Update README.md

README.md

@@ -29,6 +29,8 @@ This repository focuses on the 7B pretrained version, which is tailored to fit t
 The main difference between Llama-2-Ko Series and Open-Llama-2-Ko is the dataset, Open-Llama-2-Ko series only used publicly accessable Korean corpus,
 including [AI Hub](https://www.aihub.or.kr), [Modu Corpus, 모두의 말뭉치](https://corpus.korean.go.kr/) and [Korean Wikipedia](https://dumps.wikimedia.org/kowiki/).
 
+Since the train is done using only publicly available corpus, this model is opened to everyone without any restrictions. (*This model follows MIT License)
+
 ## Model Details
 
 **Model Developers** Junbum Lee (Beomi)
@@ -45,7 +47,7 @@ Open-Llama-2-Ko is an auto-regressive language model that uses an optimized tran
 
 ||Training Data|Params|Content Length|GQA|Tokens|LR|
 |---|---|---|---|---|---|---|
-|Llama 2|*A new mix of Publicly Accessable Korean Corpus*|7B|4k|&#10007;|>15B*|5e<sup>-5</sup>|
+|Llama 2|*A new mix of Publicly Accessable Korean Corpus*|7B|2k|&#10007;|>15B*|5e<sup>-5</sup>|
 
 **Train Corpus**