idT5: Indonesian Version of Multilingual T5 Transformer
Paper • 2302.00856 • Published
How to use muchad/idt5-base with Transformers:
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("muchad/idt5-base")
model = AutoModelForSeq2SeqLM.from_pretrained("muchad/idt5-base")Smaller version of the Google's Multilingual T5-base model with only Indonesian and some English embeddings.
This model has to be fine-tuned before it is useable on a downstream task.
Fine-tuned idT5 for the Question Generation and Question Answering tasks, available at idT5-qa-qg.