Hugging Face's logo

WhereIsAI
/
UAE-Large-V1

Feature Extraction
sentence-transformers
ONNX
Safetensors
OpenVINO
Transformers
Transformers.js
English
bert
mteb
sentence_embedding
feature_extraction
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Community
29

Will there be a 2048 token length version?

#7
by kk3dmax - opened
Discussion
kk3dmax

Will there be a 2048 token length version? (512 is not enough for most RAG tasks).
SeanLee97
 WhereIsAI org

Hi @kk3dmax , thanks for following our work!

Yes, we are working on an efficient smaller model.
It also supports longer context (>4090).
Stay tuned :)
kk3dmax

Thanks bro!
mzhadigerov

any news @SeanLee97 ? :)

yousefmrashad

Hello, @SeanLee97 ! I would like to express my great admiration to you and your team for your amazing work! :) I would also like to add that I'm an undergrad currently working on a RAG application as a graduation project, and it relies on your embedding model. Therefore I'm very eager to hear any news about your upcoming model. Keep up the good work!

Sign up or log in to comment