Instructions to use djovak/multi-qa-MiniLM-L6-cos-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use djovak/multi-qa-MiniLM-L6-cos-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="djovak/multi-qa-MiniLM-L6-cos-v1")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("djovak/multi-qa-MiniLM-L6-cos-v1") model = AutoModel.from_pretrained("djovak/multi-qa-MiniLM-L6-cos-v1") - Notebooks
- Google Colab
- Kaggle
MTEB evaluation results on English language for 'multi-qa-MiniLM-L6-cos-v1' sbert model
Model and licence can be found here
- Downloads last month
- 200
Spaces using djovak/multi-qa-MiniLM-L6-cos-v1 11
🥇
mteb/leaderboard_legacy
🥇
SmileXing/leaderboard
🥇
sq66/leaderboard_legacy
🚀
reader-1/1
🥇
shiwan7788/leaderboard-uni
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported61.791
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported25.829
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported56.004
- accuracy on MTEB AmazonPolarityClassificationtest set self-reported62.361
- ap on MTEB AmazonPolarityClassificationtest set self-reported57.689
- f1 on MTEB AmazonPolarityClassificationtest set self-reported62.248
- accuracy on MTEB AmazonReviewsClassification (en)test set self-reported29.590
- f1 on MTEB AmazonReviewsClassification (en)test set self-reported29.242