A harbor-current network artifact is larger than the team will later accept. Official refine skills name pruning and compression. Quantizing and restudying accuracy is out of exam scope. How should they shrink the model?

Short Explanation

The harbor-current network is too fat. Official size levers are prune, compress, or a tighter feature set. Quantization is off the exam, Translate is not pruning, and an S3 storage class does not shrink the model.

Full Explanation

Official refine skills reduce model size with pruning, compression, or a tighter feature set. Quantization is out of exam scope. Translate is not pruning, and an S3 storage class does not shrink the model itself.

×