---
title: README
emoji: π
colorFrom: blue
colorTo: blue
sdk: static
pinned: false
---
Advancing Open-source Language Models with Mixed-Quality Data
Online Demo
|
GitHub
|
Paper
|
Discord
About OpenChat
- 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.
# π° News
- [2023/12/10] We released the [OpenChat-3.5-1210](https://huggingface.co/openchat/openchat-3.5-1210) model, 15-point improvements in coding.
- [2023/11/01] We released the [OpenChat-3.5-7B](https://huggingface.co/openchat/openchat_3.5) model, surpassing ChatGPT on various benchmarks π₯.
- [2023/09/21] We released our paper [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://arxiv.org/pdf/2309.11235.pdf).
# π Benchmarks
| Model | # Params | Average | MT-Bench | HumanEval | BBH MC | AGIEval | TruthfulQA | MMLU | GSM8K | BBH CoT |
|--------------------|----------|----------|--------------|-----------------|----------|----------|---------------|--------------|--------------|-------------|
| 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-Ξ²^ | 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 | - |
## π Comparison with [X.AI Grok](https://x.ai/)
| | License | # Param | Average | MMLU | HumanEval | MATH | GSM8k |
|-------------------|-------------|---------|----------|------|-----------|----------|----------|
| 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 |
# πContact
We are a student team at 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:
**Project Leader:**
- Guan Wang [imonenext at gmail dot com]
- [Sijie Cheng](https://adacheng.github.io/) [csj23 at mails dot tsinghua dot edu dot cn]
**Main Contributors:**
- [Xianyuan Zhan](https://scholar.google.com.hk/citations?user=pDMnGloAAAAJ&hl=zh-CN) (Tsinghua University): Provided invaluable advice on paper writing.
- [Alpay Ariyak](https://github.com/alpayariyak): Responsible for data collection and PR for `openchat-3.5-1210`, including updates to model and organization cards.
- LDJ: Tasked with partial data collection for `openchat-3.5`.
**Sponsors:**
- [Sen Song](https://scholar.google.com/citations?user=cYgtRP4AAAAJ&hl=en) (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/), Changling Liu (GPT Desk Pte. Ltd.), Qiying Yu (Tsinghua University), AutoMeta (Alignment Lab AI). 