w11wo/indo-roberta-small

Indo RoBERTa Small

Indo RoBERTa Small is a masked language model based on the RoBERTa model. It was trained on the latest (late December 2020) Indonesian Wikipedia articles.

The model was trained from scratch and achieved a perplexity of 48.27 on the validation dataset (20% of the articles). Many of the techniques used are based on a Hugging Face tutorial notebook written by Sylvain Gugger, where Sylvain Gugger fine-tuned a DistilGPT-2 on Wikitext2.

Hugging Face's Transformers library was used to train the model -- utilizing the base RoBERTa model and their Trainer class. PyTorch was used as the backend framework during training, but the model remains compatible with TensorFlow nonetheless.

Model

Evaluation Results

The model was trained for 3 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 = "w11wo/indo-roberta-small"

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 = "w11wo/indo-roberta-small"
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)

Disclaimer

Do remember that although the dataset originated from Wikipedia, the model may not always generate factual texts. Additionally, the biases which came from the Wikipedia articles may be carried over into the results of this model.

Author

Indo RoBERTa Small was trained and evaluated by Wilson Wongso. All computation and development are done on Google Colaboratory using their free GPU access.