Files changed (1) hide show
  1. README.md +118 -2
README.md CHANGED
@@ -1,12 +1,115 @@
1
  ---
2
  license: cc-by-nc-4.0
3
- base_model: mlabonne/Beagle14-7B
4
  tags:
5
  - merge
6
  - mergekit
7
  - lazymergekit
8
  - dpo
9
  - rlhf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  ![](https://i.imgur.com/89ZAKcn.png)
@@ -97,4 +200,17 @@ print(outputs[0]["generated_text"])
97
  <a href="https://github.com/argilla-io/distilabel">
98
  <img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/>
99
  </a>
100
- </p>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-nc-4.0
 
3
  tags:
4
  - merge
5
  - mergekit
6
  - lazymergekit
7
  - dpo
8
  - rlhf
9
+ base_model: mlabonne/Beagle14-7B
10
+ model-index:
11
+ - name: NeuralBeagle14-7B
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: 72.95
26
+ name: normalized accuracy
27
+ source:
28
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralBeagle14-7B
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: 88.34
42
+ name: normalized accuracy
43
+ source:
44
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralBeagle14-7B
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: 64.55
59
+ name: accuracy
60
+ source:
61
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralBeagle14-7B
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: 69.93
76
+ source:
77
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralBeagle14-7B
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: 82.4
92
+ name: accuracy
93
+ source:
94
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralBeagle14-7B
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: 70.28
109
+ name: accuracy
110
+ source:
111
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralBeagle14-7B
112
+ name: Open LLM Leaderboard
113
  ---
114
 
115
  ![](https://i.imgur.com/89ZAKcn.png)
 
200
  <a href="https://github.com/argilla-io/distilabel">
201
  <img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/>
202
  </a>
203
+ </p>
204
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
205
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mlabonne__NeuralBeagle14-7B)
206
+
207
+ | Metric |Value|
208
+ |---------------------------------|----:|
209
+ |Avg. |74.74|
210
+ |AI2 Reasoning Challenge (25-Shot)|72.95|
211
+ |HellaSwag (10-Shot) |88.34|
212
+ |MMLU (5-Shot) |64.55|
213
+ |TruthfulQA (0-shot) |69.93|
214
+ |Winogrande (5-shot) |82.40|
215
+ |GSM8k (5-shot) |70.28|
216
+