mlx-community/multilingual-e5-large
The Model mlx-community/multilingual-e5-large was converted to MLX format from intfloat/multilingual-e5-large using mlx-lm version 0.0.3.
Use with mlx
pip install mlx-embeddings
from mlx_embeddings import load, generate
import mlx.core as mx
model, tokenizer = load("mlx-community/multilingual-e5-large")
# For text embeddings
output = generate(model, processor, texts=["I like grapes", "I like fruits"])
embeddings = output.text_embeds # Normalized embeddings
# Compute dot product between normalized embeddings
similarity_matrix = mx.matmul(embeddings, embeddings.T)
print("Similarity matrix between texts:")
print(similarity_matrix)
- Downloads last month
- 30
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Evaluation results
- accuracy on MTEB AmazonCounterfactualClassification (en)test set self-reported79.060
- ap on MTEB AmazonCounterfactualClassification (en)test set self-reported43.487
- f1 on MTEB AmazonCounterfactualClassification (en)test set self-reported73.327
- accuracy on MTEB AmazonCounterfactualClassification (de)test set self-reported71.221
- ap on MTEB AmazonCounterfactualClassification (de)test set self-reported81.558
- f1 on MTEB AmazonCounterfactualClassification (de)test set self-reported69.283
- accuracy on MTEB AmazonCounterfactualClassification (en-ext)test set self-reported80.420
- ap on MTEB AmazonCounterfactualClassification (en-ext)test set self-reported29.349
- f1 on MTEB AmazonCounterfactualClassification (en-ext)test set self-reported67.625
- accuracy on MTEB AmazonCounterfactualClassification (ja)test set self-reported77.837