sequelbox commited on
Commit
8656b88
1 Parent(s): de229f2
Files changed (1) hide show
  1. README.md +92 -0
README.md CHANGED
@@ -40,6 +40,98 @@ model-index:
40
  - type: acc
41
  value: 77.27
42
  name: acc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  license: llama3.1
44
  ---
45
 
 
40
  - type: acc
41
  value: 77.27
42
  name: acc
43
+ - task:
44
+ type: text-generation
45
+ name: Text Generation
46
+ dataset:
47
+ name: IFEval (0-Shot)
48
+ type: HuggingFaceH4/ifeval
49
+ args:
50
+ num_few_shot: 0
51
+ metrics:
52
+ - type: inst_level_strict_acc and prompt_level_strict_acc
53
+ value: 55.39
54
+ name: strict accuracy
55
+ source:
56
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
57
+ name: Open LLM Leaderboard
58
+ - task:
59
+ type: text-generation
60
+ name: Text Generation
61
+ dataset:
62
+ name: BBH (3-Shot)
63
+ type: BBH
64
+ args:
65
+ num_few_shot: 3
66
+ metrics:
67
+ - type: acc_norm
68
+ value: 28.47
69
+ name: normalized accuracy
70
+ source:
71
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
72
+ name: Open LLM Leaderboard
73
+ - task:
74
+ type: text-generation
75
+ name: Text Generation
76
+ dataset:
77
+ name: MATH Lvl 5 (4-Shot)
78
+ type: hendrycks/competition_math
79
+ args:
80
+ num_few_shot: 4
81
+ metrics:
82
+ - type: exact_match
83
+ value: 10.12
84
+ name: exact match
85
+ source:
86
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
87
+ name: Open LLM Leaderboard
88
+ - task:
89
+ type: text-generation
90
+ name: Text Generation
91
+ dataset:
92
+ name: GPQA (0-shot)
93
+ type: Idavidrein/gpqa
94
+ args:
95
+ num_few_shot: 0
96
+ metrics:
97
+ - type: acc_norm
98
+ value: 1.57
99
+ name: acc_norm
100
+ source:
101
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
102
+ name: Open LLM Leaderboard
103
+ - task:
104
+ type: text-generation
105
+ name: Text Generation
106
+ dataset:
107
+ name: MuSR (0-shot)
108
+ type: TAUR-Lab/MuSR
109
+ args:
110
+ num_few_shot: 0
111
+ metrics:
112
+ - type: acc_norm
113
+ value: 11.41
114
+ name: acc_norm
115
+ source:
116
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
117
+ name: Open LLM Leaderboard
118
+ - task:
119
+ type: text-generation
120
+ name: Text Generation
121
+ dataset:
122
+ name: MMLU-PRO (5-shot)
123
+ type: TIGER-Lab/MMLU-Pro
124
+ config: main
125
+ split: test
126
+ args:
127
+ num_few_shot: 5
128
+ metrics:
129
+ - type: acc
130
+ value: 26.2
131
+ name: accuracy
132
+ source:
133
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.1-8B-Enigma
134
+ name: Open LLM Leaderboard
135
  license: llama3.1
136
  ---
137