question_generation
question_generation copied to clipboard
Support for russian language
Hello! How can i generate questions for russian language?
By using MT5Tokenizer and MT5Model, you can generate question for other language.
@mdhasanai
can you give an example code?
@mdhasanai
can you give an example code?
Use T5Tokenizer when you preprocess the data in prepare_data.py For example, use this
from transformers import MT5Tokenizer, BartTokenizer, HfArgumentParser
instead of
from transformers import T5Tokenizer, BartTokenizer, HfArgumentParser
Replace all the T5Tokenizer/T5Model with MT5Tokenizer/MT5Model
In this way, you can train and evaluate for Non-English dataset. To know more about the MT5 model, follow this link. https://huggingface.co/transformers/model_doc/mt5.html
@mdhasanai
thanks. model and Tokinezir all good
but how prepare datasets ? what data structure should be in the directory where "dev" and "train" are located?