13 points | by liventruth 5 days ago ago
5 comments
This should be trivially demonstrable if it actually works. Cosine similarity is not a good metric, however, for attention compression.
[flagged]
[dead]
This should be trivially demonstrable if it actually works. Cosine similarity is not a good metric, however, for attention compression.
[flagged]
[flagged]
[dead]
[flagged]