You can deploy this model and start earning money today!

rajaadil/
finer-ord-ner

Name: finer-ord-ner
Availability: InStock

safetensors

bert

Views

No views yet

card = """--- license: apache-2.0 language: en base_model: bert-base-cased tags:

token-classification
named-entity-recognition
finance
finer-ord datasets:
gtfintechlab/finer-ord metrics:
precision
recall
f1 pipeline_tag: token-classification

FiNER-ORD NER (BERT-base-cased)

Fine-tuned bert-base-cased for named entity recognition on financial text, trained on the FiNER-ORD dataset. Recognises persons (PER), locations (LOC), and organisations (ORG) in financial news and filings.

Results (validation set)

Metric	Score
Precision	0.840
Recall	0.856
F1	0.848
Accuracy	0.984

Trained for 3 epochs, batch size 16, learning rate 2e-5, best checkpoint selected on F1.

Label scheme

O, B-PER, I-PER, B-LOC, I-LOC, B-ORG, I-ORG

Usage

python

from transformers import pipeline

ner = pipeline("token-classification", model="rajaadil/finer-ord-ner",
               aggregation_strategy="simple")
ner("Goldman Sachs analyst John Smith met clients in London.")

Author

Adil Hussain — Hugging Face """

from huggingface_hub import ModelCard ModelCard(card).push_to_hub("rajaadil/finer-ord-ner")