A try for emebdding model:

The method is the same as the stella-v2, I just extend the length of the context on tao.(I found if you want to use the fully-8k context, you maybe need to convert the model to float32).

Now I'm working on the tao-v2, It will have a different sturcture.

I will release tao-v2 as fast as I can.

Thank you to the open source community.

Downloads last month: 564

Inference API

Sentence Similarity

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using Amu/tao-8k 1

Collection including Amu/tao-8k

RAG

Collection

the best collection of RAG model, like embedding, ranker etc. • 1 item • Updated Apr 11 • 1

Evaluation results

cos_sim_pearson on MTEB AFQMC
validation set self-reported

47.336
cos_sim_spearman on MTEB AFQMC
validation set self-reported

49.940
euclidean_pearson on MTEB AFQMC
validation set self-reported

48.120
euclidean_spearman on MTEB AFQMC
validation set self-reported

49.940
manhattan_pearson on MTEB AFQMC
validation set self-reported

48.074
manhattan_spearman on MTEB AFQMC
validation set self-reported

49.892
cos_sim_pearson on MTEB ATEC
test set self-reported

50.976
cos_sim_spearman on MTEB ATEC
test set self-reported

53.112
euclidean_pearson on MTEB ATEC
test set self-reported

55.120
euclidean_spearman on MTEB ATEC
test set self-reported

53.112

View on Papers With Code