Downloads · 30 days
5
13% of all-time downloads
farelnickholas/XLM-RoBERTa-NerGRIT-2026
XLM-RoBERTa-NerGRIT-2026 is a token classification model from farelnickholas. Use it when you need labels on individual words, such as names.
This model is a fine-tuned version of xlm-roberta-base (or specifically configured XLM-RoBERTa variant) on the NerGRIT dataset for the Indonesian language. It is designed to identify named entities such as Persons (PE…
Downloads · 30 days
5
13% of all-time downloads
All-time downloads
39
Public
Parameters
559M
4.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors2.2 GB · 99%
From the Hugging Face model README
This model is a fine-tuned version of xlm-roberta-base (or specifically configured XLM-RoBERTa variant) on the NerGRIT dataset for the Indonesian language. It is designed to identify named entities such as Persons (PER), Organizations (ORG), Locations (LOC), Geo-Political Entities (GPE), Dates/Times (DAT), Events (EVT), and Products (PRD).
You can use this model directly with the Hugging Face transformers library pipeline:
from transformers import pipeline
nlp = pipeline("ner", model="farelnickholas/XLM-RoBERTa-NerGRIT-2026", aggregation_strategy="simple")
text = "Presiden Joko Widodo meresmikan jembatan baru di Jakarta pada hari Senin."
results = nlp(text)
print(results)
This model is intended to be used for NLP research, information extraction, and automated text analysis on Indonesian texts. It may not perform optimally on heavily code-mixed languages or informal texts (e.g., highly unstructured social media abbreviations) without further domain adaptation.
The model was fine-tuned on the NerGRIT dataset, which contains carefully annotated entities for the Indonesian language.