Hugging Face's logo

saishf
/
SOVL-Mega-Mash-L3-8B

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
2
saishf leaderboard-pr-bot commited on
Commit
2fbf356
•
1 Parent(s): bf2d420

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (2c83504dc52498e1a1b4cb4349cc14b59454a402)


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

Files changed (1) hide show
  1. README.md +121 -5
README.md CHANGED
@@ -1,15 +1,117 @@
1
  ---
2
  license: cc-by-nc-4.0
 
 
 
 
3
  base_model:
4
  - saishf/SOVLish-Maid-L3-8B
5
  - saishf/Ortho-SOVL-8B-L3
6
  - saishf/Merge-Mayhem-L3-V2
7
  - saishf/Merge-Mayhem-L3-V2.1
8
- library_name: transformers
9
- tags:
10
- - mergekit
11
- - merge
12
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
  # merge
15
 
@@ -42,3 +144,17 @@ merge_method: model_stock
42
  base_model: saishf/Ortho-SOVL-8B-L3
43
  dtype: bfloat16
44
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-nc-4.0
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
  base_model:
8
  - saishf/SOVLish-Maid-L3-8B
9
  - saishf/Ortho-SOVL-8B-L3
10
  - saishf/Merge-Mayhem-L3-V2
11
  - saishf/Merge-Mayhem-L3-V2.1
12
+ model-index:
13
+ - name: SOVL-Mega-Mash-L3-8B
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ name: Text Generation
18
+ dataset:
19
+ name: AI2 Reasoning Challenge (25-Shot)
20
+ type: ai2_arc
21
+ config: ARC-Challenge
22
+ split: test
23
+ args:
24
+ num_few_shot: 25
25
+ metrics:
26
+ - type: acc_norm
27
+ value: 62.03
28
+ name: normalized accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
31
+ name: Open LLM Leaderboard
32
+ - task:
33
+ type: text-generation
34
+ name: Text Generation
35
+ dataset:
36
+ name: HellaSwag (10-Shot)
37
+ type: hellaswag
38
+ split: validation
39
+ args:
40
+ num_few_shot: 10
41
+ metrics:
42
+ - type: acc_norm
43
+ value: 79.68
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
47
+ name: Open LLM Leaderboard
48
+ - task:
49
+ type: text-generation
50
+ name: Text Generation
51
+ dataset:
52
+ name: MMLU (5-Shot)
53
+ type: cais/mmlu
54
+ config: all
55
+ split: test
56
+ args:
57
+ num_few_shot: 5
58
+ metrics:
59
+ - type: acc
60
+ value: 67.64
61
+ name: accuracy
62
+ source:
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
64
+ name: Open LLM Leaderboard
65
+ - task:
66
+ type: text-generation
67
+ name: Text Generation
68
+ dataset:
69
+ name: TruthfulQA (0-shot)
70
+ type: truthful_qa
71
+ config: multiple_choice
72
+ split: validation
73
+ args:
74
+ num_few_shot: 0
75
+ metrics:
76
+ - type: mc2
77
+ value: 51.84
78
+ source:
79
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
80
+ name: Open LLM Leaderboard
81
+ - task:
82
+ type: text-generation
83
+ name: Text Generation
84
+ dataset:
85
+ name: Winogrande (5-shot)
86
+ type: winogrande
87
+ config: winogrande_xl
88
+ split: validation
89
+ args:
90
+ num_few_shot: 5
91
+ metrics:
92
+ - type: acc
93
+ value: 76.16
94
+ name: accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
97
+ name: Open LLM Leaderboard
98
+ - task:
99
+ type: text-generation
100
+ name: Text Generation
101
+ dataset:
102
+ name: GSM8k (5-shot)
103
+ type: gsm8k
104
+ config: main
105
+ split: test
106
+ args:
107
+ num_few_shot: 5
108
+ metrics:
109
+ - type: acc
110
+ value: 67.25
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/SOVL-Mega-Mash-L3-8B
114
+ name: Open LLM Leaderboard
115
  ---
116
  # merge
117
 
 
144
  base_model: saishf/Ortho-SOVL-8B-L3
145
  dtype: bfloat16
146
  ```
147
+
148
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
149
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_saishf__SOVL-Mega-Mash-L3-8B)
150
+
151
+ | Metric |Value|
152
+ |---------------------------------|----:|
153
+ |Avg. |67.43|
154
+ |AI2 Reasoning Challenge (25-Shot)|62.03|
155
+ |HellaSwag (10-Shot) |79.68|
156
+ |MMLU (5-Shot) |67.64|
157
+ |TruthfulQA (0-shot) |51.84|
158
+ |Winogrande (5-shot) |76.16|
159
+ |GSM8k (5-shot) |67.25|
160
+