README.md

---
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>

<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: 65%">
  </a>
    <h1 style="font-size: 1.50em; ">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/logo_new-removebg-preview.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 of OpenChat 3.5</span>
  </a> |
  <a href="https://github.com/imoneoi/openchat">
    <img src="https://camo.githubusercontent.com/4133dc1cd4511d4a292b84ce10e52e4ed92569fb2a8165381c9c47be5edc2796/68747470733a2f2f6564656e742e6769746875622e696f2f537570657254696e7949636f6e732f696d616765732f706e672f6769746875622e706e67" 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/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>


<hr>
<p align="center" style="margin-top: 0px; font-size: 1.5em; background-color: #3c72db; padding: 0.5em; border-radius: 0.5em; color: white; font-weight: bold;">
    <a href="https://huggingface.co/openchat/openchat_3.5" style="text-decoration: none; color: white;">
      <span style="font-size: 1.6em;  font-family: 'Helvetica'; letter-spacing: 0.2em">OPENCHAT</span> 
      <span style="font-size: 1.6em;  font-family: 'Helvetica'; background-color: white; padding: 0.2em; border-radius: 0.3em; color: #3c72db;"> 3.5 </span>
      <br>
      <span>
  First 7B model that Achieves Comparable Results with ChatGPT (March) 
      <br>#1 Open-source model on MT-bench scoring 7.81, outperforming 70B models 
      </span>
   </a>
         <div align="center" style="display: flex; justify-content: center; align-items: center; "'>
  <img src="https://github.com/imoneoi/openchat/raw/master/assets/openchat.png" style="width:45%; margin-right: 2%;"> 
  <img src="https://github.com/imoneoi/openchat/raw/master/assets/openchat_grok.png" style="width: 47%;">
  </div>
</p>
<hr>

- OpenChat is an innovative library of **open-source language models**, fine-tuned with [**C-RLFT**](https://arxiv.org/pdf/2309.11235.pdf) - a strategy 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)**.
- Despite our simple approach, we are committed to developing a high-performance, commercially viable, open-source large language model, and we continue to make significant strides toward this vision.

# 📰 News

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

- [2023/09/21] We 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     | AGIEval  | BBH MC   | TruthfulQA    | MMLU         | HumanEval       | BBH CoT     | GSM8K        |
|--------------------|----------|----------|--------------|----------|----------|---------------|--------------|-----------------|-------------|--------------|
| OpenChat-3.5       | **7B**   | **61.6** | 7.81         | **47.4** | **47.6** | **59.1**      | 64.3         | **55.5**        | 63.5        | **77.3**     |
| ChatGPT (March)*   | ?        | 61.5     | **7.94**     | 47.1     | **47.6** | 57.7          | **67.3**     | 48.1            | **70.1**    | 74.9         |
|                    |          |          |              |          |          |               |              |                 |             |              |
| OpenHermes 2.5     | 7B       | 59.3     | 7.54         | 46.5     | 49.4     | 57.5          | 63.8         | 48.2            | 59.9        | 73.5         |
| OpenOrca Mistral   | 7B       | 52.7     | 6.86         | 42.9     | 49.4     | 45.9          | 59.3         | 38.4            | 58.1        | 59.1         |
| Zephyr-β^          | 7B       | 34.6     | 7.34         | 39.0     | 40.6     | 40.8          | 39.8         | 22.0            | 16.0        | 5.1          |
| Mistral**          | 7B       | -        | 6.84         | 38.0     | 39.0     | -             | 60.1         | 30.5            | -           | 52.2         |
| Open-source SOTA** | 13B-70B  | 61.4     | 7.71         | 41.7     | 49.7     | 62.3          | 63.7         | 73.2            | 41.4        | 82.3         |
|                    |          |          | WizardLM 70B | Orca 13B | Orca 13B | Platypus2 70B | WizardLM 70B | WizardCoder 34B | Flan-T5 11B | MetaMath 70B |


## 𝕏 Comparison with [X.AI Grok](https://x.ai/)

|              | License     | # Param | Average  | MMLU | HumanEval | MATH     | GSM8k    |
|--------------|-------------|---------|----------|------|-----------|----------|----------|
| 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 | ?       | 55.8     | 73   | 63.2      | 23.9     | 62.9     |

# 💌Contact

We are a student team  Tsinghua University, working on OpenChat, a project that requires additional computing power or LLMs API keys for further development. If you are interested in our project and would like to offer support, please feel free to reach out to us:

* Wang Guan [imonenext at gmail dot com]
* Cheng Sijie [csj23 at mails dot tsinghua dot edu dot cn]

We look forward to hearing  you and collaborating on this exciting project!