Update README.md

README.md

@@ -30,7 +30,7 @@ Before AlphaGo[1], Go was considered a game that was too complex for AI to maste
 In 2017, AlphaGo[1] and AlphaZero[2] defeated a Go Champion, with policy network, value network, and Monte Carlo Tree Search (MCTS)[3][4] that looks ahead.   
 MCTS is a decisive factor contributing to the world champion level performance.  
 With the recent advancement of large language model in transformer[5] based decoder with a next token prediction objective[6], and it's application in Chess[7][8], how does a language model (the GoFormer here) perform in a Go game?  
-[9] finetunes 124M, 355M, and 744M GPT-2[10] on 56,638 Go game in SGF format. To the best of the knowledge, this is the first time a language model is trained from scratch with 1.36M Go games, with a specially designed tokenizer.
+[9] finetunes 124M, 355M, and 744M GPT-2[10] on 56,638 Go game in SGF format. To the best of my knowledge, this is the first time a language model is trained from scratch with 1.36M Go games, with a specially designed tokenizer.
 
 Can GoFormer perform reasonably well just by next move (token) prediction, without MCTS[3][4]? Let's find out. 
 My research goals are that: