Model Stock: All we need is just a few fine-tuned models
Paper • 2403.19522 • Published • 15
Kyurem
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using TaylorAI/bge-micro as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Mihaiii/Wartortle
- model: TaylorAI/bge-micro-v2
- model: TaylorAI/bge-micro
merge_method: model_stock
base_model: TaylorAI/bge-micro
- Downloads last month
- 162
Model tree for Mihaiii/test24
Spaces using Mihaiii/test24 11
Paper for Mihaiii/test24
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported66.836
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported29.377
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported60.669
- accuracy on MTEB AmazonPolarityClassificationtest set self-reported70.485
- ap on MTEB AmazonPolarityClassificationtest set self-reported64.863
- f1 on MTEB AmazonPolarityClassificationtest set self-reported70.268
- accuracy on MTEB AmazonReviewsClassification (en)test set self-reported33.652
- f1 on MTEB AmazonReviewsClassification (en)test set self-reported33.482
- map_at_1 on MTEB ArguAnatest set self-reported22.404
- map_at_10 on MTEB ArguAnatest set self-reported36.145
- map_at_100 on MTEB ArguAnatest set self-reported37.309
- map_at_1000 on MTEB ArguAnatest set self-reported37.333
- map_at_20 on MTEB ArguAnatest set self-reported37.000
- map_at_3 on MTEB ArguAnatest set self-reported31.105
- map_at_5 on MTEB ArguAnatest set self-reported34.149
- mrr_at_1 on MTEB ArguAnatest set self-reported23.186