# 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>