Update README.md
Browse files
README.md
CHANGED
@@ -167,11 +167,11 @@ Evaluating our model is a key part of our fine-tuning process. It helps us under
|
|
167 |
|
168 |
We've compared GenZ models to understand the improvements our fine-tuning has achieved.
|
169 |
|
170 |
-
| Model Name | MT Bench |
|
171 |
-
|
172 |
-
| Genz 13B | 6.12 |
|
173 |
-
| Genz 13B v2| 6.79 |
|
174 |
-
| Genz 70B |
|
175 |
|
176 |
<h3>MT Bench Score</h3>
|
177 |
|
|
|
167 |
|
168 |
We've compared GenZ models to understand the improvements our fine-tuning has achieved.
|
169 |
|
170 |
+
| Model Name | MT Bench | MMLU | Human Eval | Hellaswag | BBH |
|
171 |
+
|:----------:|:--------:|:----:|:----------:|:---------:|:----:|
|
172 |
+
| Genz 13B | 6.12 | 53.62| 17.68 | 77.38 | 37.76|
|
173 |
+
| Genz 13B v2| 6.79 | 53.68| 21.95 | 77.48 | 38.1 |
|
174 |
+
| Genz 70B | 7.33 | 70.32| | | |
|
175 |
|
176 |
<h3>MT Bench Score</h3>
|
177 |
|