SudharsanSundar commited on
Commit
ba5b2f9
·
1 Parent(s): c4bdf19

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ # Model Details
2
+ - **Architecture**: Basic/default GPT-2, decoder only
3
+ - **Num params**: ~50M
4
+ - **Num tokens seen**: ~1.31 B
5
+ - **Dataset**: USPTO subset of The Pile