Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ With 1.4B non-embedding parameters and training on 2.2 trillion tokens,
|
|
| 16 |
it achieves performance competitive with current state-of-the-art fully open models and even rivals some leading open-weight models of similar scale.
|
| 17 |
|
| 18 |
<center>
|
| 19 |
-
|
| 20 |
</center>
|
| 21 |
|
| 22 |
We will publish the datasets used to train Kaiyuan-2B soon.
|
|
|
|
| 16 |
it achieves performance competitive with current state-of-the-art fully open models and even rivals some leading open-weight models of similar scale.
|
| 17 |
|
| 18 |
<center>
|
| 19 |
+
<img alt="Model Performance Comparison" src="model_performance_comparison.svg"/>
|
| 20 |
</center>
|
| 21 |
|
| 22 |
We will publish the datasets used to train Kaiyuan-2B soon.
|