Token Classification
Transformers
PyTorch
English
named-entity-recognition
ner
span-ner
globalpointer
Instructions to use xinyacs/ecombert-ner-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xinyacs/ecombert-ner-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="xinyacs/ecombert-ner-v1")# Load model directly from transformers import EcomBertNER model = EcomBertNER.from_pretrained("xinyacs/ecombert-ner-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "EcomBertNER" | |
| ], | |
| "model_name": "/home/jovyan/work/models/answerdotai/ModernBERT-large", | |
| "num_labels": 23, | |
| "head_size": 64, | |
| "loss_type": "circle", | |
| "use_rope": true, | |
| "dropout": 0.1, | |
| "circle_margin": 0.25, | |
| "circle_gamma": 32.0, | |
| "best_epoch": 5, | |
| "best_f1": 0.7364, | |
| "threshold": 0.45, | |
| "label_list": [ | |
| "MAIN_PRODUCT", | |
| "SUB_PRODUCT", | |
| "BRAND", | |
| "MODEL", | |
| "IP", | |
| "MATERIAL", | |
| "COLOR", | |
| "SHAPE", | |
| "PATTERN", | |
| "STYLE", | |
| "FUNCTION", | |
| "ATTRIBUTE", | |
| "COMPATIBILITY", | |
| "CROWD", | |
| "OCCASION", | |
| "LOCATION", | |
| "MEASUREMENT", | |
| "TIME", | |
| "QUANTITY", | |
| "SALE", | |
| "SHOP", | |
| "CONJ", | |
| "PREP" | |
| ] | |
| } |