Files changed (1) hide show
  1. README.md +110 -2
README.md CHANGED
@@ -1,8 +1,103 @@
1
  ---
2
- library_name: transformers
3
  license: apache-2.0
 
4
  datasets:
5
  - vicgalle/configurable-system-prompt-multitask
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  ---
7
 
8
  # ConfigurableSOLAR-10.7B
@@ -32,4 +127,17 @@ If you find this work, data and/or models useful for your research, please consi
32
  archivePrefix={arXiv},
33
  primaryClass={cs.CL}
34
  }
35
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  license: apache-2.0
3
+ library_name: transformers
4
  datasets:
5
  - vicgalle/configurable-system-prompt-multitask
6
+ model-index:
7
+ - name: ConfigurableSOLAR-10.7B
8
+ results:
9
+ - task:
10
+ type: text-generation
11
+ name: Text Generation
12
+ dataset:
13
+ name: IFEval (0-Shot)
14
+ type: HuggingFaceH4/ifeval
15
+ args:
16
+ num_few_shot: 0
17
+ metrics:
18
+ - type: inst_level_strict_acc and prompt_level_strict_acc
19
+ value: 51.0
20
+ name: strict accuracy
21
+ source:
22
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
23
+ name: Open LLM Leaderboard
24
+ - task:
25
+ type: text-generation
26
+ name: Text Generation
27
+ dataset:
28
+ name: BBH (3-Shot)
29
+ type: BBH
30
+ args:
31
+ num_few_shot: 3
32
+ metrics:
33
+ - type: acc_norm
34
+ value: 27.45
35
+ name: normalized accuracy
36
+ source:
37
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
38
+ name: Open LLM Leaderboard
39
+ - task:
40
+ type: text-generation
41
+ name: Text Generation
42
+ dataset:
43
+ name: MATH Lvl 5 (4-Shot)
44
+ type: hendrycks/competition_math
45
+ args:
46
+ num_few_shot: 4
47
+ metrics:
48
+ - type: exact_match
49
+ value: 0.0
50
+ name: exact match
51
+ source:
52
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
53
+ name: Open LLM Leaderboard
54
+ - task:
55
+ type: text-generation
56
+ name: Text Generation
57
+ dataset:
58
+ name: GPQA (0-shot)
59
+ type: Idavidrein/gpqa
60
+ args:
61
+ num_few_shot: 0
62
+ metrics:
63
+ - type: acc_norm
64
+ value: 6.49
65
+ name: acc_norm
66
+ source:
67
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
68
+ name: Open LLM Leaderboard
69
+ - task:
70
+ type: text-generation
71
+ name: Text Generation
72
+ dataset:
73
+ name: MuSR (0-shot)
74
+ type: TAUR-Lab/MuSR
75
+ args:
76
+ num_few_shot: 0
77
+ metrics:
78
+ - type: acc_norm
79
+ value: 5.19
80
+ name: acc_norm
81
+ source:
82
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
83
+ name: Open LLM Leaderboard
84
+ - task:
85
+ type: text-generation
86
+ name: Text Generation
87
+ dataset:
88
+ name: MMLU-PRO (5-shot)
89
+ type: TIGER-Lab/MMLU-Pro
90
+ config: main
91
+ split: test
92
+ args:
93
+ num_few_shot: 5
94
+ metrics:
95
+ - type: acc
96
+ value: 24.15
97
+ name: accuracy
98
+ source:
99
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
100
+ name: Open LLM Leaderboard
101
  ---
102
 
103
  # ConfigurableSOLAR-10.7B
 
127
  archivePrefix={arXiv},
128
  primaryClass={cs.CL}
129
  }
130
+ ```
131
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
132
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__ConfigurableSOLAR-10.7B)
133
+
134
+ | Metric |Value|
135
+ |-------------------|----:|
136
+ |Avg. |19.05|
137
+ |IFEval (0-Shot) |51.00|
138
+ |BBH (3-Shot) |27.45|
139
+ |MATH Lvl 5 (4-Shot)| 0.00|
140
+ |GPQA (0-shot) | 6.49|
141
+ |MuSR (0-shot) | 5.19|
142
+ |MMLU-PRO (5-shot) |24.15|
143
+