Commit
91faae2
1 Parent(s): 21167cb

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (34585064e04aeabf98b2ff7a3fd7859b210be304)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

Files changed (1) hide show
  1. README.md +125 -8
README.md CHANGED
@@ -1,17 +1,120 @@
1
  ---
2
  language:
3
- - en
4
  license: other
5
  tags:
6
- - art
7
- - philosophy
8
- - romance
9
- - jokes
10
- - advice
11
- - code
12
- - companionship
13
  license_name: llama3
14
  license_link: LICENSE
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  ---
16
 
17
  **Scarlett-Llama-3-8B-v1.0**
@@ -82,3 +185,17 @@ Example 4
82
 
83
 
84
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64aea8ff67511bd3d965697b/95YaYsebBPJqQ-oo8841f.jpeg)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  language:
3
+ - en
4
  license: other
5
  tags:
6
+ - art
7
+ - philosophy
8
+ - romance
9
+ - jokes
10
+ - advice
11
+ - code
12
+ - companionship
13
  license_name: llama3
14
  license_link: LICENSE
15
+ model-index:
16
+ - name: Scarlett-Llama-3-8B-v1.0
17
+ results:
18
+ - task:
19
+ type: text-generation
20
+ name: Text Generation
21
+ dataset:
22
+ name: AI2 Reasoning Challenge (25-Shot)
23
+ type: ai2_arc
24
+ config: ARC-Challenge
25
+ split: test
26
+ args:
27
+ num_few_shot: 25
28
+ metrics:
29
+ - type: acc_norm
30
+ value: 62.12
31
+ name: normalized accuracy
32
+ source:
33
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
34
+ name: Open LLM Leaderboard
35
+ - task:
36
+ type: text-generation
37
+ name: Text Generation
38
+ dataset:
39
+ name: HellaSwag (10-Shot)
40
+ type: hellaswag
41
+ split: validation
42
+ args:
43
+ num_few_shot: 10
44
+ metrics:
45
+ - type: acc_norm
46
+ value: 83.98
47
+ name: normalized accuracy
48
+ source:
49
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
50
+ name: Open LLM Leaderboard
51
+ - task:
52
+ type: text-generation
53
+ name: Text Generation
54
+ dataset:
55
+ name: MMLU (5-Shot)
56
+ type: cais/mmlu
57
+ config: all
58
+ split: test
59
+ args:
60
+ num_few_shot: 5
61
+ metrics:
62
+ - type: acc
63
+ value: 66.36
64
+ name: accuracy
65
+ source:
66
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
67
+ name: Open LLM Leaderboard
68
+ - task:
69
+ type: text-generation
70
+ name: Text Generation
71
+ dataset:
72
+ name: TruthfulQA (0-shot)
73
+ type: truthful_qa
74
+ config: multiple_choice
75
+ split: validation
76
+ args:
77
+ num_few_shot: 0
78
+ metrics:
79
+ - type: mc2
80
+ value: 55.98
81
+ source:
82
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
83
+ name: Open LLM Leaderboard
84
+ - task:
85
+ type: text-generation
86
+ name: Text Generation
87
+ dataset:
88
+ name: Winogrande (5-shot)
89
+ type: winogrande
90
+ config: winogrande_xl
91
+ split: validation
92
+ args:
93
+ num_few_shot: 5
94
+ metrics:
95
+ - type: acc
96
+ value: 77.9
97
+ name: accuracy
98
+ source:
99
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
100
+ name: Open LLM Leaderboard
101
+ - task:
102
+ type: text-generation
103
+ name: Text Generation
104
+ dataset:
105
+ name: GSM8k (5-shot)
106
+ type: gsm8k
107
+ config: main
108
+ split: test
109
+ args:
110
+ num_few_shot: 5
111
+ metrics:
112
+ - type: acc
113
+ value: 43.21
114
+ name: accuracy
115
+ source:
116
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ajibawa-2023/Scarlett-Llama-3-8B-v1.0
117
+ name: Open LLM Leaderboard
118
  ---
119
 
120
  **Scarlett-Llama-3-8B-v1.0**
 
185
 
186
 
187
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64aea8ff67511bd3d965697b/95YaYsebBPJqQ-oo8841f.jpeg)
188
+
189
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
190
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ajibawa-2023__Scarlett-Llama-3-8B-v1.0)
191
+
192
+ | Metric |Value|
193
+ |---------------------------------|----:|
194
+ |Avg. |64.92|
195
+ |AI2 Reasoning Challenge (25-Shot)|62.12|
196
+ |HellaSwag (10-Shot) |83.98|
197
+ |MMLU (5-Shot) |66.36|
198
+ |TruthfulQA (0-shot) |55.98|
199
+ |Winogrande (5-shot) |77.90|
200
+ |GSM8k (5-shot) |43.21|
201
+