Files changed (1) hide show
  1. README.md +121 -4
README.md CHANGED
@@ -1,4 +1,8 @@
1
  ---
 
 
 
 
2
  base_model:
3
  - mistralai/Mixtral-8x7B-v0.1
4
  - jondurbin/bagel-dpo-8x7b-v0.2
@@ -6,10 +10,109 @@ base_model:
6
  - mistralai/Mixtral-8x7B-v0.1
7
  - Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora
8
  - mistralai/Mixtral-8x7B-Instruct-v0.1
9
- tags:
10
- - mergekit
11
- - merge
12
- license: cc-by-nc-4.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
  # BagelMIsteryTour-v2-8x7B
15
 
@@ -71,3 +174,17 @@ dtype: bfloat16
71
 
72
 
73
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - mergekit
5
+ - merge
6
  base_model:
7
  - mistralai/Mixtral-8x7B-v0.1
8
  - jondurbin/bagel-dpo-8x7b-v0.2
 
10
  - mistralai/Mixtral-8x7B-v0.1
11
  - Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora
12
  - mistralai/Mixtral-8x7B-Instruct-v0.1
13
+ model-index:
14
+ - name: BagelMIsteryTour-v2-8x7B
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: 72.7
29
+ name: normalized accuracy
30
+ source:
31
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
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: 87.36
45
+ name: normalized accuracy
46
+ source:
47
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
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: 71.16
62
+ name: accuracy
63
+ source:
64
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
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: 74.54
79
+ source:
80
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
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: 82.64
95
+ name: accuracy
96
+ source:
97
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
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: 61.33
112
+ name: accuracy
113
+ source:
114
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ycros/BagelMIsteryTour-v2-8x7B
115
+ name: Open LLM Leaderboard
116
  ---
117
  # BagelMIsteryTour-v2-8x7B
118
 
 
174
 
175
 
176
  ```
177
+
178
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
179
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ycros__BagelMIsteryTour-v2-8x7B)
180
+
181
+ | Metric |Value|
182
+ |---------------------------------|----:|
183
+ |Avg. |74.95|
184
+ |AI2 Reasoning Challenge (25-Shot)|72.70|
185
+ |HellaSwag (10-Shot) |87.36|
186
+ |MMLU (5-Shot) |71.16|
187
+ |TruthfulQA (0-shot) |74.54|
188
+ |Winogrande (5-shot) |82.64|
189
+ |GSM8k (5-shot) |61.33|
190
+