Spaces:
Runtime error
Runtime error
Ludwig Stumpp
commited on
Commit
•
73a321a
1
Parent(s):
48cd666
Add info about zero shot to leaderboard
Browse files- data/leaderboard.csv +20 -20
data/leaderboard.csv
CHANGED
@@ -1,20 +1,20 @@
|
|
1 |
-
Model Name ,Chatbot Arena Elo (lmsys) ,LAMBADA ,TriviaQA
|
2 |
-
alpaca-13b , 1008 ,
|
3 |
-
cerebras-7b , ,
|
4 |
-
cerebras-13b , ,
|
5 |
-
chatglm-6b , 985 ,
|
6 |
-
dolly-v2-12b , 944 ,
|
7 |
-
fastchat-t5-3b , 951 ,
|
8 |
-
gpt-neox-20b , ,
|
9 |
-
gptj-6b , ,
|
10 |
-
koala-13b , 1082 ,
|
11 |
-
llama-7b , ,
|
12 |
-
llama-13b , 932 ,
|
13 |
-
mpt-7b , ,
|
14 |
-
opt-7b , ,
|
15 |
-
opt-13b , ,
|
16 |
-
stablelm-base-alpha-7b , ,
|
17 |
-
stablelm-tuned-alpha-7b , 858 ,
|
18 |
-
vicuna-13b , 1169 ,
|
19 |
-
oasst-pythia-7b , ,
|
20 |
-
oasst-pythia-12b , 1065 ,
|
|
|
1 |
+
Model Name ,Chatbot Arena Elo (lmsys) ,LAMBADA (zero-shot) ,TriviaQA (zero-shot)
|
2 |
+
alpaca-13b , 1008 , ,
|
3 |
+
cerebras-7b , , 0.636 , 0.141
|
4 |
+
cerebras-13b , , 0.635 , 0.146
|
5 |
+
chatglm-6b , 985 , ,
|
6 |
+
dolly-v2-12b , 944 , ,
|
7 |
+
fastchat-t5-3b , 951 , ,
|
8 |
+
gpt-neox-20b , , 0.719 , 0.347
|
9 |
+
gptj-6b , , 0.683 , 0.234
|
10 |
+
koala-13b , 1082 , ,
|
11 |
+
llama-7b , , 0.738 , 0.443
|
12 |
+
llama-13b , 932 , ,
|
13 |
+
mpt-7b , , 0.702 , 0.343
|
14 |
+
opt-7b , , 0.677 , 0.227
|
15 |
+
opt-13b , , 0.692 , 0.282
|
16 |
+
stablelm-base-alpha-7b , , 0.533 , 0.049
|
17 |
+
stablelm-tuned-alpha-7b , 858 , ,
|
18 |
+
vicuna-13b , 1169 , ,
|
19 |
+
oasst-pythia-7b , , 0.667 , 0.198
|
20 |
+
oasst-pythia-12b , 1065 , 0.704 , 0.233
|