Instructions to use Kahouli/magento-ner-b2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use Kahouli/magento-ner-b2b with spaCy:
!pip install https://huggingface.co/Kahouli/magento-ner-b2b/resolve/main/magento-ner-b2b-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("magento-ner-b2b") # Importing as module. import magento-ner-b2b nlp = magento-ner-b2b.load() - Notebooks
- Google Colab
- Kaggle
🛒 Magento NER – Extraction d'entités pour commandes B2B
Modèle NER fine-tuné sur le catalogue Adobe Commerce / Magento. Pipeline adaptatif supportant des datasets de 3K à 100K+ exemples.
Stack technique
- spaCy
fr_core_news_lg+ tok2vec → pipeline NER fine-tuné (ce modèle) - BERT
bert-base-multilingual-cased→ pipeline alternatif viaconfig.cfg(GPU requis) - Dedup : MinHash LSH (datasketch) sur datasets ≥ 50K
- Split : stratifié par combinaison de labels
Entités reconnues
| Label | Source CSV | Exemple |
|---|---|---|
PRODUCT |
name |
Joust Duffle Bag |
SKU |
sku |
24-MB01 |
QUANTITY |
(commande) | 5, 12 |
CATEGORY |
categories |
Gear, Hoodies & Sweatshirts |
Usage rapide
import spacy
nlp = spacy.load("Kahouli/magento-ner-b2b")
doc = nlp("Je voudrais 5 Joust Duffle Bag catégorie Gear")
for ent in doc.ents:
print(ent.text, ent.label_)
- Downloads last month
- 52
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support