DRXD1000 commited on
Commit
f07212d
·
1 Parent(s): 65131bf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -17,6 +17,26 @@ and HuggingFaceH4/ultrafeedback_binarized was created in addition to a series of
17
  Thanks to the new type of training, Phoenix is not only able to compete with the Mistral model from LeoLM but also **beats the Llama-70b-chat model in 2 mt-bench categories**This model **wouldn't have been possible without the amazing work of Huggingface, LeoLM, openbnb, Argilla the Alma-Team and many others of the AI community**
18
 
19
  ## MT-Bench-DE Scores
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
 
21
  ## Model Details
22
 
 
17
  Thanks to the new type of training, Phoenix is not only able to compete with the Mistral model from LeoLM but also **beats the Llama-70b-chat model in 2 mt-bench categories**This model **wouldn't have been possible without the amazing work of Huggingface, LeoLM, openbnb, Argilla the Alma-Team and many others of the AI community**
18
 
19
  ## MT-Bench-DE Scores
20
+ Phoenix beats the LeoLM-Mistral model in all categories except for coding and humanities.
21
+ Additionally it also Beats LeoLM/Llama-2-70b-chat in roleplay and reasoning which shows the power of DPO.
22
+
23
+ ```
24
+ {
25
+ "first_turn": 6.39375,
26
+ "second_turn": 5.1625,
27
+ "categories": {
28
+ "writing": 7.45,
29
+ "roleplay": 7.9,
30
+ "reasoning": 4.3,
31
+ "math": 3.25,
32
+ "coding": 2.5,
33
+ "extraction": 5.9,
34
+ "stem": 7.125,
35
+ "humanities": 7.8
36
+ },
37
+ "average": 5.778124999999999
38
+ }
39
+ ```
40
 
41
  ## Model Details
42