Y
Hacker News
new
|
ask
|
show
|
jobs
by
pharmakom
1188 days ago
If someone were to add noise to the llama weights and then retrain a little, would anyone be able to tell? Could that org then pass it off as their own training, MIT licensed for the good of humanity?
2 comments
visarga
1188 days ago
Could be better to permute the neurons and weight matrices in such a way as to obtain the exact same network (an isomorphic graph).
link
c1ccccc1
1188 days ago
By looking at the weights? Yes, it would be very easy to tell.
link