wsinfer.modellib.models#

Classes#

`get_registered_model`(...)
`get_pretrained_torch_module`(→ torch.nn.Module)	Get a PyTorch Module with weights loaded.
`jit_compile`(...)	JIT-compile a model for inference.

class wsinfer.modellib.models.LocalModelTorchScript[source]#: Bases: wsinfer_zoo.client.Model

wsinfer.modellib.models.get_registered_model(name: str) → wsinfer_zoo.client.HFModelTorchScript[source]#

wsinfer.modellib.models.get_pretrained_torch_module(model: wsinfer_zoo.client.HFModelTorchScript | LocalModelTorchScript) → torch.nn.Module[source]#: Get a PyTorch Module with weights loaded.

wsinfer.modellib.models.jit_compile(model: torch.nn.Module) → torch.jit.ScriptModule | torch.nn.Module | Callable[source]#

JIT-compile a model for inference.

A torchscript model may be JIT compiled here as well.