Files changed (1) hide show
  1. README.md +120 -3
README.md CHANGED
@@ -1,14 +1,117 @@
1
  ---
2
- license: apache-2.0
3
- datasets:
4
- - ajibawa-2023/Children-Stories-Collection
5
  language:
6
  - en
 
7
  tags:
8
  - story
9
  - young children
10
  - educational
11
  - knowledge
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
 
@@ -78,3 +181,17 @@ Example 3
78
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64aea8ff67511bd3d965697b/o7hiMI5noO8fPedUG75H8.jpeg)
79
 
80
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
 
 
2
  language:
3
  - en
4
+ license: apache-2.0
5
  tags:
6
  - story
7
  - young children
8
  - educational
9
  - knowledge
10
+ datasets:
11
+ - ajibawa-2023/Children-Stories-Collection
12
+ model-index:
13
+ - name: Young-Children-Storyteller-Mistral-7B
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ name: Text Generation
18
+ dataset:
19
+ name: AI2 Reasoning Challenge (25-Shot)
20
+ type: ai2_arc
21
+ config: ARC-Challenge
22
+ split: test
23
+ args:
24
+ num_few_shot: 25
25
+ metrics:
26
+ - type: acc_norm
27
+ value: 68.69
28
+ name: normalized accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Young-Children-Storyteller-Mistral-7B
31
+ name: Open LLM Leaderboard
32
+ - task:
33
+ type: text-generation
34
+ name: Text Generation
35
+ dataset:
36
+ name: HellaSwag (10-Shot)
37
+ type: hellaswag
38
+ split: validation
39
+ args:
40
+ num_few_shot: 10
41
+ metrics:
42
+ - type: acc_norm
43
+ value: 84.67
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Young-Children-Storyteller-Mistral-7B
47
+ name: Open LLM Leaderboard
48
+ - task:
49
+ type: text-generation
50
+ name: Text Generation
51
+ dataset:
52
+ name: MMLU (5-Shot)
53
+ type: cais/mmlu
54
+ config: all
55
+ split: test
56
+ args:
57
+ num_few_shot: 5
58
+ metrics:
59
+ - type: acc
60
+ value: 64.11
61
+ name: accuracy
62
+ source:
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Young-Children-Storyteller-Mistral-7B
64
+ name: Open LLM Leaderboard
65
+ - task:
66
+ type: text-generation
67
+ name: Text Generation
68
+ dataset:
69
+ name: TruthfulQA (0-shot)
70
+ type: truthful_qa
71
+ config: multiple_choice
72
+ split: validation
73
+ args:
74
+ num_few_shot: 0
75
+ metrics:
76
+ - type: mc2
77
+ value: 62.62
78
+ source:
79
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Young-Children-Storyteller-Mistral-7B
80
+ name: Open LLM Leaderboard
81
+ - task:
82
+ type: text-generation
83
+ name: Text Generation
84
+ dataset:
85
+ name: Winogrande (5-shot)
86
+ type: winogrande
87
+ config: winogrande_xl
88
+ split: validation
89
+ args:
90
+ num_few_shot: 5
91
+ metrics:
92
+ - type: acc
93
+ value: 81.22
94
+ name: accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Young-Children-Storyteller-Mistral-7B
97
+ name: Open LLM Leaderboard
98
+ - task:
99
+ type: text-generation
100
+ name: Text Generation
101
+ dataset:
102
+ name: GSM8k (5-shot)
103
+ type: gsm8k
104
+ config: main
105
+ split: test
106
+ args:
107
+ num_few_shot: 5
108
+ metrics:
109
+ - type: acc
110
+ value: 65.2
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Young-Children-Storyteller-Mistral-7B
114
+ name: Open LLM Leaderboard
115
  ---
116
 
117
 
 
181
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64aea8ff67511bd3d965697b/o7hiMI5noO8fPedUG75H8.jpeg)
182
 
183
 
184
+
185
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
186
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ajibawa-2023__Young-Children-Storyteller-Mistral-7B)
187
+
188
+ | Metric |Value|
189
+ |---------------------------------|----:|
190
+ |Avg. |71.08|
191
+ |AI2 Reasoning Challenge (25-Shot)|68.69|
192
+ |HellaSwag (10-Shot) |84.67|
193
+ |MMLU (5-Shot) |64.11|
194
+ |TruthfulQA (0-shot) |62.62|
195
+ |Winogrande (5-shot) |81.22|
196
+ |GSM8k (5-shot) |65.20|
197
+