Commit
•
22edf13
1
Parent(s):
f450854
Update README.md
Browse files
README.md
CHANGED
|
@@ -68,12 +68,15 @@ pinned: false
|
|
| 68 |
<br>#1 Open-source model on MT-bench scoring 7.81, outperforming 70B models
|
| 69 |
</span>
|
| 70 |
</a>
|
| 71 |
-
<div align="center" style="
|
| 72 |
-
<img src="https://github.com/
|
| 73 |
-
<img src="https://github.com/imoneoi/openchat/raw/master/assets/openchat_grok.png" style="width: 47%;">
|
| 74 |
</div>
|
| 75 |
</p>
|
| 76 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
- 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.
|
| 78 |
- 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)**.
|
| 79 |
- 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.
|
|
|
|
| 68 |
<br>#1 Open-source model on MT-bench scoring 7.81, outperforming 70B models
|
| 69 |
</span>
|
| 70 |
</a>
|
| 71 |
+
<div align="center" style="justify-content: center; align-items: center; "'>
|
| 72 |
+
<img src="https://github.com/alpayariyak/openchat/blob/master/assets/Untitled%20design-17.png?raw=true" style="width: 100%;">
|
|
|
|
| 73 |
</div>
|
| 74 |
</p>
|
| 75 |
|
| 76 |
+
<h1 style="vertical-align: middle;">
|
| 77 |
+
<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: 0px; margin-top: 0px; margin-bottom: 0px;"/>About OpenChat
|
| 78 |
+
</h1>
|
| 79 |
+
|
| 80 |
- 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.
|
| 81 |
- 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)**.
|
| 82 |
- 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.
|