Hugging Face's logo

intfloat
/
e5-large-v2

Sentence Similarity
sentence-transformers
PyTorch
Safetensors
English
bert
mteb
Sentence Transformers
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
20

Changing the dimensions of the embeddings

#9
by Suijhin - opened
Discussion
Suijhin

Hi,
I just wanted to know if its possible to get the dimension of the embedding as 512, without training again

intfloat
 Owner

As far as I know, there is no obvious way to do this without training.

But you can reduce the storage cost by using compression techniques like product quantization, which has a nice implementation in FAISS.

Sign up or log in to comment