Is it possible to run this model with transformers.js/onnxruntime web/webgpu?
#13 opened 14 days ago
by
numinousmuses
This 4-bit ONNX version of the model is basically unusable.
#12 opened 30 days ago
by
limingde
The Section 3. json files for cpu/mobile seem to be incorrect links
#11 opened about 1 month ago
by
Dihf
running ONNX on Apple Silicon
#8 opened about 1 month ago
by
klnstpr
Now that this is quantized, what are the memory requirements?
#6 opened about 2 months ago
by
salamanders
Consider adding prebuild onnx for cpu
3
#3 opened about 2 months ago
by
234r89r23u89023rui90
Add language tag
#2 opened about 2 months ago
by
lbourdois