Commit
•
dbc1107
1
Parent(s):
f322e92
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
@@ -15,93 +15,185 @@ model-index:
|
|
15 |
type: text-generation
|
16 |
name: TruthfulQA (MC2)
|
17 |
dataset:
|
18 |
-
type: text-generation
|
19 |
name: truthful_qa
|
|
|
20 |
config: multiple_choice
|
21 |
split: validation
|
22 |
metrics:
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
- task:
|
27 |
type: text-generation
|
28 |
name: ARC-Challenge
|
29 |
dataset:
|
30 |
-
type: text-generation
|
31 |
name: ai2_arc
|
|
|
32 |
config: ARC-Challenge
|
33 |
split: test
|
34 |
metrics:
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
- task:
|
39 |
type: text-generation
|
40 |
name: HellaSwag
|
41 |
dataset:
|
42 |
-
type: text-generation
|
43 |
name: Rowan/hellaswag
|
|
|
44 |
split: test
|
45 |
metrics:
|
46 |
-
|
47 |
-
|
48 |
-
|
|
|
|
|
49 |
- task:
|
50 |
type: text-generation
|
51 |
name: Winogrande
|
52 |
dataset:
|
53 |
-
type: text-generation
|
54 |
name: winogrande
|
|
|
55 |
config: winogrande_debiased
|
56 |
split: test
|
57 |
metrics:
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
- task:
|
62 |
type: text-generation
|
63 |
name: MMLU
|
64 |
dataset:
|
65 |
-
type: text-generation
|
66 |
name: cais/mmlu
|
|
|
67 |
config: all
|
68 |
split: test
|
69 |
metrics:
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
- task:
|
74 |
type: text-generation
|
75 |
-
name:
|
76 |
dataset:
|
|
|
77 |
type: text-generation
|
78 |
-
|
79 |
-
split: test
|
80 |
metrics:
|
81 |
-
|
82 |
-
|
|
|
83 |
- task:
|
84 |
type: text-generation
|
85 |
-
name:
|
86 |
dataset:
|
|
|
87 |
type: text-generation
|
88 |
-
|
89 |
split: validation
|
90 |
metrics:
|
91 |
-
|
92 |
-
|
93 |
-
verified: true
|
94 |
- task:
|
95 |
type: text-generation
|
96 |
-
name:
|
97 |
dataset:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
type: text-generation
|
99 |
-
name:
|
100 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
split: validation
|
|
|
|
|
102 |
metrics:
|
103 |
-
|
104 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
---
|
106 |
|
107 |
# juanako-7b-UNA (Uniform Neural Alignment)
|
@@ -369,3 +461,17 @@ Thanks to all the brilliant humans behind the creation of AI, here some of the o
|
|
369 |
archivePrefix={arXiv},
|
370 |
}
|
371 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
type: text-generation
|
16 |
name: TruthfulQA (MC2)
|
17 |
dataset:
|
|
|
18 |
name: truthful_qa
|
19 |
+
type: text-generation
|
20 |
config: multiple_choice
|
21 |
split: validation
|
22 |
metrics:
|
23 |
+
- type: accuracy
|
24 |
+
value: 65.13
|
25 |
+
verified: true
|
26 |
- task:
|
27 |
type: text-generation
|
28 |
name: ARC-Challenge
|
29 |
dataset:
|
|
|
30 |
name: ai2_arc
|
31 |
+
type: text-generation
|
32 |
config: ARC-Challenge
|
33 |
split: test
|
34 |
metrics:
|
35 |
+
- type: accuracy
|
36 |
+
value: 68.17
|
37 |
+
verified: true
|
38 |
- task:
|
39 |
type: text-generation
|
40 |
name: HellaSwag
|
41 |
dataset:
|
|
|
42 |
name: Rowan/hellaswag
|
43 |
+
type: text-generation
|
44 |
split: test
|
45 |
metrics:
|
46 |
+
- type: accuracy
|
47 |
+
value: 85.34
|
48 |
+
verified: true
|
49 |
+
- type: accuracy
|
50 |
+
value: 83.57
|
51 |
- task:
|
52 |
type: text-generation
|
53 |
name: Winogrande
|
54 |
dataset:
|
|
|
55 |
name: winogrande
|
56 |
+
type: text-generation
|
57 |
config: winogrande_debiased
|
58 |
split: test
|
59 |
metrics:
|
60 |
+
- type: accuracy
|
61 |
+
value: 78.85
|
62 |
+
verified: true
|
63 |
- task:
|
64 |
type: text-generation
|
65 |
name: MMLU
|
66 |
dataset:
|
|
|
67 |
name: cais/mmlu
|
68 |
+
type: text-generation
|
69 |
config: all
|
70 |
split: test
|
71 |
metrics:
|
72 |
+
- type: accuracy
|
73 |
+
value: 62.47
|
74 |
+
verified: true
|
75 |
- task:
|
76 |
type: text-generation
|
77 |
+
name: DROP
|
78 |
dataset:
|
79 |
+
name: drop
|
80 |
