zelk12 commited on
Commit
a410434
1 Parent(s): fd68607

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (45ea433aa58fe28e1eb3fd4149b11c4097944e0f)

Files changed (1) hide show
  1. README.md +113 -5
README.md CHANGED
@@ -1,12 +1,107 @@
1
  ---
2
- base_model:
3
- - zelk12/MT-Merge-gemma-2-9B
4
- - allknowingroger/Gemmaslerp2-9B
5
  library_name: transformers
6
  tags:
7
  - mergekit
8
  - merge
9
- license: gemma
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
  # merge
12
 
@@ -36,4 +131,17 @@ base_model: allknowingroger/Gemmaslerp2-9B
36
  dtype: bfloat16
37
  parameters:
38
  t: 0.25
39
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: gemma
 
 
3
  library_name: transformers
4
  tags:
5
  - mergekit
6
  - merge
7
+ base_model:
8
+ - zelk12/MT-Merge-gemma-2-9B
9
+ - allknowingroger/Gemmaslerp2-9B
10
+ model-index:
11
+ - name: gemma-2-S2MTM-9B
12
+ results:
13
+ - task:
14
+ type: text-generation
15
+ name: Text Generation
16
+ dataset:
17
+ name: IFEval (0-Shot)
18
+ type: HuggingFaceH4/ifeval
19
+ args:
20
+ num_few_shot: 0
21
+ metrics:
22
+ - type: inst_level_strict_acc and prompt_level_strict_acc
23
+ value: 78.23
24
+ name: strict accuracy
25
+ source:
26
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/gemma-2-S2MTM-9B
27
+ name: Open LLM Leaderboard
28
+ - task:
29
+ type: text-generation
30
+ name: Text Generation
31
+ dataset:
32
+ name: BBH (3-Shot)
33
+ type: BBH
34
+ args:
35
+ num_few_shot: 3
36
+ metrics:
37
+ - type: acc_norm
38
+ value: 43.12
39
+ name: normalized accuracy
40
+ source:
41
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/gemma-2-S2MTM-9B
42
+ name: Open LLM Leaderboard
43
+ - task:
44
+ type: text-generation
45
+ name: Text Generation
46
+ dataset:
47
+ name: MATH Lvl 5 (4-Shot)
48
+ type: hendrycks/competition_math
49
+ args:
50
+ num_few_shot: 4
51
+ metrics:
52
+ - type: exact_match
53
+ value: 4.0
54
+ name: exact match
55
+ source:
56
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/gemma-2-S2MTM-9B
57
+ name: Open LLM Leaderboard
58
+ - task:
59
+ type: text-generation
60
+ name: Text Generation
61
+ dataset:
62
+ name: GPQA (0-shot)
63
+ type: Idavidrein/gpqa
64
+ args:
65
+ num_few_shot: 0
66
+ metrics:
67
+ - type: acc_norm
68
+ value: 12.75
69
+ name: acc_norm
70
+ source:
71
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/gemma-2-S2MTM-9B
72
+ name: Open LLM Leaderboard
73
+ - task:
74
+ type: text-generation
75
+ name: Text Generation
76
+ dataset:
77
+ name: MuSR (0-shot)
78
+ type: TAUR-Lab/MuSR
79
+ args:
80
+ num_few_shot: 0
81
+ metrics:
82
+ - type: acc_norm
83
+ value: 12.16
84
+ name: acc_norm
85
+ source:
86
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/gemma-2-S2MTM-9B
87
+ name: Open LLM Leaderboard
88
+ - task:
89
+ type: text-generation
90
+ name: Text Generation
91
+ dataset:
92
+ name: MMLU-PRO (5-shot)
93
+ type: TIGER-Lab/MMLU-Pro
94
+ config: main
95
+ split: test
96
+ args:
97
+ num_few_shot: 5
98
+ metrics:
99
+ - type: acc
100
+ value: 36.63
101
+ name: accuracy
102
+ source:
103
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=zelk12/gemma-2-S2MTM-9B
104
+ name: Open LLM Leaderboard
105
  ---
106
  # merge
107
 
 
131
  dtype: bfloat16
132
  parameters:
133
  t: 0.25
134
+ ```
135
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
136
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/zelk12__gemma-2-S2MTM-9B-details)
137
+
138
+ | Metric |Value|
139
+ |-------------------|----:|
140
+ |Avg. |31.15|
141
+ |IFEval (0-Shot) |78.23|
142
+ |BBH (3-Shot) |43.12|
143
+ |MATH Lvl 5 (4-Shot)| 4.00|
144
+ |GPQA (0-shot) |12.75|
145
+ |MuSR (0-shot) |12.16|
146
+ |MMLU-PRO (5-shot) |36.63|
147
+