Files changed (1) hide show
  1. README.md +118 -2
README.md CHANGED
@@ -6,10 +6,113 @@ tags:
6
  - lazymergekit
7
  - microsoft/Orca-2-13b
8
  - KoboldAI/LLaMA2-13B-Psyfighter2
9
- license_name: microsoft-research-license
10
  base_model:
11
  - KoboldAI/LLaMA2-13B-Psyfighter2
12
  - microsoft/Orca-2-13b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
 
15
  # Psyfighter2-Orca2-ties
@@ -35,4 +138,17 @@ parameters:
35
  normalize: true
36
  int8_mask: true
37
  dtype: float16
38
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  - lazymergekit
7
  - microsoft/Orca-2-13b
8
  - KoboldAI/LLaMA2-13B-Psyfighter2
 
9
  base_model:
10
  - KoboldAI/LLaMA2-13B-Psyfighter2
11
  - microsoft/Orca-2-13b
12
+ license_name: microsoft-research-license
13
+ model-index:
14
+ - name: Psyfighter2-Orca2-13B-ties
15
+ results:
16
+ - task:
17
+ type: text-generation
18
+ name: Text Generation
19
+ dataset:
20
+ name: AI2 Reasoning Challenge (25-Shot)
21
+ type: ai2_arc
22
+ config: ARC-Challenge
23
+ split: test
24
+ args:
25
+ num_few_shot: 25
26
+ metrics:
27
+ - type: acc_norm
28
+ value: 62.46
29
+ name: normalized accuracy
30
+ source:
31
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
32
+ name: Open LLM Leaderboard
33
+ - task:
34
+ type: text-generation
35
+ name: Text Generation
36
+ dataset:
37
+ name: HellaSwag (10-Shot)
38
+ type: hellaswag
39
+ split: validation
40
+ args:
41
+ num_few_shot: 10
42
+ metrics:
43
+ - type: acc_norm
44
+ value: 81.74
45
+ name: normalized accuracy
46
+ source:
47
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
48
+ name: Open LLM Leaderboard
49
+ - task:
50
+ type: text-generation
51
+ name: Text Generation
52
+ dataset:
53
+ name: MMLU (5-Shot)
54
+ type: cais/mmlu
55
+ config: all
56
+ split: test
57
+ args:
58
+ num_few_shot: 5
59
+ metrics:
60
+ - type: acc
61
+ value: 60.31
62
+ name: accuracy
63
+ source:
64
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
65
+ name: Open LLM Leaderboard
66
+ - task:
67
+ type: text-generation
68
+ name: Text Generation
69
+ dataset:
70
+ name: TruthfulQA (0-shot)
71
+ type: truthful_qa
72
+ config: multiple_choice
73
+ split: validation
74
+ args:
75
+ num_few_shot: 0
76
+ metrics:
77
+ - type: mc2
78
+ value: 55.4
79
+ source:
80
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
81
+ name: Open LLM Leaderboard
82
+ - task:
83
+ type: text-generation
84
+ name: Text Generation
85
+ dataset:
86
+ name: Winogrande (5-shot)
87
+ type: winogrande
88
+ config: winogrande_xl
89
+ split: validation
90
+ args:
91
+ num_few_shot: 5
92
+ metrics:
93
+ - type: acc
94
+ value: 77.27
95
+ name: accuracy
96
+ source:
97
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
98
+ name: Open LLM Leaderboard
99
+ - task:
100
+ type: text-generation
101
+ name: Text Generation
102
+ dataset:
103
+ name: GSM8k (5-shot)
104
+ type: gsm8k
105
+ config: main
106
+ split: test
107
+ args:
108
+ num_few_shot: 5
109
+ metrics:
110
+ - type: acc
111
+ value: 43.67
112
+ name: accuracy
113
+ source:
114
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tuantran1632001/Psyfighter2-Orca2-13B-ties
115
+ name: Open LLM Leaderboard
116
  ---
117
 
118
  # Psyfighter2-Orca2-ties
 
138
  normalize: true
139
  int8_mask: true
140
  dtype: float16
141
+ ```
142
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
143
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_tuantran1632001__Psyfighter2-Orca2-13B-ties)
144
+
145
+ | Metric |Value|
146
+ |---------------------------------|----:|
147
+ |Avg. |63.48|
148
+ |AI2 Reasoning Challenge (25-Shot)|62.46|
149
+ |HellaSwag (10-Shot) |81.74|
150
+ |MMLU (5-Shot) |60.31|
151
+ |TruthfulQA (0-shot) |55.40|
152
+ |Winogrande (5-shot) |77.27|
153
+ |GSM8k (5-shot) |43.67|
154
+