← Back to context Comment by Tepix 4 hours ago How else do you want to reproduce a model if you don't have the training data? 4 comments Tepix Reply brainwad 3 hours ago Just reproduce it? Copy the weights. What I think you want is the ability to improve it, to make what in copyright would be called a derivative work. Dylan16807 2 hours ago Reproduce meaning do the same process yourself and make sure you get the same output. MisterMunchkin 1 hour ago That isn’t possible, training is non-deterministic.
brainwad 3 hours ago Just reproduce it? Copy the weights. What I think you want is the ability to improve it, to make what in copyright would be called a derivative work. Dylan16807 2 hours ago Reproduce meaning do the same process yourself and make sure you get the same output. MisterMunchkin 1 hour ago That isn’t possible, training is non-deterministic.
Dylan16807 2 hours ago Reproduce meaning do the same process yourself and make sure you get the same output. MisterMunchkin 1 hour ago That isn’t possible, training is non-deterministic.
Just reproduce it? Copy the weights. What I think you want is the ability to improve it, to make what in copyright would be called a derivative work.
Reproduce meaning do the same process yourself and make sure you get the same output.
That isn’t possible, training is non-deterministic.