jspringer
/

echo-mistral-7b-instruct-lasttoken

Feature Extraction

Eval Results (legacy)

text-embeddings-inference

Model card Files Files and versions

Repetition Improves Language Model Embeddings

Please refer to our paper: https://arxiv.org/abs/2402.15449

And our GitHub: https://github.com/jakespringer/echo-embeddings

We provide a description of the model as well as example usage in the above links.

Downloads last month: 59

Safetensors

Model size

7B params

Tensor type

F16

·

Paper for jspringer/echo-mistral-7b-instruct-lasttoken

Repetition Improves Language Model Embeddings

Paper • 2402.15449 • Published Feb 23, 2024 • 2

Evaluation results

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

82.970
ap on MTEB AmazonCounterfactualClassification (en)
test set self-reported

49.629
f1 on MTEB AmazonCounterfactualClassification (en)
test set self-reported

77.590
accuracy on MTEB AmazonPolarityClassification
test set self-reported

90.975
ap on MTEB AmazonPolarityClassification
test set self-reported

87.573
f1 on MTEB AmazonPolarityClassification
test set self-reported

90.967
accuracy on MTEB AmazonReviewsClassification (en)
test set self-reported

48.708
f1 on MTEB AmazonReviewsClassification (en)
test set self-reported

47.736