---
license: llama3
language:
- en
pipeline_tag: text-generation
tags:
- distillation
- synthetic data
- function calling
- structured outputs
- json mode
---

# Hermes 2 Theta Llama-3 70B Model Card

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/GDWbCfmrJDJjRRYavWrqL.png)

## Model Description

Hermes-2 Θ (Theta) 70B is the continuation of our experimental merged model released by [Nous Research](https://nousresearch.com/), in collaboration with Charles Goddard and [Arcee AI](https://www.arcee.ai/), the team behind [MergeKit](https://github.com/arcee-ai/mergekit). 

Hermes-2 Θ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 Θ, combining the best of both worlds of each model.


![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sFhJmgamOCDJJdfjWbAQU.png)