jina-embeddings-v5-text-nano-clustering-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 = [
    "We propose a novel neural network architecture for image segmentation.",
    "This paper analyzes the effects of monetary policy on inflation.",
    "Our method achieves state-of-the-art results on object detection benchmarks.",
    "We study the relationship between interest rates and housing prices.",
]
embeddings = model.encode(texts, tokenizer, task_type="clustering")