This is a slightly smaller model trained on OSCAR Sinhala dedup dataset. As Sinhala is one of those low resource languages, there are only a handful of models been trained. So, this would be a great place to start training for more downstream tasks.

Model Specification

The model chosen for training is Roberta with the following specifications:

vocab_size=52000
max_position_embeddings=514
num_attention_heads=12
num_hidden_layers=6
type_vocab_size=1

How to Use

You can use this model directly with a pipeline for masked language modeling:

from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline

model = AutoModelWithLMHead.from_pretrained("keshan/SinhalaBERTo")
tokenizer = AutoTokenizer.from_pretrained("keshan/SinhalaBERTo")

fill_mask = pipeline('fill-mask', model=model, tokenizer=tokenizer)

fill_mask("මම ගෙදර <mask>.")