "grad_norm": 1076.2171630859375,
+      "learning_rate": 3.770739064856712e-06,
+      "loss": 160.1889,
+      "step": 500
+    },
+    {
+      "epoch": 0.4526935264825713,
+      "grad_norm": 881.1419677734375,
+      "learning_rate": 7.541478129713424e-06,
+      "loss": 96.3458,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4526935264825713,
+      "eval_loss": 76.46768188476562,
+      "eval_runtime": 176.6442,
+      "eval_samples_per_second": 11.118,
+      "eval_steps_per_second": 1.393,
+      "step": 1000
+    },
+    {
+      "epoch": 0.679040289723857,
+      "grad_norm": 794.5887451171875,
+      "learning_rate": 9.854124748490947e-06,
+      "loss": 80.5069,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9053870529651425,
+      "grad_norm": 963.1815795898438,
+      "learning_rate": 9.43494299128102e-06,
+      "loss": 72.5744,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9053870529651425,
+      "eval_loss": 61.90445327758789,
+      "eval_runtime": 183.6264,
+      "eval_samples_per_second": 10.696,
+      "eval_steps_per_second": 1.34,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1317338162064283,
+      "grad_norm": 921.5068359375,
+      "learning_rate": 9.015761234071095e-06,
+      "loss": 65.6815,
+      "step": 2500
+    },
+    {
+      "epoch": 1.358080579447714,
+      "grad_norm": 855.2803955078125,
+      "learning_rate": 8.596579476861168e-06,
+      "loss": 61.6207,
+      "step": 3000
+    },
+    {
+      "epoch": 1.358080579447714,
+      "eval_loss": 57.32611846923828,
+      "eval_runtime": 184.8952,
+      "eval_samples_per_second": 10.622,
+      "eval_steps_per_second": 1.33,
+      "step": 3000
+    },
+    {
+      "epoch": 1.5844273426889997,
+      "grad_norm": 1172.0072021484375,
+      "learning_rate": 8.177397719651241e-06,
+      "loss": 61.3402,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8107741059302853,
+      "grad_norm": 979.0298461914062,
+      "learning_rate": 7.758215962441316e-06,
+      "loss": 63.4637,
+      "step": 4000
+    },
+    {
+      "epoch": 1.8107741059302853,
+      "eval_loss": 54.714115142822266,
+      "eval_runtime": 178.8924,
+      "eval_samples_per_second": 10.979,
+      "eval_steps_per_second": 1.375,
+      "step": 4000
+    },
+    {
+      "epoch": 2.037120869171571,
+      "grad_norm": 2496.968017578125,
+      "learning_rate": 7.339034205231389e-06,
+      "loss": 57.3627,
+      "step": 4500
+    },
+    {
+      "epoch": 2.2634676324128566,
+      "grad_norm": 965.2960815429688,
+      "learning_rate": 6.919852448021462e-06,
+      "loss": 55.2798,
+      "step": 5000
+    },
+    {
+      "epoch": 2.2634676324128566,
+      "eval_loss": 52.85610580444336,
+      "eval_runtime": 175.63,
+      "eval_samples_per_second": 11.183,
+      "eval_steps_per_second": 1.401,
+      "step": 5000
+    },
+    {
+      "epoch": 2.4898143956541423,
+      "grad_norm": 1013.7318115234375,
+      "learning_rate": 6.500670690811537e-06,
+      "loss": 54.6516,
+      "step": 5500
+    },
+    {
+      "epoch": 2.716161158895428,
+      "grad_norm": 995.4374389648438,
+      "learning_rate": 6.08148893360161e-06,
+      "loss": 54.9203,
+      "step": 6000
+    },
+    {
+      "epoch": 2.716161158895428,
+      "eval_loss": 53.687313079833984,
+      "eval_runtime": 173.1278,
+      "eval_samples_per_second": 11.344,
+      "eval_steps_per_second": 1.421,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13254,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}