Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Zero-shot Reasoning on (ARC-E, PIQA, SciQ, HellaSwag, LAMBADA, WinoGrande, BoolQ)
Loading...
51.22
ARC-E
Inheritune
50.3464
50.5732
50.8
51.0268
Apr 12, 2024
ARC-E
PIQA
SciQ
HellaSwag
LAMBADA
WinoGrande
BoolQ
Average Accuracy (Zero-shot)
Updated 4d ago
Evaluation Results
Method
Method
Links
ARC-E
PIQA
SciQ
HellaSwag
LAMBADA
WinoGrande
BoolQ
Average Accuracy (Zero-shot)
Inheritune
Model Layers=24, Train...
2024.04
51.22
66.87
79.2
34.2
43.3
53.28
60.4
55.5
GPT-2 XLarge (Full model)
Model Layers=48, Train...
2024.04
50.38
66.7
77
33.65
39.9
51.93
57.86
53.92
Feedback
Search any
task
Search any
task