# Tavern Models

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXekOaGCC9ku_V3N6mTujRt0T6Pu6l33BELHjqDZQqErRH2wwZxUz1Q7VD3vpZ1-HZGROqrFLOW45l3HevFQ0FWbubNRADxgbzdOzcbBWQfkAfwVgzk-OFl1J-3wBehpjEmNCd_7Ed5er5_rNpPMUv-Bul-y?key=MnFKq-nRdc-nnmPeanRXjA" alt=""><figcaption></figcaption></figure>

## What is the Language model:

* A language model is a type of machine learning model trained to conduct a probability distribution over words. In simple terms, a model tries to guess the best word to put in a sentence based on what's already written.

## Why we offer different Language models:

Different models have different strengths and weaknesses and are trained for different purposes. All the Moescape Exclusive models are trained or fine-tuned for role-playing on Tavern so you can have the best experience.<br>

## Here is how to switch models on Tavern:

1. In your active chat, go to the "..." menu button in the top-right of the screen.
2. Click on 'Chat Settings'
3. Under the 'Model' section, you will be able to select the model of your choice. That's it!

***

Nephra 8B

Token Limit: 8192

Llama 3 model trained on Roleplay Datasets.<br>

Lunara 12B

Token Limit: 8192

Lunara 12B is a Mistral Nemo model trained on a roleplay dataset

Apollo 13B

Token Limit: 4096

Good writer and strong in arts and science, with well-rounded skills.

Nephra 70B

Token Limit: 8192

Llama 3 model trained on Roleplay Datasets.

Seth 70B (BETA)

Token Limit: 8192

Seth 70B is a model finetuned from LLama 3.1 on a human creative and roleplay dataset.

Tip: The larger the size, the more knowledge the model has to comprehend the context

<br>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.moescape.ai/tavern-chatbot-guide/tavern-models.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.