News for hackers. Stuff that matters.
Re:CodeAlpaca – Instruction following code generation model by pharmakom on Saturday March 25, 2023 @03:16PM (#35306064)
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?
Re:CodeAlpaca – Instruction following code generation model by c1ccccc1 on Saturday March 25, 2023 @04:16PM (#35306821)
By looking at the weights? Yes, it would be very easy to tell.
Re:CodeAlpaca – Instruction following code generation model by visarga on Saturday March 25, 2023 @05:23PM (#35307551)
Could be better to permute the neurons and weight matrices in such a way as to obtain the exact same network (an isomorphic graph).