# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("Dongjae/mrc2reader")
model = AutoModelForQuestionAnswering.from_pretrained("Dongjae/mrc2reader")Quick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
The Reader model is for Korean Question Answering
The backbone model is deepset/xlm-roberta-large-squad2.
It is a finetuned model with KorQuAD-v1 dataset.
As a result of verification using KorQuAD evaluation dataset, it showed approximately 87% and 92% respectively for the EM score and F1 score.
Thank you
- Downloads last month
- 8
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="Dongjae/mrc2reader")