Files changed (1) hide show
  1. README.md +118 -1
README.md CHANGED
@@ -1,12 +1,115 @@
1
  ---
2
  language:
3
  - en
4
- library_name: transformers
5
  license: other
 
6
  datasets:
7
  - psmathur/orca_mini_v1_dataset
8
  - ehartford/dolphin
9
  pipeline_tag: text-generation
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  # orca_mini_v3_70b
@@ -183,3 +286,17 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
183
  | Winogrande (5-shot) | 82.72 |
184
  | GSM8K (5-shot) | 40.86 |
185
  | DROP (3-shot) | 40.17 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  language:
3
  - en
 
4
  license: other
5
+ library_name: transformers
6
  datasets:
7
  - psmathur/orca_mini_v1_dataset
8
  - ehartford/dolphin
9
  pipeline_tag: text-generation
10
+ model-index:
11
+ - name: orca_mini_v3_70b
12
+ results:
13
+ - task:
14
+ type: text-generation
15
+ name: Text Generation
16
+ dataset:
17
+ name: AI2 Reasoning Challenge (25-Shot)
18
+ type: ai2_arc
19
+ config: ARC-Challenge
20
+ split: test
21
+ args:
22
+ num_few_shot: 25
23
+ metrics:
24
+ - type: acc_norm
25
+ value: 71.25
26
+ name: normalized accuracy
27
+ source:
28
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v3_70b
29
+ name: Open LLM Leaderboard
30
+ - task:
31
+ type: text-generation
32
+ name: Text Generation
33
+ dataset:
34
+ name: HellaSwag (10-Shot)
35
+ type: hellaswag
36
+ split: validation
37
+ args:
38
+ num_few_shot: 10
39
+ metrics:
40
+ - type: acc_norm
41
+ value: 87.85
42
+ name: normalized accuracy
43
+ source:
44
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v3_70b
45
+ name: Open LLM Leaderboard
46
+ - task:
47
+ type: text-generation
48
+ name: Text Generation
49
+ dataset:
50
+ name: MMLU (5-Shot)
51
+ type: cais/mmlu
52
+ config: all
53
+ split: test
54
+ args:
55
+ num_few_shot: 5
56
+ metrics:
57
+ - type: acc
58
+ value: 70.18
59
+ name: accuracy
60
+ source:
61
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v3_70b
62
+ name: Open LLM Leaderboard
63
+ - task:
64
+ type: text-generation
65
+ name: Text Generation
66
+ dataset:
67
+ name: TruthfulQA (0-shot)
68
+ type: truthful_qa
69
+ config: multiple_choice
70
+ split: validation
71
+ args:
72
+ num_few_shot: 0
73
+ metrics:
74
+ - type: mc2
75
+ value: 61.27
76
+ source:
77
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v3_70b
78
+ name: Open LLM Leaderboard
79
+ - task:
80
+ type: text-generation
81
+ name: Text Generation
82
+ dataset:
83
+ name: Winogrande (5-shot)
84
+ type: winogrande
85
+ config: winogrande_xl
86
+ split: validation
87
+ args:
88
+ num_few_shot: 5
89
+ metrics:
90
+ - type: acc
91
+ value: 82.72
92
+ name: accuracy
93
+ source:
94
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v3_70b
95
+ name: Open LLM Leaderboard
96
+ - task:
97
+ type: text-generation
98
+ name: Text Generation
99
+ dataset:
100
+ name: GSM8k (5-shot)
101
+ type: gsm8k
102
+ config: main
103
+ split: test
104
+ args:
105
+ num_few_shot: 5
106
+ metrics:
107
+ - type: acc
108
+ value: 40.86
109
+ name: accuracy
110
+ source:
111
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v3_70b
112
+ name: Open LLM Leaderboard
113
  ---
114
 
115
  # orca_mini_v3_70b
 
286
  | Winogrande (5-shot) | 82.72 |
287
  | GSM8K (5-shot) | 40.86 |
288
  | DROP (3-shot) | 40.17 |
289
+
290
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
291
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__orca_mini_v3_70b)
292
+
293
+ | Metric |Value|
294
+ |---------------------------------|----:|
295
+ |Avg. |69.02|
296
+ |AI2 Reasoning Challenge (25-Shot)|71.25|
297
+ |HellaSwag (10-Shot) |87.85|
298
+ |MMLU (5-Shot) |70.18|
299
+ |TruthfulQA (0-shot) |61.27|
300
+ |Winogrande (5-shot) |82.72|
301
+ |GSM8k (5-shot) |40.86|
302
+