Update README.md

4 years ago · e2f3465fe6
parent f11b97ae48
commit e2f3465fe6
1 changed files with 1 additions and 1 deletions
--- a/README.md
+++ b/README.md
@ -8,7 +8,7 @@ You only need x_t, a_t, b_t of position t to compute the vectors for position t+
 Hence it can be 100x faster than GPT, and 100x more VRAM friendly.
-See the release for a 27M params model on enwik8 with 1.65 dev perplexity (0.72 BPC).
+See the release for a **27M params model on enwik8 with 0.72 BPC(dev)**.
 ## How it works