Update README.md
Browse files
README.md
CHANGED
|
@@ -263,7 +263,22 @@ evaluated with lm-evaluation-benchmark-harness 0.4.2
|
|
| 263 |
|
| 264 |
|
| 265 |
**MT-Bench English**
|
| 266 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 267 |
|
| 268 |
|
| 269 |
**MT-Bench German**
|
|
|
|
| 263 |
|
| 264 |
|
| 265 |
**MT-Bench English**
|
| 266 |
+
```
|
| 267 |
+
########## First turn ##########
|
| 268 |
+
score
|
| 269 |
+
model turn
|
| 270 |
+
Llama-3-SauerkrautLM-70b-Instruct 1 8.86875
|
| 271 |
+
|
| 272 |
+
########## Second turn ##########
|
| 273 |
+
score
|
| 274 |
+
model turn
|
| 275 |
+
Llama-3-SauerkrautLM-70b-Instruct 2 8.506329
|
| 276 |
+
|
| 277 |
+
########## Average ##########
|
| 278 |
+
score
|
| 279 |
+
model
|
| 280 |
+
Llama-3-SauerkrautLM-70b-Instruct 8.688679
|
| 281 |
+
```
|
| 282 |
|
| 283 |
|
| 284 |
**MT-Bench German**
|