search

theirstory / gliner-spacy

A spaCy wrapper for GliNER
MIT License
91 stars 8 forks source link

Fix documentation regarding the GPU/CUDA `map_location` value #17

Closed eriknovak closed 5 months ago

eriknovak commented 5 months ago

The map_location value is used to determine the device on which GLiNER is run. This is done using torch.device, which supports cuda for running it on the GPU. The value gpu is not supported as shown in the following RuntimeError:

RuntimeError: Expected one of cpu, cuda, ipu, xpu, mkldnn, opengl, opencl, ideep, hip, ve, fpga, ort, xla, lazy, vulkan, mps, meta, hpu, mtia, privateuseone device type at start of device string: gpu
wjbmattingly commented 5 months ago

Ah, thanks for catching that! =)

eriknovak commented 5 months ago

Not a problem! I really like this project, so I am glad to contribute :)

wjbmattingly commented 5 months ago

I'm so happy to hear that!