Token Classification
GLiNER2
Safetensors
GLiNER
extractor
pii
ner
privacy
redaction
information-extraction
span-extraction
Instructions to use fastino/gliner2-privacy-filter-PII-multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER2
How to use fastino/gliner2-privacy-filter-PII-multi with GLiNER2:
from gliner2 import GLiNER2 model = GLiNER2.from_pretrained("fastino/gliner2-privacy-filter-PII-multi") # Extract entities text = "Apple CEO Tim Cook announced iPhone 15 in Cupertino yesterday." result = extractor.extract_entities(text, ["company", "person", "product", "location"]) print(result) - GLiNER
How to use fastino/gliner2-privacy-filter-PII-multi with GLiNER:
from gliner import GLiNER model = GLiNER.from_pretrained("fastino/gliner2-privacy-filter-PII-multi") - Notebooks
- Google Colab
- Kaggle
| { | |
| "add_prefix_space": true, | |
| "backend": "tokenizers", | |
| "bos_token": "[CLS]", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "eos_token": "[SEP]", | |
| "extra_special_tokens": [ | |
| "[SEP_STRUCT]", | |
| "[SEP_TEXT]", | |
| "[P]", | |
| "[C]", | |
| "[E]", | |
| "[R]", | |
| "[L]", | |
| "[EXAMPLE]", | |
| "[OUTPUT]", | |
| "[DESCRIPTION]" | |
| ], | |
| "is_local": true, | |
| "local_files_only": false, | |
| "mask_token": "[MASK]", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "sp_model_kwargs": {}, | |
| "split_by_punct": false, | |
| "tokenizer_class": "DebertaV2Tokenizer", | |
| "unk_id": 3, | |
| "unk_token": "[UNK]", | |
| "vocab_type": "spm" | |
| } | |