Files changed (1) hide show
  1. README.md +120 -3
README.md CHANGED
@@ -1,14 +1,117 @@
1
  ---
 
 
 
2
  datasets:
3
  - ehartford/dolphin
4
  - jondurbin/airoboros-2.2.1
5
  - ehartford/samantha-data
6
  - ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
7
- language:
8
- - en
9
- license: other
10
  license_name: yi-license
11
  license_link: LICENSE
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  Dolphin 2.2 🐬
@@ -95,3 +198,17 @@ Both theories have their strengths and weaknesses, and neither has achieved wide
95
  [I also have some swag you can buy](https://fa7113.myshopify.com/)
96
 
97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ license: other
5
  datasets:
6
  - ehartford/dolphin
7
  - jondurbin/airoboros-2.2.1
8
  - ehartford/samantha-data
9
  - ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
 
 
 
10
  license_name: yi-license
11
  license_link: LICENSE
12
+ model-index:
13
+ - name: dolphin-2.2-yi-34b-200k
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: 42.15
28
+ name: normalized accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
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: 68.18
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
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: 55.47
61
+ name: accuracy
62
+ source:
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
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: 45.93
78
+ source:
79
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
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: 64.56
94
+ name: accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
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: 3.71
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
114
+ name: Open LLM Leaderboard
115
  ---
116
 
117
  Dolphin 2.2 🐬
 
198
  [I also have some swag you can buy](https://fa7113.myshopify.com/)
199
 
200
 
201
+
202
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
203
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__dolphin-2.2-yi-34b-200k)
204
+
205
+ | Metric |Value|
206
+ |---------------------------------|----:|
207
+ |Avg. |46.67|
208
+ |AI2 Reasoning Challenge (25-Shot)|42.15|
209
+ |HellaSwag (10-Shot) |68.18|
210
+ |MMLU (5-Shot) |55.47|
211
+ |TruthfulQA (0-shot) |45.93|
212
+ |Winogrande (5-shot) |64.56|
213
+ |GSM8k (5-shot) | 3.71|
214
+