Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Python Code Generation on MBPP
Loading...
54.5
Normal (%)
zephyr-gemma-7b
50.132
51.266
52.4
53.534
May 26, 2024
Normal (%)
Plus (%)
Updated 4d ago
Evaluation Results
Method
Method
Links
Normal (%)
Plus (%)
zephyr-gemma-7b
Decoding=Greedy, Evalu...
2024.05
54.5
44.7
RPO
Decoding=Greedy, Evalu...
2024.05
54.2
46.3
DPO
Decoding=Greedy, Evalu...
2024.05
54.2
43.9
zephyr-7b-gemma-sft
Decoding=Greedy, Evalu...
2024.05
50.3
44.2
Feedback
Search any
task
Search any
task