Commit
9e6dcfc
1 Parent(s): d8a9d1c

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (4f0a64ad16fde4c996b383da2f2d9a7b2b17cd3c)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +29 -22
README.md CHANGED
@@ -1,17 +1,19 @@
1
  ---
2
- base_model:
3
- - SanjiWatsuki/Silicon-Maid-7B
4
- - Guilherme34/Samantha-v2
5
- - jan-hq/stealth-v1.3
6
- - mitultiwari/mistral-7B-instruct-dpo
7
- - senseable/WestLake-7B-v2
8
  library_name: transformers
9
  tags:
10
  - mergekit
11
  - merge
12
  datasets:
13
  - Anthropic/hh-rlhf
14
- license: cc
 
 
 
 
 
15
  model-index:
16
  - name: sethuiyer/Aika-7B
17
  results:
@@ -30,8 +32,7 @@ model-index:
30
  value: 65.36
31
  name: normalized accuracy
32
  source:
33
- url: >-
34
- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
35
  name: Open LLM Leaderboard
36
  - task:
37
  type: text-generation
@@ -47,8 +48,7 @@ model-index:
47
  value: 81.49
48
  name: normalized accuracy
49
  source:
50
- url: >-
51
- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
52
  name: Open LLM Leaderboard
53
  - task:
54
  type: text-generation
@@ -65,8 +65,7 @@ model-index:
65
  value: 53.91
66
  name: accuracy
67
  source:
68
- url: >-
69
- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
70
  name: Open LLM Leaderboard
71
  - task:
72
  type: text-generation
@@ -82,8 +81,7 @@ model-index:
82
  - type: mc2
83
  value: 51.22
84
  source:
85
- url: >-
86
- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
87
  name: Open LLM Leaderboard
88
  - task:
89
  type: text-generation
@@ -100,8 +98,7 @@ model-index:
100
  value: 77.74
101
  name: accuracy
102
  source:
103
- url: >-
104
- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
105
  name: Open LLM Leaderboard
106
  - task:
107
  type: text-generation
@@ -118,11 +115,8 @@ model-index:
118
  value: 25.78
119
  name: accuracy
120
  source:
121
- url: >-
122
- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
123
  name: Open LLM Leaderboard
124
- language:
125
- - en
126
  ---
127
  # Aika-7B
128
 
@@ -158,4 +152,17 @@ You get Aika - a considerate, personal digital assistant.
158
 
159
  ### Configuration
160
 
161
- Please check [mergekit_config.yml](https://huggingface.co/sethuiyer/Aika-7B/blob/main/mergekit_config.yml) for the merge config.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ license: cc
 
 
 
5
  library_name: transformers
6
  tags:
7
  - mergekit
8
  - merge
9
  datasets:
10
  - Anthropic/hh-rlhf
11
+ base_model:
12
+ - SanjiWatsuki/Silicon-Maid-7B
13
+ - Guilherme34/Samantha-v2
14
+ - jan-hq/stealth-v1.3
15
+ - mitultiwari/mistral-7B-instruct-dpo
16
+ - senseable/WestLake-7B-v2
17
  model-index:
18
  - name: sethuiyer/Aika-7B
19
  results:
 
32
  value: 65.36
33
  name: normalized accuracy
34
  source:
35
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
 
36
  name: Open LLM Leaderboard
37
  - task:
38
  type: text-generation
 
48
  value: 81.49
49
  name: normalized accuracy
50
  source:
51
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
 
52
  name: Open LLM Leaderboard
53
  - task:
54
  type: text-generation
 
65
  value: 53.91
66
  name: accuracy
67
  source:
68
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
 
69
  name: Open LLM Leaderboard
70
  - task:
71
  type: text-generation
 
81
  - type: mc2
82
  value: 51.22
83
  source:
84
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
 
85
  name: Open LLM Leaderboard
86
  - task:
87
  type: text-generation
 
98
  value: 77.74
99
  name: accuracy
100
  source:
101
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
 
102
  name: Open LLM Leaderboard
103
  - task:
104
  type: text-generation
 
115
  value: 25.78
116
  name: accuracy
117
  source:
118
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Aika-7B
 
119
  name: Open LLM Leaderboard
 
 
120
  ---
121
  # Aika-7B
122
 
 
152
 
153
  ### Configuration
154
 
155
+ Please check [mergekit_config.yml](https://huggingface.co/sethuiyer/Aika-7B/blob/main/mergekit_config.yml) for the merge config.
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_sethuiyer__Aika-7B)
158
+
159
+ | Metric |Value|
160
+ |---------------------------------|----:|
161
+ |Avg. |59.25|
162
+ |AI2 Reasoning Challenge (25-Shot)|65.36|
163
+ |HellaSwag (10-Shot) |81.49|
164
+ |MMLU (5-Shot) |53.91|
165
+ |TruthfulQA (0-shot) |51.22|
166
+ |Winogrande (5-shot) |77.74|
167
+ |GSM8k (5-shot) |25.78|
168
+