> ## Documentation Index
> Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Transformer RNN models

> Lucidworks AI custom embedding model training

export const LwTemplate = ({title = "Key questions to get you started", icon = "sparkles", cta = "Powered by Agent Studio", linkHref = "https://lucidworks.com/demo/?utm_source=docs&utm_medium=referral&utm_campaign=docs_cta_ai"}) => {
  const [isLoaded, setIsLoaded] = useState(false);
  useEffect(() => {
    const timer = setTimeout(() => {
      setIsLoaded(true);
    }, 500);
    return () => clearTimeout(timer);
  }, []);
  return <div className="lw-template-container">
      <Card title={title} icon={icon}>
        {isLoaded && <span dangerouslySetInnerHTML={{
    __html: `<lw-template id="a029c1a9-28be-427e-b0e1-5d918920246a"></lw-template
            >`
  }} />}
        <Link href={linkHref} className="agent-studio-link text-left text-gray-600 gap-2 dark:text-gray-400 text-sm font-medium flex flex-row items-center hover:text-primary dark:hover:text-primary-light group-hover:text-primary group-hover:dark:text-primary-light">Powered by Lucidworks Agent Studio</Link>
      </Card>
    </div>;
};

[localhost link]: http://localhost:3000/docs/lw-platform/lw-ai/lw-ai-custom-embedding-model-training/custom-embedding-transformer-rnn-models

[mintlify link]: https://doc.lucidworks.com/docs/lw-platform/lw-ai/lw-ai-custom-embedding-model-training/custom-embedding-transformer-rnn-models

[old doc.lw link]: https://doc.lucidworks.com/lw-platform/ai/gmhy47

While [recurring neural network (RNN) models](/docs/lw-platform/lw-ai/lw-ai-custom-embedding-model-training/custom-embedding-rnn-models) are powerful for tasks that demand fast inference and domain-specific tuning, such as e-commerce, Transformer RNN models excel at handling complex language understanding and are well-suited for common AI tasks like classification, prediction, and sequence modeling.

<LwTemplate />

Because a transformer RNN model uses a frozen pre-trained transformer (FPT) base, its customizability is limited.
And due to the complexity of the transformer architecture, it requires more training and inference time than RNN-only models.
However, it also delivers high-quality results with minimal tuning, even when your data is limited or noisy.

To help you get started faster, Lucidworks AI provides the models below as pre-trained bases:

* [Hugging Face all\_minilm\_l12\_rnn model](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2)
* [snowflake\_arctic\_embed\_l\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models#snowflake-arctic-embed-l-v2-0) (recommended multilingual model)
* [e5\_small\_v2\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models#e5-small-v2)
* [e5\_base\_v2\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models)
* [e5\_large\_v2\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models#e5-large-v2)
* [multilingual\_e5\_small\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models#multilingual-e5-small)
* [multilingual\_e5\_base\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models#multilingual-e5-base)
* [multilingual\_e5\_large\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models#multilingual-e5-large)
* [gte\_small\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models)
* [gte\_base\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models#gte-base)
* [gte\_large\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models)
* [snowflake\_arctic\_embed\_xs\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models#snowflake-arctic-embed-xs)
* [snowflake\_arctic\_embed\_s\_rnn](/docs/lw-platform/lw-ai/lw-ai-pre-trained-embedding-models#snowflake-arctic-embed-s)