Hugging Face's logo

intfloat
/
e5-base-v2

Sentence Similarity
sentence-transformers
PyTorch
ONNX
Safetensors
English
bert
mteb
Sentence Transformers
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
11

Thanks, requesting for details on instructions

#2
by gsaivinay - opened
Discussion
gsaivinay

Hello, thanks for this awesome models which is ranked high on MTEB.

Could you please provide examples for instruction prompt format to generate embedding for documents and queries?

intfloat
 Owner

E5 models are not instruction tuned.
For retrieval tasks, we prepend "query: " and "passage: " to the query and corpus passages, respectively.
For all other tasks, we prepend "query: " to the inputs.

As said in the model card, all the results can be reproduced using code at https://github.com/microsoft/unilm/tree/master/e5

Sign up or log in to comment