Update README.md

README.md

@@ -13,8 +13,9 @@ also sorry I just realized theres some residual from where I copied the model co
 | cerebras 111m | 21.550655364990234 | 2.2b |
 | cerebras 256m | 15.203496932983398 | 5.1b |
 | cerebras 590m | 12.098200798034668 | 11.something b |
-| pythia 70m (95.6M) | 22.393400192260742 | 300b |
-| pythia 160m (213M) | 13.933751106262207 | 300b |
+| deduped pythia 70m (95.6M) | 22.393400192260742 | 300b |
+| deduped pythia 160m (213M) | 13.933751106262207 | 300b |
+| deduped pythia 410m (506M) | 9.61842155456543 | 300b |
 | llama w same settings as cerebras 111m (119m) | 13.882301330566406 | 2.2b |
 | llama plus w same settings as cerebras 111m and llama 70b embeddings (369m) | 13.565109252929688 | 2.2b |
 | **GLORT2 (205m)** | 13.051741600036621 | 2.2b |