type: text-generation
|
81 |
+
split: validation
|
|
|
82 |
metrics:
|
83 |
+
- type: accuracy
|
84 |
+
value: 38.74
|
85 |
+
verified: true
|
86 |
- task:
|
87 |
type: text-generation
|
88 |
+
name: PubMedQA
|
89 |
dataset:
|
90 |
+
name: bigbio/pubmed_qa
|
91 |
type: text-generation
|
92 |
+
config: pubmed_qa_artificial_bigbio_qa
|
93 |
split: validation
|
94 |
metrics:
|
95 |
+
- type: accuracy
|
96 |
+
value: 76.0
|
|
|
97 |
- task:
|
98 |
type: text-generation
|
99 |
+
name: Text Generation
|
100 |
dataset:
|
101 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
102 |
+
type: ai2_arc
|
103 |
+
config: ARC-Challenge
|
104 |
+
split: test
|
105 |
+
args:
|
106 |
+
num_few_shot: 25
|
107 |
+
metrics:
|
108 |
+
- type: acc_norm
|
109 |
+
value: 68.17
|
110 |
+
name: normalized accuracy
|
111 |
+
source:
|
112 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
|
113 |
+
name: Open LLM Leaderboard
|
114 |
+
- task:
|
115 |
type: text-generation
|
116 |
+
name: Text Generation
|
117 |
+
dataset:
|
118 |
+
name: HellaSwag (10-Shot)
|
119 |
+
type: hellaswag
|
120 |
+
split: validation
|
121 |
+
args:
|
122 |
+
num_few_shot: 10
|
123 |
+
metrics:
|
124 |
+
- type: acc_norm
|
125 |
+
value: 85.34
|
126 |
+
name: normalized accuracy
|
127 |
+
source:
|
128 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
|
129 |
+
name: Open LLM Leaderboard
|
130 |
+
- task:
|
131 |
+
type: text-generation
|
132 |
+
name: Text Generation
|
133 |
+
dataset:
|
134 |
+
name: MMLU (5-Shot)
|
135 |
+
type: cais/mmlu
|
136 |
+
config: all
|
137 |
+
split: test
|
138 |
+
args:
|
139 |
+
num_few_shot: 5
|
140 |
+
metrics:
|
141 |
+
- type: acc
|
142 |
+
value: 62.47
|
143 |
+
name: accuracy
|
144 |
+
source:
|
145 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
|
146 |
+
name: Open LLM Leaderboard
|
147 |
+
- task:
|
148 |
+
type: text-generation
|
149 |
+
name: Text Generation
|
150 |
+
dataset:
|
151 |
+
name: TruthfulQA (0-shot)
|
152 |
+
type: truthful_qa
|
153 |
+
config: multiple_choice
|
154 |
split: validation
|
155 |
+
args:
|
156 |
+
num_few_shot: 0
|
157 |
metrics:
|
158 |
+
- type: mc2
|
159 |
+
value: 65.13
|
160 |
+
source:
|
161 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
|
162 |
+
name: Open LLM Leaderboard
|
163 |
+
- task:
|
164 |
+
type: text-generation
|
165 |
+
name: Text Generation
|
166 |
+
dataset:
|
167 |
+
name: Winogrande (5-shot)
|
168 |
+
type: winogrande
|
169 |
+
config: winogrande_xl
|
170 |
+
split: validation
|
171 |
+
args:
|
172 |
+
num_few_shot: 5
|
173 |
+
metrics:
|
174 |
+
- type: acc
|
175 |
+
value: 78.85
|
176 |
+
name: accuracy
|
177 |
+
source:
|
178 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
|
179 |
+
name: Open LLM Leaderboard
|
180 |
+
- task:
|
181 |
+
type: text-generation
|
182 |
+
name: Text Generation
|
183 |
+
dataset:
|
184 |
+
name: GSM8k (5-shot)
|
185 |
+
type: gsm8k
|
186 |
+
config: main
|
187 |
+
split: test
|
188 |
+
args:
|
189 |
+
num_few_shot: 5
|
190 |
+
metrics:
|
191 |
+
- type: acc
|
192 |
+
value: 44.81
|
193 |
+
name: accuracy
|
194 |
+
source:
|
195 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=fblgit/juanako-7b-UNA
|
196 |
+
name: Open LLM Leaderboard
|
197 |
---
|
198 |
|
199 |
# juanako-7b-UNA (Uniform Neural Alignment)
|
|
|
461 |
archivePrefix={arXiv},
|
462 |
}
|
463 |
```
|
464 |
+
|
465 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
466 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_fblgit__juanako-7b-UNA)
|
467 |
+
|
468 |
+
| Metric |Value|
|
469 |
+
|---------------------------------|----:|
|
470 |
+
|Avg. |67.46|
|
471 |
+
|AI2 Reasoning Challenge (25-Shot)|68.17|
|
472 |
+
|HellaSwag (10-Shot) |85.34|
|
473 |
+
|MMLU (5-Shot) |62.47|
|
474 |
+
|TruthfulQA (0-shot) |65.13|
|
475 |
+
|Winogrande (5-shot) |78.85|
|
476 |
+
|GSM8k (5-shot) |44.81|
|
477 |
+
|