Update README.md
Browse files
README.md
CHANGED
@@ -114,6 +114,21 @@ results = tokenizer.batch_decode(outputs)[0]
|
|
114 |
print(results)
|
115 |
```
|
116 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
117 |
## More Information
|
118 |
|
119 |
Many thanks for
|
|
|
114 |
print(results)
|
115 |
```
|
116 |
|
117 |
+
## Evaluation
|
118 |
+
|
119 |
+
### Results
|
120 |
+
|
121 |
+
#### OpenLLM Leaderboard
|
122 |
+
|
123 |
+
It will be evaluated and updated later.
|
124 |
+
|
125 |
+
#### VMLU
|
126 |
+
|
127 |
+
Below are the results evaluated with the VMLU evaluation suite, which is often used to evaluate models that work with Vietnamese.
|
128 |
+
Note: the results are run with the model in 4bit quantum form, I'm not sure if it has any loss in results or not, if someone can help me run it with full it would be great.
|
129 |
+
|
130 |
+
![VMLU - lamhieu/ghost-7b-v0.9.0](https://cdn-uploads.huggingface.co/production/uploads/600ae38cc92b79f54efd4556/GdMgr0-YnAGRqD_RJr_ux.png)
|
131 |
+
|
132 |
## More Information
|
133 |
|
134 |
Many thanks for
|