OneMI_Gliner_v2.1

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This is a Named Entity Recognition (NER) model capable of identifying finance related entity type using a bidirectional transformer encoder (BERT-like).

Model Description

<!-- Provide a longer summary of what this model is. -->

This model is trined on custom dataset provided for a specific usecase. The base model is urchade/gliner_large-v2.1

• Developed by: [Tredence Analytics Solutions Pvt Ltd]
• Language(s) (NLP): [English]
• License: [apache-2.0]
• Finetuned from model [optional]: urchade/gliner_large-v2.1

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

Installation

To use this model, you must install the GLiNER Python library. To install, simply run:

!pip install gliner

Usage

from gliner import GLiNER

model = GLiNER.from_pretrained("Abhishek4907/OneMI_Gliner_v2.1")

query = "What is g&a for group treasury"
labels = ["coa value", "measure", "gl measure", "coa variation", "measure variation"]

entity_classification = model.predict_entities(text = query, return_scores = True, multi_label = True, threshold = 0.9, labels = labels)
print(entity_classification)