Commit
•
99d59d4
1
Parent(s):
2b2dbf0
Update README.md
Browse files
README.md
CHANGED
|
@@ -39,7 +39,7 @@ pipeline_tag: text-generation
|
|
| 39 |
**🤖 #1 Open-source model on MT-bench scoring 7.81, outperforming 70B models 🤖**
|
| 40 |
|
| 41 |
<div align="center" style="justify-content: center; align-items: center; "'>
|
| 42 |
-
<img src="https://github.com/alpayariyak/openchat/blob/master/assets/
|
| 43 |
</div>
|
| 44 |
|
| 45 |
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. 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.
|
|
|
|
| 39 |
**🤖 #1 Open-source model on MT-bench scoring 7.81, outperforming 70B models 🤖**
|
| 40 |
|
| 41 |
<div align="center" style="justify-content: center; align-items: center; "'>
|
| 42 |
+
<img src="https://github.com/alpayariyak/openchat/blob/master/assets/3.5-benchmarks.png?raw=true" style="width: 100%; border-radius: 0.5em">
|
| 43 |
</div>
|
| 44 |
|
| 45 |
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. 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.
|