---
title: athene
canonical_url: "https://www.modelscope.cn/models/cortexso/athene"
md_url: "https://www.modelscope.cn/models/cortexso/athene.md"
repository: cortexso/athene
last_updated: 2025-08-29
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 102
stars: 0
tags:
  - cortex.cpp
  - gguf
---

# athene

> athene - cortexso 在 ModelScope 开源的模型。Athene-V2-Chat-72B is an open-weight LLM that competes on par with GPT-4o across various benchmarks. It is currently ranked as the best open model on Chatbot Arena, where it outperforms GPT-4o-0513 (the highest-ranked…

cortexso/athene 是 ModelScope 魔搭社区上的text-generation模型，采用 other 许可。

- **Repository**: cortexso/athene
- **License**: other
- **Tasks**: text-generation
- **Tags**: cortex.cpp, gguf
- **Downloads**: 102
- **Stars**: 0
- **Last updated**: 2025-08-29

Source: https://www.modelscope.cn/models/cortexso/athene

---

## Overview

Athene-V2-Chat-72B is an open-weight LLM that competes on par with GPT-4o across various benchmarks. It is currently ranked as the best open model on Chatbot Arena, where it outperforms GPT-4o-0513 (the highest-ranked GPT-4o model on Arena) in hard and math categories. It also matches GPT-4o-0513 in coding, instruction following, longer queries, and multi-turn conversations.

Trained through RLHF with Qwen-2.5-72B-Instruct as the base model, Athene-V2-Chat-72B excels in chat, math, and coding. Additionally, its sister model, Athene-V2-Agent-72B, surpasses GPT-4o in complex function calling and agentic applications, further extending its capabilities.
## Variants

| No | Variant | Cortex CLI command |
| --- | --- | --- |
| 1 | [Athene-72b](https://huggingface.co/cortexso/athene/tree/72b) | `cortex run athene:72b` |

## Use it with Jan (UI)

1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
2. Use in Jan model Hub:
    ```bash
    cortexhub/athene
    ```

## Use it with Cortex (CLI)

1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
2. Run the model with command:
    ```bash
    cortex run athene
    ```
    
## Credits

- **Author:** Nexusflow
- **Converter:** [Homebrew](https://homebrew.ltd/)
- **Original License:** [Licence](https://huggingface.co/Nexusflow/Athene-V2-Chat/blob/main/Nexusflow_Research_License_.pdf)
- **Papers:** [Athene V2 Blog](https://nexusflow.ai/blogs/athene-v2)