metadata
language:
- en
Luxical One
This is a small lexical-dense text embedding model distilled for English-language symmetrical full-document text similarity and classification applications from Snowflake/snowflake-arctic-embed-m-v2.0.
Quickstart
Luxical One includes a basic HuggingFace integration that supports model inference. GPU inference is not supported (GPU "acceleration" would not provide a meaningful boost on most systems due to how fast and small the model is).
You must have the luxical package installed to run this model, and you must trust the remote code bundled with the model. Currently only cpython versions 3.11-3.13 and macos/linux operating systems are supported.
To install luxical:
pip install luxical
To load and use the model in transformers:
from transformers import AutoModel
from pathlib import Path
# Load from the Huggingface Hub.
hub_model = AutoModel.from_pretrained(
"datologyai/luxical-one",
trust_remote_code=True,
)
# Embed some text.
emb = local_model(["Luxical integrates with Huggingface."]).embeddings