Quark-LLM
/

quark-llm-embedding-1.5B

Eval Results (legacy)

Model card Files Files and versions

quark-llm-embedding-1.5B

Chinese Text Embedding Model developed by Alibaba Quark-LLM Team. Details will be published later.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Evaluation results

cosine_pearson on MTEB AFQMC
validation set self-reported

47.143
cosine_spearman on MTEB AFQMC
validation set self-reported

48.161
manhattan_pearson on MTEB AFQMC
validation set self-reported

46.853
manhattan_spearman on MTEB AFQMC
validation set self-reported

48.077
euclidean_pearson on MTEB AFQMC
validation set self-reported

46.935
euclidean_spearman on MTEB AFQMC
validation set self-reported

48.161
main_score on MTEB AFQMC
validation set self-reported

48.161
cosine_pearson on MTEB ATEC
test set self-reported

53.317