For our >350M models, here is an example of how to load these within Colab: https://colab.research.google.com/drive/11YU00W-JLNXn-3YckJG... This little hack will force tensor alloc on GPU instead of CPU mem.
For our >350M models, here is an example of how to load these within Colab: https://colab.research.google.com/drive/11YU00W-JLNXn-3YckJG... This little hack will force tensor alloc on GPU instead of CPU mem.