---
title: README
emoji: 🚀
colorFrom: blue
colorTo: blue
sdk: static
pinned: false
---

<style>
  a {
    text-decoration: none; /* Removes the default underline */
    color: inherit; /* Inherits the color from the parent element */
  }

  a:hover, a:focus {
    text-decoration: underline; /* Adds underline on hover or focus for better accessibility */
  }

  .link-text {
    display: inline-block; 
    vertical-align: middle; 
    font-size: 1.26em; 
    margin-right: 10px; 
    margin-left: 0px; 
    margin-top: 0px; 
    margin-bottom: 0px;
  }
</style>

<style>
  .common-button {
    background-color: white;
    color: #3c72db;
    border: 2px solid #3c72db;
    padding: 10px 25px;
    border-radius: 0.3em;
    margin: 2px;
    font-size: 1em;
    text-decoration: none;
  }
</style>

<link href='https://fonts.googleapis.com/css?family=Source+Sans+Pro' rel='stylesheet' type='text/css'>

<div align="center">
        <a>
    <img src="https://github.com/imoneoi/openchat/raw/master/assets/logo_new.png" style="width: 55%">
  </a>
    <h1 style="font-size: 1.30em; ">Advancing Open-source Language Models with Mixed-Quality Data</h1>
</div>

<p align="center" style="margin-top: 0px;">
  <a href="https://openchat.team">
    <img src="https://github.com/alpayariyak/openchat/blob/master/assets/logo_nobg.png?raw=true" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
    <span class="link-text">Online Demo</span>
  </a> |
  <a href="https://github.com/imoneoi/openchat">
    <img src="https://camo.githubusercontent.com/582429992c94328783a1509030dfd344c5845fb94be4a7b85fcf8e70b686e1b1/68747470733a2f2f6564656e742e6769746875622e696f2f537570657254696e7949636f6e732f696d616765732f706e672f6769746875622e706e67" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
    <span class="link-text">GitHub</span>
  </a> |
  <a href="https://arxiv.org/pdf/2309.11235.pdf">
    <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
    <span class="link-text">Paper</span>
  </a> |
  <a href="https://discord.gg/pQjnXvNKHY">
    <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/>
    <span class="link-text">Discord</span>
  </a>
</p>

 OpenChat is dedicated to advancing and releasing **open-source language models**, fine-tuned with our [**C-RLFT**](https://arxiv.org/pdf/2309.11235.pdf) technique, which is inspired by offline reinforcement learning. Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with `ChatGPT`, even with a `7B` model which can be run on a **consumer GPU (e.g. RTX 3090)**.

# 📰 News

- [2024/03/15] Nexusflow releases [Starling-Beta](https://huggingface.co/Nexusflow/Starling-LM-7B-beta), an RLHF-tune of openchat-3.5-1106, which is currently the highest ranking Open Source LLM on LMSys Arena not originating from a company, **beating all others at only 7B**.

- [2024/03/08] Released [OpenChat-3.5-0106-Gemma](https://huggingface.co/openchat/openchat-3.5-0106-gemma), the highest performing Gemma fine-tune.

- [2024/01/07] Released [OpenChat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106), trained with a new data pipeline - **the strongest 7B LLM in the world**.
    - Ranked as the top 7B LLM on LMSys Arena.
    - Ranked on LMSys Arena as the top open source LLM not originating from a company.

- [2023/12/10] Rleased [OpenChat-3.5-1210](https://huggingface.co/openchat/openchat-3.5-1210), 15-point improvements in coding.

- [2023/11/01] Released [OpenChat-3.5-7B](https://huggingface.co/openchat/openchat_3.5), surpassing ChatGPT on various benchmarks 🔥.

- [2023/09/21] Released our paper [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://arxiv.org/pdf/2309.11235.pdf).

