Qwen embedding mode inference does not work

Tried the Qwen embedding 8B with Nebius. Get errors!

1 Like

Hmm… Seems just not deployed…?

I was using Nebius as the inference provider. Do I still have to deploy??

1 Like

Oh. True. But seems working…?

Does not work when I use the sample code

1 Like

Hmm… How about updating library?

pip install -U huggingface_hub