abdel_kareem
abdel_kareem
This is may help [small demo](https://www.kaggle.com/code/abdelkareem/dinov2-instance-retrieval)
> Does this problem still exist? It's still existing. I faced it today and solved with remove all faiss version and install the conda one from the official repo: ```py...
is there any updates!
Solved after creating a new Env with a fresh install for CUDA and pytorch then faced other errors related to Cuda, but it's working now.
I faced it again after 3 months and can't solve it now :(
for the current version, it really depends on the GPU (cuda) for the training and searching building a cpu version for the current code is not that easy, and not...
may be try to export it into the huggingface hub and then download it again, but didn't find it in the path is extremely weird.
still relevant ... and really really needed
you use the colqwen to retrive the image and then pass it into the vllm
The code about this is in the index.py file which is logging these logs. I tried to set ```py verbose=1# -1,0,False,3 ``` After reading the verbsose code from Colbert which...