flax-community / indonesian-roberta-large

Indonesian RoBERTa Large

Indonesian RoBERTa Large is a masked language model based on the RoBERTa model. It was trained on the OSCAR dataset, specifically the unshuffled_deduplicated_id subset. The model was trained from scratch and achieved an evaluation loss of 4.801 and an evaluation accuracy of 29.8%.

This model was trained using HuggingFace's Flax framework and is part of the JAX/Flax Community Week organized by HuggingFace. All training was done on a TPUv3-8 VM, sponsored by the Google Cloud team.

All necessary scripts used for training could be found in the Files and versions tab, as well as the Training metrics logged via Tensorboard.

Model

Evaluation Results

The model was trained for 10 epochs and the following is the final result once the training ended.

How to Use

As Masked Language Model

from transformers import pipeline

pretrained_name = "flax-community/indonesian-roberta-large"

fill_mask = pipeline(
    "fill-mask",
    model=pretrained_name,
    tokenizer=pretrained_name
)

fill_mask("Budi sedang <mask> di sekolah.")

Feature Extraction in PyTorch

from transformers import RobertaModel, RobertaTokenizerFast

pretrained_name = "flax-community/indonesian-roberta-large"
model = RobertaModel.from_pretrained(pretrained_name)
tokenizer = RobertaTokenizerFast.from_pretrained(pretrained_name)

prompt = "Budi sedang berada di sekolah."
encoded_input = tokenizer(prompt, return_tensors='pt')
output = model(**encoded_input)

Team Members

• Wilson Wongso ( @w11wo )
• Steven Limcorn ( @stevenlimcorn )
• Samsul Rahmadani ( @munggok )
• Chew Kok Wah ( @chewkokwah )