Commit
ea2ea14
1 Parent(s): 4c8868e

Adding Evaluation Results (#8)

Browse files

- Adding Evaluation Results (f56a53d6eaaf0251ee8d3690f07490eb910e29e6)


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

Files changed (1) hide show
  1. README.md +120 -4
README.md CHANGED
@@ -1,8 +1,7 @@
1
  ---
2
  language:
3
  - en
4
- base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
- pipeline_tag: text-generation
6
  tags:
7
  - facebook
8
  - meta
@@ -11,9 +10,113 @@ tags:
11
  - llama-3
12
  - moe
13
  - code
14
- license: other
 
15
  license_name: llama3
16
  license_link: LICENSE
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  ---
18
 
19
 
@@ -137,4 +240,17 @@ If you'd like to discuss potential collaborations or applications, feel free to
137
 
138
  **Meta Llama 3 is
139
  licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights
140
- Reserved.**
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  language:
3
  - en
4
+ license: other
 
5
  tags:
6
  - facebook
7
  - meta
 
10
  - llama-3
11
  - moe
12
  - code
13
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
14
+ pipeline_tag: text-generation
15
  license_name: llama3
16
  license_link: LICENSE
17
+ model-index:
18
+ - name: Llama-3-Aplite-Instruct-4x8B-MoE
19
+ results:
20
+ - task:
21
+ type: text-generation
22
+ name: Text Generation
23
+ dataset:
24
+ name: AI2 Reasoning Challenge (25-Shot)
25
+ type: ai2_arc
26
+ config: ARC-Challenge
27
+ split: test
28
+ args:
29
+ num_few_shot: 25
30
+ metrics:
31
+ - type: acc_norm
32
+ value: 61.86
33
+ name: normalized accuracy
34
+ source:
35
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
36
+ name: Open LLM Leaderboard
37
+ - task:
38
+ type: text-generation
39
+ name: Text Generation
40
+ dataset:
41
+ name: HellaSwag (10-Shot)
42
+ type: hellaswag
43
+ split: validation
44
+ args:
45
+ num_few_shot: 10
46
+ metrics:
47
+ - type: acc_norm
48
+ value: 81.08
49
+ name: normalized accuracy
50
+ source:
51
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
52
+ name: Open LLM Leaderboard
53
+ - task:
54
+ type: text-generation
55
+ name: Text Generation
56
+ dataset:
57
+ name: MMLU (5-Shot)
58
+ type: cais/mmlu
59
+ config: all
60
+ split: test
61
+ args:
62
+ num_few_shot: 5
63
+ metrics:
64
+ - type: acc
65
+ value: 67.47
66
+ name: accuracy
67
+ source:
68
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
69
+ name: Open LLM Leaderboard
70
+ - task:
71
+ type: text-generation
72
+ name: Text Generation
73
+ dataset:
74
+ name: TruthfulQA (0-shot)
75
+ type: truthful_qa
76
+ config: multiple_choice
77
+ split: validation
78
+ args:
79
+ num_few_shot: 0
80
+ metrics:
81
+ - type: mc2
82
+ value: 51.87
83
+ source:
84
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
85
+ name: Open LLM Leaderboard
86
+ - task:
87
+ type: text-generation
88
+ name: Text Generation
89
+ dataset:
90
+ name: Winogrande (5-shot)
91
+ type: winogrande
92
+ config: winogrande_xl
93
+ split: validation
94
+ args:
95
+ num_few_shot: 5
96
+ metrics:
97
+ - type: acc
98
+ value: 77.82
99
+ name: accuracy
100
+ source:
101
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
102
+ name: Open LLM Leaderboard
103
+ - task:
104
+ type: text-generation
105
+ name: Text Generation
106
+ dataset:
107
+ name: GSM8k (5-shot)
108
+ type: gsm8k
109
+ config: main
110
+ split: test
111
+ args:
112
+ num_few_shot: 5
113
+ metrics:
114
+ - type: acc
115
+ value: 61.87
116
+ name: accuracy
117
+ source:
118
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=raincandy-u/Llama-3-Aplite-Instruct-4x8B-MoE
119
+ name: Open LLM Leaderboard
120
  ---
121
 
122
 
 
240
 
241
  **Meta Llama 3 is
242
  licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights
243
+ Reserved.**
244
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
245
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_raincandy-u__Llama-3-Aplite-Instruct-4x8B-MoE)
246
+
247
+ | Metric |Value|
248
+ |---------------------------------|----:|
249
+ |Avg. |66.99|
250
+ |AI2 Reasoning Challenge (25-Shot)|61.86|
251
+ |HellaSwag (10-Shot) |81.08|
252
+ |MMLU (5-Shot) |67.47|
253
+ |TruthfulQA (0-shot) |51.87|
254
+ |Winogrande (5-shot) |77.82|
255
+ |GSM8k (5-shot) |61.87|
256
+