jina-embeddings-v5-text-nano-text-matching-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 = [
    "غروب جميل على الشاطئ",  # Arabic
    "海滩上美丽的日落",  # Chinese
    "Un beau coucher de soleil sur la plage",  # French
    "Ein wunderschöner Sonnenuntergang am Strand",  # German
]
embeddings = model.encode(texts, tokenizer, task_type="text-matching")