cjaniake / squad_v2.0_pt Goto Github PK

Hello,
The train dataset has 40 MB which is normal, however, the dev dataset also has 40MB, which in the EN version only has 4MB...
I analyzed the first entries of both datasets and they are in fact equal...

Great after all.

I've specific questions. There is a model sagorsarker/bangla-bert-base already available for Bengali language, also a squad like dataset from google tydiqa contains questions of Bengali. So, is it possible to finetune with the model & dataset ???
run_squad.py is valid for it ?as simple as that or i Use run_squad_trainer.py ?(updated script) from huggingface repo
Any tutorials for finu-tune my own model very easily. It'll really helpful
Thank you.