News for hackers. Stuff that matters.
Re:38TB of data accidentally exposed by Microsoft AI researc... by mxz3000 on Monday September 18, 2023 @12:15PM (#37558233)
at work we use the ONNX serialisation format for all of our prod models. Those get loaded by the ONNX runtime for inference. works great.

perhaps it's be viable to add support for the ONNX format even for use cases like model checkpointing during training, etc ?

There are no comments on this comment yet.