Optimized and quantized of the original model
Optimization format: ONNX
Quantization: int8
Original model is available at intfloat/multilingual-e5-small
- Downloads last month
- 18
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported73.791
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported37.000
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported67.955
- accuracy on MTEB AmazonCounterfactualClassification (de)test set self-reported71.649
- ap on MTEB AmazonCounterfactualClassification (de)test set self-reported82.119
- f1 on MTEB AmazonCounterfactualClassification (de)test set self-reported69.880
- accuracy on MTEB AmazonCounterfactualClassification (en-ext)test set self-reported75.810
- ap on MTEB AmazonCounterfactualClassification (en-ext)test set self-reported24.469
from sentence_transformers import SentenceTransformer model = SentenceTransformer("deepfile/multilingual-e5-small-onnx-qint8") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3]