bhack
bhack
Do we have a review here?
If we are going in a direction where foundarional like models or their distilled/pruned version are going to be few-shot fine-tuned on the user task/dataset It Is more important that...
> If we are going in a direction where foundarional like models or thir distilled/pruned version are going to be few-shot fine-tuned on the user task/dataset It Is more important...
> I don't foresee a problem if someone wanted to refer to the official implementation while contributing a model here. If an official implementation is available then referring to it...
> It is hard to pick a side. On this my opinion is that it really depend on the model size. So we need to define what kind of models...
> Please note that I'm not talking about weight porting here anymore. It's purely about the implementation. Referring to the original model paper, framework documentation, official implementation, etc. -- these...
> If the original scripts are not reproducible, I'm not sure if we can consider converted weights reproducible. This is not always the case. An extra point is: if we...
What I mean is that if you have just ported the weights on your first point you can only use the second point to validate "the learning" part of the...
> If training from scratch can be done then no need to worry about this point in the first place. This requires that we could expect always a traing job/scripts...
Just to make another CVPR 2022 few-shot use case: https://github.com/microsoft/GLIP Can we verify, as a proxy, just the reproducibility of the few-shot task with a CI job?