d-kleine/NER_decoder

Named Entity Recognition with an decoder-only (autoregressive) LLM using HuggingFace

21
/ 100
Experimental

This project helps machine learning engineers and researchers adapt large language models (LLMs) for Named Entity Recognition (NER) tasks. It takes raw text as input and identifies specific entities like people, organizations, and locations within it, producing tagged text as output. This is for those who want to experiment with using generative LLMs for understanding tasks.

No commits in the last 6 months.

Use this if you are an AI/ML practitioner looking to explore how decoder-only LLMs like LLaMA can be fine-tuned for text understanding tasks such as Named Entity Recognition.

Not ideal if you need a production-ready, highly optimized, and thoroughly tested NER solution that generalizes well to new, unseen data, as this is a showcase project.

Named Entity Recognition Large Language Models Natural Language Processing Model Fine-tuning AI Research
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 3 / 25

How are scores calculated?

Stars

48

Forks

1

Language

Jupyter Notebook

License

Last pushed

Sep 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/d-kleine/NER_decoder"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.