# 📊 Benchmarks
| Model              | # Params | Average  | MT-Bench     | HumanEval       | BBH MC   | AGIEval  | TruthfulQA    | MMLU         | GSM8K        | BBH CoT     |
|--------------------|----------|----------|--------------|-----------------|----------|----------|---------------|--------------|--------------|-------------|
| OpenChat-3.5-0106   | **7B**   | **64.5** | 7.8      | **71.3**  | 51.5     | 49.1     | 61.0   | **65.8**     | 77.4     | 62.2     |
| OpenChat-3.5-0106-Gemma | **7B**   | 64.4     | 7.83     | 67.7      | **52.7** | **50.2** | 55.4       | 65.7     | **81.5** | 63.7     |
| OpenChat-3.5-1210  | **7B**   | 63.8 | 7.76         | 68.9        | 49.5 | 48.0 | **61.8**      | 65.3         | 77.3     | 61.8        |
| OpenChat-3.5       | **7B**   | 61.6     | 7.81         | 55.5            | 47.6     | 47.4     | 59.1          | 64.3         | **77.3**     | 63.5        |
| ChatGPT (March)*   | ?        | 61.5     | **7.94**     | 48.1            | 47.6     | 47.1     | 57.7          | 67.3     | 74.9         | **70.1**    |
|                    |          |          |              |                 |          |          |               |              |              |             |
| OpenHermes 2.5     | 7B       | 59.3     | 7.54         | 48.2            | 49.4     | 46.5     | 57.5          | 63.8         | 73.5         | 59.9        |
| OpenOrca Mistral   | 7B       | 52.7     | 6.86         | 38.4            | 49.4     | 42.9     | 45.9          | 59.3         | 59.1         | 58.1        |
| Zephyr-β^          | 7B       | 34.6     | 7.34         | 22.0            | 40.6     | 39.0     | 40.8          | 39.8         | 5.1          | 16.0        |
| Mistral            | 7B       | -        | 6.84         | 30.5            | 39.0     | 38.0     | -             | 60.1         | 52.2         | -           |
## 𝕏 Comparison with [X.AI Grok](https://x.ai/)

|                   | License     | # Param | Average  | MMLU | HumanEval | MATH     | GSM8k    |
|-------------------|-------------|---------|----------|------|-----------|----------|----------|
| **OpenChat-3.5-0106** | Apache-2.0  | **7B**  | **61.0** | 65.8   | **71.3**  | **29.3** | **77.4** |
| OpenChat 3.5 1210 | Apache-2.0  | **7B**  | 60.1 | 65.3 | 68.9  | 28.9 | 77.3 |
| OpenChat 3.5      | Apache-2.0  | **7B**  | 56.4     | 64.3 | 55.5      | 28.6     | 77.3 |
| Grok-0            | Proprietary | 33B     | 44.5     | 65.7 | 39.7      | 15.7     | 56.8     |
| Grok-1            | Proprietary | ???B    | 55.8     | **73**   | 63.2      | 23.9     | 62.9     |

# 💌Contact

**Project Lead:**
- Guan Wang [imonenext at gmail dot com]
- [Alpay Ariyak](https://github.com/alpayariyak) [aariyak at wpi dot edu]

**Main Contributors:**
- [Sijie Cheng](https://adacheng.github.io/) [csj23 at mails dot tsinghua dot edu dot cn]
- [Xianyuan Zhan](https://scholar.google.com.hk/citations?user=pDMnGloAAAAJ) (Tsinghua University)
- Qiying Yu (Tsinghua University)
- Changling Liu (GPT Desk Pte. Ltd.)
- LDJ
- AutoMeta (Alignment Lab AI)

**Sponsors:**
- [Sen Song](https://scholar.google.com/citations?user=cYgtRP4AAAAJ) (Tsinghua University)
- [Yang Liu](https://nlp.csai.tsinghua.edu.cn/~ly/) (Tsinghua University)
- [01.AI Company](https://www.lingyiwanwu.com/en)
- [RunPod](https://www.runpod.io/)