Update README.md

README.md

@@ -5,7 +5,7 @@ inference: false
 
 # IndoBERT-Lite base fine-tuned on Translated SQuAD v2
 
-[IndoBERT-Lite](https://huggingface.co/indobenchmark/indobert-lite-base-p2) created by [Indo Benchmark](https://www.indobenchmark.com/) and fine-tuned on [Translated SQuAD 2.0](https://github.com/Wikidepia/indonesia_dataset/tree/master/question-answering/SQuAD) for **Q&A** downstream task.
+[IndoBERT-Lite](https://huggingface.co/indobenchmark/indobert-lite-base-p2) trained by [Indo Benchmark](https://www.indobenchmark.com/) and fine-tuned on [Translated SQuAD 2.0](https://github.com/Wikidepia/indonesia_dataset/tree/master/question-answering/SQuAD) for **Q&A** downstream task.
 
 ## Model in action
 
@@ -15,7 +15,7 @@ Fast usage with **pipelines**:
 from transformers import BertTokenizerFast, pipeline
 
 tokenizer = BertTokenizerFast.from_pretrained(
-    'Wikidepia/albert-bahasa-uncased-squad'
+    'Wikidepia/indobert-lite-squad'
 )
 qa_pipeline = pipeline(
     "question-answering",