Token Classification
ONNX
GLiNER2
English
onnxruntime
ner
transaction-extraction
sms-parsing
deberta
on-device
mobile
Instructions to use Sowrabhm/fintext-extractor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER2
How to use Sowrabhm/fintext-extractor with GLiNER2:
from gliner2 import AutoExtractor extractor = AutoExtractor.from_pretrained("Sowrabhm/fintext-extractor") # Extract entities text = "Apple CEO Tim Cook announced iPhone 15 in Cupertino yesterday." result = extractor.extract_entities(text, ["company", "person", "product", "location"]) print(result) - Notebooks
- Google Colab
- Kaggle
Download config.json from Sowrabhm/fintext-extractor: direct link, hf CLI and curl.
- Browser
- Download file 890 Bytes
-
https://huggingface.co/Sowrabhm/fintext-extractor/resolve/main/config.json
- Command line
-
hf download hf://Sowrabhm/fintext-extractor/config.json
-
curl -L -o config.json https://huggingface.co/Sowrabhm/fintext-extractor/resolve/main/config.json
890 Bytes
| { | |
| "model_type": "gliner2", | |
| "architecture": { | |
| "classifier": "microsoft/deberta-v3-large", | |
| "extractor": "fastino/gliner2-large-v1" | |
| }, | |
| "pipeline": "two-stage", | |
| "stages": { | |
| "classification": { | |
| "task": "is_transaction", | |
| "labels": ["non-transaction", "transaction"], | |
| "max_length": 128 | |
| }, | |
| "extraction": { | |
| "classification_task": "transaction_type", | |
| "classification_labels": ["DEBIT", "CREDIT"], | |
| "structure": "transaction_info", | |
| "fields": [ | |
| "transaction_amount", | |
| "transaction_date", | |
| "transaction_description", | |
| "masked_account_digits" | |
| ], | |
| "max_width": 8 | |
| } | |
| }, | |
| "precision_variants": ["fp16", "fp32"], | |
| "version": "1.0.0" | |
| } | |