Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Instruction Following on Vicuna benchmark
Loading...
8.09
GPT-4 Evaluation Score
llama2 → CP → FT + chat vector
4.4708
5.4104
6.35
7.2896
Oct 7, 2023
GPT-4 Evaluation Score
Updated 4d ago
Evaluation Results
Method
Method
Links
GPT-4 Evaluation Score
llama2 → CP → FT + chat vector
Model Base=Chinese-LLA...
2023.10
8.09
llama2 → CP → FT + 0.5 chat vector
Model Base=Chinese-LLA...
2023.10
8.02
llama2 → CP → FT + 0.5 chat vector
Model Base=Chinese-LLA...
2023.10
7.89
llama2 → CP → FT + chat vector
Model Base=Chinese-LLA...
2023.10
7.86
llama2 → CP → FT
Model Base=Chinese-LLA...
2023.10
7.58
llama2 → CP → FT
Model Base=Chinese-LLA...
2023.10
7.47
llama2 → CP → FT + chat vector
Model Base=Traditional...
2023.10
7.37
llama2 → CP + chat vector
Model Base=Chinese-LLA...
2023.10
7.07
llama2 → CP → FT + chat vector
Model Base=Traditional...
2023.10
7.06
llama2 → CP + chat vector
Model Base=Traditional...
2023.10
7.03
llama2 → CP + chat vector
Model Base=Chinese-LLA...
2023.10
6.7
llama2-chat → CP → FT
Model Base=Traditional...
2023.10
6.46
llama2 → CP → FT
Model Base=Traditional...
2023.10
6.13
llama2 → CP + chat vector
Model Base=Traditional...
2023.10
6.04
llama2-chat → CP → FT
Model Base=Traditional...
2023.10
5.89
llama2 → CP → FT
Model Base=Traditional...
2023.10
5.5
llama2 → CP + 0.5 chat vector
Model Base=Chinese-LLA...
2023.10
5.06
llama2 → CP + 0.5 chat vector
Model Base=Chinese-LLA...
2023.10
4.61
Feedback
Search any
task
Search any
task