Update README.md
Browse files
README.md
CHANGED
@@ -26,7 +26,21 @@ Read our [blog post]() or our paper (preprint coming soon) for more details!
|
|
26 |
`LeoLM/leo-hessianai-7b-chat` is a German chat model built on our foundation model `LeoLM/leo-hessianai-7b` and finetuned on a selection of German instruction datasets.
|
27 |
The model performs exceptionally well on writing, explanation and discussion tasks but struggles somewhat with math and advanced reasoning. See our MT-Bench-DE scores:
|
28 |
```
|
29 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
```
|
31 |
|
32 |
## Model Details
|
|
|
26 |
`LeoLM/leo-hessianai-7b-chat` is a German chat model built on our foundation model `LeoLM/leo-hessianai-7b` and finetuned on a selection of German instruction datasets.
|
27 |
The model performs exceptionally well on writing, explanation and discussion tasks but struggles somewhat with math and advanced reasoning. See our MT-Bench-DE scores:
|
28 |
```
|
29 |
+
{
|
30 |
+
"first_turn": 5.75,
|
31 |
+
"second_turn": 4.45,
|
32 |
+
"categories": {
|
33 |
+
"writing": 5.875,
|
34 |
+
"roleplay": 6.3,
|
35 |
+
"reasoning": 3.5,
|
36 |
+
"math": 2.85,
|
37 |
+
"coding": 2.95,
|
38 |
+
"extraction": 4.3,
|
39 |
+
"stem": 7.4,
|
40 |
+
"humanities": 7.625
|
41 |
+
},
|
42 |
+
"average": 5.1
|
43 |
+
}
|
44 |
```
|
45 |
|
46 |
## Model Details
|