Update README.md
Browse files
README.md
CHANGED
@@ -20,6 +20,7 @@ tags:
|
|
20 |
|
21 |
|
22 |
|
|
|
23 |
<p
|
24 |
align="center"
|
25 |
<a href="The TOP1 MT-Bench Model">xDAN-AI</a> •
|
@@ -32,10 +33,14 @@ tags:
|
|
32 |
|
33 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/643197ac288c9775673a01e9/QANDZApzpTHM6sBsjmdew.png)
|
34 |
|
|
|
|
|
|
|
35 |
########## First turn ##########
|
36 |
| model | turn | score |
|
37 |
|--------------------|------|----------|
|
38 |
| gpt-4 | 1 | 8.95625 |
|
|
|
39 |
| xDAN-L1-Chat-RL-v1 | 1 | 8.87500 |
|
40 |
| claude-v1 | 1 | 8.15000 |
|
41 |
| gpt-3.5-turbo | 1 | 8.07500 |
|
|
|
20 |
|
21 |
|
22 |
|
23 |
+
## The first 7b model achieving an 8.8 on MT-Bench which is performance at Humanalities, Coding and Writing.
|
24 |
<p
|
25 |
align="center"
|
26 |
<a href="The TOP1 MT-Bench Model">xDAN-AI</a> •
|
|
|
33 |
|
34 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/643197ac288c9775673a01e9/QANDZApzpTHM6sBsjmdew.png)
|
35 |
|
36 |
+
|
37 |
+
|
38 |
+
|
39 |
########## First turn ##########
|
40 |
| model | turn | score |
|
41 |
|--------------------|------|----------|
|
42 |
| gpt-4 | 1 | 8.95625 |
|
43 |
+
| xDAN-L2-Chat-RL-v2 | 1 | 8.88750 |
|
44 |
| xDAN-L1-Chat-RL-v1 | 1 | 8.87500 |
|
45 |
| claude-v1 | 1 | 8.15000 |
|
46 |
| gpt-3.5-turbo | 1 | 8.07500 |
|