DigitalDaimyo
/

AddressedStateAttention

addressed-state-attention

interpretable-ai

mechanistic-interpretability

Model card Files Files and versions

DigitalDaimyo commited on 24 days ago

Commit

12b15e5

·

verified ·

1 Parent(s): 008a40a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -45,4 +45,4 @@ FineWeb, 187M params: 3.73 val loss / 41.6 PPL (75k steps)
 Architecture: 21 layers, 768d, 12 heads, 16 slots
 Links
 Code: https://github.com/DigitalDaimyo/AddressedStateAttention
-Paper: https://github.com/DigitalDaimyo/AddressedStateAttention/tree/main/paper_drafts

 Architecture: 21 layers, 768d, 12 heads, 16 slots
 Links
 Code: https://github.com/DigitalDaimyo/AddressedStateAttention
+Paper: https://github.com/DigitalDaimyo/AddressedStateAttention/paper_drafts