Files changed (1) hide show
  1. README.md +118 -2
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- base_model: mlabonne/NeuralMarcoro14-7B
3
  license: apache-2.0
4
  tags:
5
  - mlabonne/NeuralMarcoro14-7B
@@ -9,6 +8,110 @@ tags:
9
  - mistral
10
  datasets:
11
  - hromi/winograd_dpo_basic
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  ![](https://wizzion.com/sojka.jpg)
@@ -68,4 +171,17 @@ Originally I planned to call the model "ContaminatedWine" but then I had a nice
68
  # Thanks
69
  Thanks to mlabonne and Cultrix for demonstrating that DPO is not 'rocket science' but within reach of anyone with an idea, a dataset and a GPU.
70
 
71
- And thanks to [unslothai](https://github.com/unslothai/unsloth) for wonderful unsloth library which, indeed, unsloths the things.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  license: apache-2.0
3
  tags:
4
  - mlabonne/NeuralMarcoro14-7B
 
8
  - mistral
9
  datasets:
10
  - hromi/winograd_dpo_basic
11
+ base_model: mlabonne/NeuralMarcoro14-7B
12
+ model-index:
13
+ - name: Garrulus
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: 73.29
28
+ name: normalized accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Garrulus
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: 88.87
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Garrulus
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: 64.57
61
+ name: accuracy
62
+ source:
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Garrulus
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: 68.23
78
+ source:
79
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Garrulus
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: 91.48
94
+ name: accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Garrulus
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: 64.52
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=udkai/Garrulus
114
+ name: Open LLM Leaderboard
115
  ---
116
 
117
  ![](https://wizzion.com/sojka.jpg)
 
171
  # Thanks
172
  Thanks to mlabonne and Cultrix for demonstrating that DPO is not 'rocket science' but within reach of anyone with an idea, a dataset and a GPU.
173
 
174
+ And thanks to [unslothai](https://github.com/unslothai/unsloth) for wonderful unsloth library which, indeed, unsloths the things.
175
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
176
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_udkai__Garrulus)
177
+
178
+ | Metric |Value|
179
+ |---------------------------------|----:|
180
+ |Avg. |75.16|
181
+ |AI2 Reasoning Challenge (25-Shot)|73.29|
182
+ |HellaSwag (10-Shot) |88.87|
183
+ |MMLU (5-Shot) |64.57|
184
+ |TruthfulQA (0-shot) |68.23|
185
+ |Winogrande (5-shot) |91.48|
186
+ |GSM8k (5-shot) |64.52|
187
+