metadata
library_name: transformers
tags:
- ner
- named-entity-recognition
- token-classification
- pytorch
- transformers
- bert
- conll2003
- nlp
- fine-tuning
datasets:
- eriktks/conll2003
language:
- en
metrics:
- seqeval
base_model:
- google-bert/bert-base-uncased
pipeline_tag: token-classification
BERT NER — Fine-tuned Named Entity Recognition Model
Model: ELHACHYMI/bert-ner
Base model: bert-base-uncased
Task: Token Classification — Named Entity Recognition (NER)
Dataset: CoNLL-2003 (English)
Model Overview
This model is a fine-tuned version of BERT Base Uncased on the CoNLL-2003 Named Entity Recognition (NER) dataset.
It predicts the following entity types:
- PER — Person
- ORG — Organization
- LOC — Location
- MISC — Miscellaneous
- O — Outside any entity
The model is suitable for information extraction, document understanding, chatbot entity detection, and structured text processing.
Labels
The model uses the standard IOB2 tagging scheme:
| ID | Label |
|---|---|
| 0 | O |
| 1 | B-PER |
| 2 | I-PER |
| 3 | B-ORG |
| 4 | I-ORG |
| 5 | B-LOC |
| 6 | I-LOC |
| 7 | B-MISC |
| 8 | I-MISC |
How to Load the Model
Using Hugging Face Pipeline
from transformers import pipeline
ner = pipeline("ner", model="ELHACHYMI/bert-ner", aggregation_strategy="simple")
text = "Bill Gates founded Microsoft in the United States."
print(ner(text))