Model Descripstion
FEEL-IN is a state-of-the-art language model for Indonesian based on the RoBERTa model. The pre-trained model is trained using a masked language modeling (MLM) objective.
How to Use
You can use this model directly with a pipeline for masked language modeling:
from transformers import pipeline
unmasker = pipeline('fill-mask', model='ksnugroho/feelin-base-uncased')
unmasker("Adik sedang <mask> sepak bola <mask> lapangan")
Load tokenizer:
from transformers import RobertaTokenizer
tokenizer = RobertaTokenizer.from_pretrained('ksnugroho/feelin-base-uncased')
Load model in PyTorch:
from transformers import RobertaModel
model = RobertaModel.from_pretrained('ksnugroho/feelin-base-uncased')
and in TensorFlow:
from transformers import TFRobertaModel
model = TFRobertaModel.from_pretrained('ksnugroho/feelin-base-uncased')
tested with transformers==4.25.1
Authors
FEEL-IN was trained and evaluated by Kuncahyo Setyo Nugroho, Fitra Abdurrachman Bachtiar, Wayan Firdaus Mahmudy
Intelligent Systems Lab, Faculty of Computer Science, Brawijaya University, Indonesia
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.