Update README.md

README.md

@@ -35,7 +35,7 @@ Polyglot-Ko was trained on 1.2TB Korean Dataset, a large-scale curated dataset c
 
 ## Training procedure
 
-Polyglot-Ko was trained for 213 billion tokens over 102,000 steps on 256 * A100 GPUs. It was trained as an autoregressive language model, using cross-entropy loss to maximize the likelihood of predicting the next token correctly.
+Polyglot-Ko was trained for 213 billion tokens over 102,000 steps on 256 * A100 GPUs with [GPT-NeoX framework](https://github.com/EleutherAI/gpt-neox). It was trained as an autoregressive language model, using cross-entropy loss to maximize the likelihood of predicting the next token correctly. 
 
 ## How to use