Files changed (1) hide show
  1. README.md +123 -6
README.md CHANGED
@@ -1,13 +1,116 @@
1
  ---
2
- license: cc-by-nc-nd-4.0
3
  language:
4
- - en
 
5
  library_name: transformers
6
- pipeline_tag: text-generation
7
  tags:
8
- - starling
9
- - mistral
10
- - llama-2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <h1 style="font-size: 36px;">Velara-11b</h1>
@@ -79,3 +182,17 @@ PENDING
79
 
80
  # Training Data:
81
  PENDING
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  language:
3
+ - en
4
+ license: cc-by-nc-nd-4.0
5
  library_name: transformers
 
6
  tags:
7
+ - starling
8
+ - mistral
9
+ - llama-2
10
+ pipeline_tag: text-generation
11
+ model-index:
12
+ - name: Velara
13
+ results:
14
+ - task:
15
+ type: text-generation
16
+ name: Text Generation
17
+ dataset:
18
+ name: AI2 Reasoning Challenge (25-Shot)
19
+ type: ai2_arc
20
+ config: ARC-Challenge
21
+ split: test
22
+ args:
23
+ num_few_shot: 25
24
+ metrics:
25
+ - type: acc_norm
26
+ value: 58.96
27
+ name: normalized accuracy
28
+ source:
29
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara
30
+ name: Open LLM Leaderboard
31
+ - task:
32
+ type: text-generation
33
+ name: Text Generation
34
+ dataset:
35
+ name: HellaSwag (10-Shot)
36
+ type: hellaswag
37
+ split: validation
38
+ args:
39
+ num_few_shot: 10
40
+ metrics:
41
+ - type: acc_norm
42
+ value: 82.83
43
+ name: normalized accuracy
44
+ source:
45
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara
46
+ name: Open LLM Leaderboard
47
+ - task:
48
+ type: text-generation
49
+ name: Text Generation
50
+ dataset:
51
+ name: MMLU (5-Shot)
52
+ type: cais/mmlu
53
+ config: all
54
+ split: test
55
+ args:
56
+ num_few_shot: 5
57
+ metrics:
58
+ - type: acc
59
+ value: 59.45
60
+ name: accuracy
61
+ source:
62
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara
63
+ name: Open LLM Leaderboard
64
+ - task:
65
+ type: text-generation
66
+ name: Text Generation
67
+ dataset:
68
+ name: TruthfulQA (0-shot)
69
+ type: truthful_qa
70
+ config: multiple_choice
71
+ split: validation
72
+ args:
73
+ num_few_shot: 0
74
+ metrics:
75
+ - type: mc2
76
+ value: 44.7
77
+ source:
78
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara
79
+ name: Open LLM Leaderboard
80
+ - task:
81
+ type: text-generation
82
+ name: Text Generation
83
+ dataset:
84
+ name: Winogrande (5-shot)
85
+ type: winogrande
86
+ config: winogrande_xl
87
+ split: validation
88
+ args:
89
+ num_few_shot: 5
90
+ metrics:
91
+ - type: acc
92
+ value: 73.8
93
+ name: accuracy
94
+ source:
95
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara
96
+ name: Open LLM Leaderboard
97
+ - task:
98
+ type: text-generation
99
+ name: Text Generation
100
+ dataset:
101
+ name: GSM8k (5-shot)
102
+ type: gsm8k
103
+ config: main
104
+ split: test
105
+ args:
106
+ num_few_shot: 5
107
+ metrics:
108
+ - type: acc
109
+ value: 40.33
110
+ name: accuracy
111
+ source:
112
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Delcos/Velara
113
+ name: Open LLM Leaderboard
114
  ---
115
 
116
  <h1 style="font-size: 36px;">Velara-11b</h1>
 
182
 
183
  # Training Data:
184
  PENDING
185
+
186
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
187
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Delcos__Velara)
188
+
189
+ | Metric |Value|
190
+ |---------------------------------|----:|
191
+ |Avg. |60.01|
192
+ |AI2 Reasoning Challenge (25-Shot)|58.96|
193
+ |HellaSwag (10-Shot) |82.83|
194
+ |MMLU (5-Shot) |59.45|
195
+ |TruthfulQA (0-shot) |44.70|
196
+ |Winogrande (5-shot) |73.80|
197
+ |GSM8k (5-shot) |40.33|
198
+