Failed to load vit_large_patch14_clip_336.openai

staghado / vit.cpp

Inference Vision Transformer (ViT) in plain C/C++ with ggml

MIT License

214 stars 16 forks source link

Open twmht opened 7 months ago

twmht commented 7 months ago

converter

python convert-pth-to-ggml.py --model_name vit_large_patch14_clip_336.openai --ftype 1

runner

./bin/vit -t 4 -m ../ggml-model-f16.gguf -i ../assets/tench.jpg

Any idea?

staghado commented 7 months ago

Only the original ViT is supported! The openai ViT is different