| ▲ | colingauvin a day ago | |
This should be trivially demonstrable if it actually works. Cosine similarity is not a good metric, however, for attention compression. | ||
| ▲ | liventruth 8 hours ago | parent | next [-] | |
[flagged] | ||
| ▲ | liventruth 7 hours ago | parent | prev | next [-] | |
[flagged] | ||
| ▲ | liventruth 11 hours ago | parent | prev [-] | |
[dead] | ||