HIT-TMG

/

KaLM-embedding-multilingual-max-instruct-v1

like 4

Follow

HITsz-Text Machine Group 31

Evaluation results

• accuracy on MTEB AmazonCounterfactualClassification (en-ext)
  test set self-reported
  94.708
• ap on MTEB AmazonCounterfactualClassification (en-ext)
  test set self-reported
  63.958
• ap_weighted on MTEB AmazonCounterfactualClassification (en-ext)
  test set self-reported
  63.958
• f1 on MTEB AmazonCounterfactualClassification (en-ext)
  test set self-reported
  87.762
• f1_weighted on MTEB AmazonCounterfactualClassification (en-ext)
  test set self-reported
  95.060
• main_score on MTEB AmazonCounterfactualClassification (en-ext)
  test set self-reported
  94.708
• accuracy on MTEB AmazonCounterfactualClassification (en)
  test set self-reported
  92.612
• ap on MTEB AmazonCounterfactualClassification (en)
  test set self-reported
  71.971
• ap_weighted on MTEB AmazonCounterfactualClassification (en)
  test set self-reported
  71.971
• f1 on MTEB AmazonCounterfactualClassification (en)
  test set self-reported
  89.437