jinaai/jina-embeddings-v5-text-nano-classification-mlx

pip install mlx tokenizers

git clone https://huggingface.co/jinaai/jina-embeddings-v5-text-nano-classification-mlx
cd jina-embeddings-v5-text-nano-classification-mlx

import mlx.core as mx
from tokenizers import Tokenizer
from model import JinaEmbeddingModel
import json

with open("config.json") as f:
    config = json.load(f)

model = JinaEmbeddingModel(config)
weights = mx.load("model.safetensors")
model.load_weights(list(weights.items()))

tokenizer = Tokenizer.from_file("tokenizer.json")

texts = [
    "My order hasn't arrived yet and it's been two weeks.",
    "How do I reset my password?",
    "I'd like a refund for my recent purchase.",
    "Your product exceeded my expectations. Great job!",
]
embeddings = model.encode(texts, tokenizer, task_type="classification")

@article{akram2026jina,
  title={jina-embeddings-v5-text: Task-Targeted Embedding Distillation},
  author={Mohammad Kalim Akram and Saba Sturua and Nastia Havriushenko and Quentin Herreros and Michael G{\"u}nther and Maximilian Werk and Han Xiao},
  journal={arXiv preprint arXiv:2602.15547},
  year={2026}
}