Files changed (1) hide show
  1. README.md +122 -6
README.md CHANGED
@@ -1,17 +1,120 @@
1
  ---
 
 
 
 
2
  tags:
3
  - text2text-generation
4
  datasets:
5
  - kaist-ai/Feedback-Collection
6
- license: apache-2.0
7
- language:
8
- - en
9
- pipeline_tag: text2text-generation
10
- library_name: transformers
11
  metrics:
12
  - pearsonr
13
  - spearmanr
14
  - accuracy
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  ---
16
  ## Links for Reference
17
 
@@ -207,4 +310,17 @@ If you find the following model helpful, please consider citing our paper!
207
  archivePrefix={arXiv},
208
  primaryClass={cs.CL}
209
  }
210
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ library_name: transformers
6
  tags:
7
  - text2text-generation
8
  datasets:
9
  - kaist-ai/Feedback-Collection
 
 
 
 
 
10
  metrics:
11
  - pearsonr
12
  - spearmanr
13
  - accuracy
14
+ pipeline_tag: text2text-generation
15
+ model-index:
16
+ - name: prometheus-13b-v1.0
17
+ results:
18
+ - task:
19
+ type: text-generation
20
+ name: Text Generation
21
+ dataset:
22
+ name: AI2 Reasoning Challenge (25-Shot)
23
+ type: ai2_arc
24
+ config: ARC-Challenge
25
+ split: test
26
+ args:
27
+ num_few_shot: 25
28
+ metrics:
29
+ - type: acc_norm
30
+ value: 53.24
31
+ name: normalized accuracy
32
+ source:
33
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-v1.0
34
+ name: Open LLM Leaderboard
35
+ - task:
36
+ type: text-generation
37
+ name: Text Generation
38
+ dataset:
39
+ name: HellaSwag (10-Shot)
40
+ type: hellaswag
41
+ split: validation
42
+ args:
43
+ num_few_shot: 10
44
+ metrics:
45
+ - type: acc_norm
46
+ value: 80.75
47
+ name: normalized accuracy
48
+ source:
49
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-v1.0
50
+ name: Open LLM Leaderboard
51
+ - task:
52
+ type: text-generation
53
+ name: Text Generation
54
+ dataset:
55
+ name: MMLU (5-Shot)
56
+ type: cais/mmlu
57
+ config: all
58
+ split: test
59
+ args:
60
+ num_few_shot: 5
61
+ metrics:
62
+ - type: acc
63
+ value: 51.49
64
+ name: accuracy
65
+ source:
66
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-v1.0
67
+ name: Open LLM Leaderboard
68
+ - task:
69
+ type: text-generation
70
+ name: Text Generation
71
+ dataset:
72
+ name: TruthfulQA (0-shot)
73
+ type: truthful_qa
74
+ config: multiple_choice
75
+ split: validation
76
+ args:
77
+ num_few_shot: 0
78
+ metrics:
79
+ - type: mc2
80
+ value: 45.66
81
+ source:
82
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-v1.0
83
+ name: Open LLM Leaderboard
84
+ - task:
85
+ type: text-generation
86
+ name: Text Generation
87
+ dataset:
88
+ name: Winogrande (5-shot)
89
+ type: winogrande
90
+ config: winogrande_xl
91
+ split: validation
92
+ args:
93
+ num_few_shot: 5
94
+ metrics:
95
+ - type: acc
96
+ value: 73.72
97
+ name: accuracy
98
+ source:
99
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-v1.0
100
+ name: Open LLM Leaderboard
101
+ - task:
102
+ type: text-generation
103
+ name: Text Generation
104
+ dataset:
105
+ name: GSM8k (5-shot)
106
+ type: gsm8k
107
+ config: main
108
+ split: test
109
+ args:
110
+ num_few_shot: 5
111
+ metrics:
112
+ - type: acc
113
+ value: 31.69
114
+ name: accuracy
115
+ source:
116
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai/prometheus-13b-v1.0
117
+ name: Open LLM Leaderboard
118
  ---
119
  ## Links for Reference
120
 
 
310
  archivePrefix={arXiv},
311
  primaryClass={cs.CL}
312
  }
313
+ ```
314
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
315
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_kaist-ai__prometheus-13b-v1.0)
316
+
317
+ | Metric |Value|
318
+ |---------------------------------|----:|
319
+ |Avg. |56.09|
320
+ |AI2 Reasoning Challenge (25-Shot)|53.24|
321
+ |HellaSwag (10-Shot) |80.75|
322
+ |MMLU (5-Shot) |51.49|
323
+ |TruthfulQA (0-shot) |45.66|
324
+ |Winogrande (5-shot) |73.72|
325
+ |GSM8k (5-shot) |31.69|
326
+