---
title: Access global models in the Registry
description: Access and deploy pre-trained, global models for predictive or generative use cases.
section_name: NextGen Registry
maturity: public-preview

---

# Access global models in the Registry {: #access-global-models-in-the-registry }

!!! info "Availability information"
    Global models in the Registry are off by default. Contact your DataRobot representative or administrator for information on enabling this feature.

    <b>Feature flag:</b> Enable Global Models in the Model Registry

Now available for public preview, you can deploy pre-trained, global models for predictive or generative use cases. These high-quality, open-source models are trained and ready for deployment, allowing you to make predictions immediately after installing DataRobot. For LLM use cases, you can find classifiers to identify prompt injection, toxicity, and sentiment, as well as a regressor to output a refusal score. Global models are available to all users; however, only administrators have edit rights.

To identify global models on the **Registry > Model directory** page, locate the **Global** column and look for models with :fontawesome-solid-globe:{.lg } **Yes**:

![](images/nxt-global-model-list.png)

You can filter the **Registry > Model directory** page to list only global models. Click :fontawesome-solid-filter:{.lg } **Filter models**, select the **Global model** check-box, then click **Apply filters**:

![](images/nxt-global-model-filter.png)

The following global models are available:

| Model                              | Type       | Target    | Description |
|------------------------------------|------------|-----------|-------------|
| Prompt Injection Classifier        | Binary     | injection | Classify text as prompt injection or legitimate. This model requires one column named `text`, containing the text to classify. For more information, see the [deberta-v3-base-injection](https://huggingface.co/deepset/deberta-v3-base-injection){ target=_blank } model details. |
| Toxicity Classifier                | Binary     | toxicity  | Classify text as toxic or non-toxic. This model requires one column named `text`, containing the text to classify. For more information, see the [toxic-comment-model](https://huggingface.co/martin-ha/toxic-comment-model){ target=_blank } details. | 
| Sentiment Classifier               | Binary     | sentiment | Classify text sentiment as positive or negative. This model requires one column named `text` containing the text to classify. For more information, see the [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english){ target=_blank } model details. |
| Refusal Score                      | Regression | target    | Outputs a maximum similarity score, comparing the input to a list of cases where an LLM has refused to answer a query because the prompt is outside the limits of what the model is configured to answer. | 
| Python Dummy Binary Classification | Binary     | target    | Always yields 0.75 for the positive class. For more information, see the [python3_dummy_binary](https://github.com/datarobot/datarobot-user-models/tree/master/model_templates/python3_dummy_binary){ target=_blank } model details. |

To clear the global model filter, in the **Filters applied** row, you can click **x** on the **Global** filter badge. You can also click **Clear all** to remove every filter applied.



