add colab

README.md

@@ -45,6 +45,7 @@ Public leaderboard             |  Private leaderboard
 [MRCQuestionAnswering](https://github.com/nguyenvulebinh/extractive-qa-mrc) using [XLM-RoBERTa](https://huggingface.co/transformers/model_doc/xlmroberta.html) as a pre-trained language model. By default, XLM-RoBERTa will split word in to sub-words. But in my implementation, I re-combine sub-words representation (after encoded by BERT layer) into word representation using sum strategy.
 
 ## Using pre-trained model
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1Yqgdfaca7L94OyQVnq5iQq8wRTFvVZjv?usp=sharing)
 
 - Hugging Face pipeline style (**NOT using sum features strategy**).
 
@@ -70,8 +71,8 @@ from infer import tokenize_function, data_collator, extract_answer
 from model.mrc_model import MRCQuestionAnswering
 from transformers import AutoTokenizer
 
-# model_checkpoint = "nguyenvulebinh/vi-mrc-large"
-model_checkpoint = "nguyenvulebinh/vi-mrc-base"
+model_checkpoint = "nguyenvulebinh/vi-mrc-large"
+#model_checkpoint = "nguyenvulebinh/vi-mrc-base"
 tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
 model = MRCQuestionAnswering.from_pretrained(model_checkpoint)