Files changed (1) hide show
  1. README.md +124 -8
README.md CHANGED
@@ -1,16 +1,119 @@
1
  ---
 
 
 
 
 
 
 
2
  base_model:
3
  - SanjiWatsuki/Sonya-7B
4
  - EmbeddedLLM/Mistral-7B-Merge-14-v0.1
5
  - SanjiWatsuki/Kunoichi-7B
6
- tags:
7
- - mergekit
8
- - merge
9
- license: openrail
10
- language:
11
- - en
12
- library_name: transformers
13
  pipeline_tag: text-generation
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
  # merged
16
  ![intro](332f1afc-d0b6-47f8-8a1c-b4bdccea94b4.png "Intro")
@@ -49,4 +152,17 @@ slices:
49
  model: SanjiWatsuki/Sonya-7B
50
  - layer_range: [0, 32]
51
  model: SanjiWatsuki/Kunoichi-7B
52
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ license: openrail
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
  base_model:
10
  - SanjiWatsuki/Sonya-7B
11
  - EmbeddedLLM/Mistral-7B-Merge-14-v0.1
12
  - SanjiWatsuki/Kunoichi-7B
 
 
 
 
 
 
 
13
  pipeline_tag: text-generation
14
+ model-index:
15
+ - name: Mistral_Sonyichi-7B-slerp
16
+ results:
17
+ - task:
18
+ type: text-generation
19
+ name: Text Generation
20
+ dataset:
21
+ name: AI2 Reasoning Challenge (25-Shot)
22
+ type: ai2_arc
23
+ config: ARC-Challenge
24
+ split: test
25
+ args:
26
+ num_few_shot: 25
27
+ metrics:
28
+ - type: acc_norm
29
+ value: 67.49
30
+ name: normalized accuracy
31
+ source:
32
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
33
+ name: Open LLM Leaderboard
34
+ - task:
35
+ type: text-generation
36
+ name: Text Generation
37
+ dataset:
38
+ name: HellaSwag (10-Shot)
39
+ type: hellaswag
40
+ split: validation
41
+ args:
42
+ num_few_shot: 10
43
+ metrics:
44
+ - type: acc_norm
45
+ value: 86.43
46
+ name: normalized accuracy
47
+ source:
48
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
49
+ name: Open LLM Leaderboard
50
+ - task:
51
+ type: text-generation
52
+ name: Text Generation
53
+ dataset:
54
+ name: MMLU (5-Shot)
55
+ type: cais/mmlu
56
+ config: all
57
+ split: test
58
+ args:
59
+ num_few_shot: 5
60
+ metrics:
61
+ - type: acc
62
+ value: 63.58
63
+ name: accuracy
64
+ source:
65
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
66
+ name: Open LLM Leaderboard
67
+ - task:
68
+ type: text-generation
69
+ name: Text Generation
70
+ dataset:
71
+ name: TruthfulQA (0-shot)
72
+ type: truthful_qa
73
+ config: multiple_choice
74
+ split: validation
75
+ args:
76
+ num_few_shot: 0
77
+ metrics:
78
+ - type: mc2
79
+ value: 63.25
80
+ source:
81
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
82
+ name: Open LLM Leaderboard
83
+ - task:
84
+ type: text-generation
85
+ name: Text Generation
86
+ dataset:
87
+ name: Winogrande (5-shot)
88
+ type: winogrande
89
+ config: winogrande_xl
90
+ split: validation
91
+ args:
92
+ num_few_shot: 5
93
+ metrics:
94
+ - type: acc
95
+ value: 78.53
96
+ name: accuracy
97
+ source:
98
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
99
+ name: Open LLM Leaderboard
100
+ - task:
101
+ type: text-generation
102
+ name: Text Generation
103
+ dataset:
104
+ name: GSM8k (5-shot)
105
+ type: gsm8k
106
+ config: main
107
+ split: test
108
+ args:
109
+ num_few_shot: 5
110
+ metrics:
111
+ - type: acc
112
+ value: 63.84
113
+ name: accuracy
114
+ source:
115
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Mistral_Sonyichi-7B-slerp
116
+ name: Open LLM Leaderboard
117
  ---
118
  # merged
119
  ![intro](332f1afc-d0b6-47f8-8a1c-b4bdccea94b4.png "Intro")
 
152
  model: SanjiWatsuki/Sonya-7B
153
  - layer_range: [0, 32]
154
  model: SanjiWatsuki/Kunoichi-7B
155
+ ```
156
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
157
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_s3nh__Mistral_Sonyichi-7B-slerp)
158
+
159
+ | Metric |Value|
160
+ |---------------------------------|----:|
161
+ |Avg. |70.52|
162
+ |AI2 Reasoning Challenge (25-Shot)|67.49|
163
+ |HellaSwag (10-Shot) |86.43|
164
+ |MMLU (5-Shot) |63.58|
165
+ |TruthfulQA (0-shot) |63.25|
166
+ |Winogrande (5-shot) |78.53|
167
+ |GSM8k (5-shot) |63.84|
168
+