Introduction

It's clone from 'dunzhang/stella_en_400M_v5'. This version is changing the code for only using CPU for inference.

Downloads last month: 46

Safetensors

Model size

0.4B params

Tensor type

F32

Evaluation results

accuracy on MTEB AmazonCounterfactualClassification (en)
test set self-reported

92.358
ap on MTEB AmazonCounterfactualClassification (en)
test set self-reported

70.813
ap_weighted on MTEB AmazonCounterfactualClassification (en)
test set self-reported

70.813
f1 on MTEB AmazonCounterfactualClassification (en)
test set self-reported

88.951
f1_weighted on MTEB AmazonCounterfactualClassification (en)
test set self-reported

92.686
main_score on MTEB AmazonCounterfactualClassification (en)
test set self-reported

92.358
accuracy on MTEB AmazonPolarityClassification
test set self-reported

97.195
ap on MTEB AmazonPolarityClassification
test set self-reported

96.082
ap_weighted on MTEB AmazonPolarityClassification
test set self-reported

96.082
f1 on MTEB AmazonPolarityClassification
test set self-reported

97.194
f1_weighted on MTEB AmazonPolarityClassification
test set self-reported

97.194
main_score on MTEB AmazonPolarityClassification
test set self-reported

97.195
accuracy on MTEB AmazonReviewsClassification (en)
test set self-reported

59.528
f1 on MTEB AmazonReviewsClassification (en)
test set self-reported

59.210
f1_weighted on MTEB AmazonReviewsClassification (en)
test set self-reported

59.210
main_score on MTEB AmazonReviewsClassification (en)
test set self-reported

59.528
main_score on MTEB ArguAna
test set self-reported

64.240
map_at_1 on MTEB ArguAna
test set self-reported

40.398
map_at_10 on MTEB ArguAna
test set self-reported

56.215
map_at_100 on MTEB ArguAna
test set self-reported

56.834