A try for emebdding model:
The method is the same as the stella-v2, I just fine-tuned it in a small dataset for test.
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
- 463
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 1
Evaluation results
- cos_sim_pearson on MTEB AFQMCvalidation set self-reported47.338
- cos_sim_spearman on MTEB AFQMCvalidation set self-reported49.941
- euclidean_pearson on MTEB AFQMCvalidation set self-reported48.121
- euclidean_spearman on MTEB AFQMCvalidation set self-reported49.941
- manhattan_pearson on MTEB AFQMCvalidation set self-reported48.076
- manhattan_spearman on MTEB AFQMCvalidation set self-reported49.895
- cos_sim_pearson on MTEB ATECtest set self-reported50.977
- cos_sim_spearman on MTEB ATECtest set self-reported53.113
- euclidean_pearson on MTEB ATECtest set self-reported55.121
- euclidean_spearman on MTEB ATECtest set self-reported53.113