Files changed (1) hide show
  1. README.md +121 -5
README.md CHANGED
@@ -1,14 +1,117 @@
1
  ---
 
 
 
 
2
  base_model:
3
  - simonveitner/Math-OpenHermes-2.5-Mistral-7B
4
  - mlabonne/NeuralHermes-2.5-Mistral-7B-laser
5
  - openaccess-ai-collective/dpopenhermes-alpha-v0
6
  - teknium/OpenHermes-2.5-Mistral-7B
7
  - mlabonne/NeuralHermes-2.5-Mistral-7B
8
- tags:
9
- - mergekit
10
- - merge
11
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
  # merged
14
 
@@ -55,4 +158,17 @@ slices:
55
  model: mlabonne/NeuralHermes-2.5-Mistral-7B-laser
56
  parameters:
57
  weight: 0.25
58
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ tags:
4
+ - mergekit
5
+ - merge
6
  base_model:
7
  - simonveitner/Math-OpenHermes-2.5-Mistral-7B
8
  - mlabonne/NeuralHermes-2.5-Mistral-7B-laser
9
  - openaccess-ai-collective/dpopenhermes-alpha-v0
10
  - teknium/OpenHermes-2.5-Mistral-7B
11
  - mlabonne/NeuralHermes-2.5-Mistral-7B
12
+ model-index:
13
+ - name: Hermes-low-tune-2
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: 65.61
28
+ name: normalized accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-2
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: 84.47
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-2
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: 63.69
61
+ name: accuracy
62
+ source:
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-2
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: 53.18
78
+ source:
79
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-2
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: 77.74
94
+ name: accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-2
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: 63.53
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Hermes-low-tune-2
114
+ name: Open LLM Leaderboard
115
  ---
116
  # merged
117
 
 
158
  model: mlabonne/NeuralHermes-2.5-Mistral-7B-laser
159
  parameters:
160
  weight: 0.25
161
+ ```
162
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
163
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nlpguy__Hermes-low-tune-2)
164
+
165
+ | Metric |Value|
166
+ |---------------------------------|----:|
167
+ |Avg. |68.04|
168
+ |AI2 Reasoning Challenge (25-Shot)|65.61|
169
+ |HellaSwag (10-Shot) |84.47|
170
+ |MMLU (5-Shot) |63.69|
171
+ |TruthfulQA (0-shot) |53.18|
172
+ |Winogrande (5-shot) |77.74|
173
+ |GSM8k (5-shot) |63.53|
174
+