Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Document non-strict loading of checkpoints in Fabric (#17765)
A
Adrian Wälchli committed
3cfacc7d3e9e35af7dc96d19b7a71b0bee51a50d
Parent: 24a3115
Committed by GitHub <noreply@github.com>
on 6/7/2023, 10:24:21 PM