ldwang commited on
Commit
8298da2
1 Parent(s): 1b9b2ce

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -8
README.md CHANGED
@@ -1,11 +1,11 @@
1
- ---
2
- license: apache-2.0
3
- language:
4
- - en
5
- - zh
6
- tags:
7
- - moe
8
- ---
9
  # AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies
10
  <p align="center">
11
  <br>
@@ -142,6 +142,10 @@ The performance of the AquilaMoE model series improves significantly across mult
142
  | mmlu-ppl | 59.93 |
143
  | winograd-ppl | 57.5 |
144
 
 
 
 
 
145
  *Table: Performance of AquilaMoE-SFT (16\*8B) on various benchmarks.*
146
 
147
  ## License Agreement
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - zh
6
+ tags:
7
+ - moe
8
+ ---
9
  # AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies
10
  <p align="center">
11
  <br>
 
142
  | mmlu-ppl | 59.93 |
143
  | winograd-ppl | 57.5 |
144
 
145
+ | Model | GPT 3.5 Turbo (11/06) | GPT 3.5 Turbo (03/01) | AquilaMoE-SFT |
146
+ |------------------|-----------------------|-----------------------|---------------|
147
+ | AlpacaEval 2.0 | 19.3 | 18.1 | 21.1 |
148
+
149
  *Table: Performance of AquilaMoE-SFT (16\*8B) on various benchmarks.*
150
 
151
  ## License Agreement