Commit
•
16e5cde
1
Parent(s):
927e6c9
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
@@ -7,16 +7,16 @@ language:
|
|
7 |
- vi
|
8 |
- ms
|
9 |
- lo
|
|
|
|
|
|
|
|
|
|
|
10 |
datasets:
|
11 |
- cerebras/SlimPajama-627B
|
12 |
- Skywork/SkyPile-150B
|
13 |
- allenai/MADLAD-400
|
14 |
- cc100
|
15 |
-
tags:
|
16 |
-
- multilingual
|
17 |
-
- sea
|
18 |
-
- sailor
|
19 |
-
license: apache-2.0
|
20 |
base_model: Qwen/Qwen1.5-4B
|
21 |
model-index:
|
22 |
- name: Sailor-4B
|
@@ -27,117 +27,217 @@ model-index:
|
|
27 |
name: XQuAD-Thai
|
28 |
type: XQuAD-Thai
|
29 |
metrics:
|
30 |
-
-
|
31 |
-
type: EM (3-Shot)
|
32 |
value: 46.82
|
33 |
-
|
34 |
-
|
35 |
value: 63.34
|
|
|
36 |
- task:
|
37 |
type: text-generation
|
38 |
dataset:
|
39 |
name: TyDiQA-Indonesian
|
40 |
type: TyDiQA-Indonesian
|
41 |
metrics:
|
42 |
-
-
|
43 |
-
type: EM (3-Shot)
|
44 |
value: 53.98
|
45 |
-
|
46 |
-
|
47 |
value: 73.48
|
|
|
48 |
- task:
|
49 |
type: text-generation
|
50 |
dataset:
|
51 |
name: XQuAD-Vietnamese
|
52 |
type: XQuAD-Vietnamese
|
53 |
metrics:
|
54 |
-
-
|
55 |
-
type: EM (3-Shot)
|
56 |
value: 47.65
|
57 |
-
|
58 |
-
|
59 |
value: 67.09
|
|
|
60 |
- task:
|
61 |
type: text-generation
|
62 |
dataset:
|
63 |
name: XCOPA-Thai
|
64 |
type: XCOPA-Thai
|
65 |
metrics:
|
66 |
-
-
|
67 |
-
type: EM (3-Shot)
|
68 |
value: 53.4
|
|
|
69 |
- task:
|
70 |
type: text-generation
|
71 |
dataset:
|
72 |
name: XCOPA-Indonesian
|
73 |
type: XCOPA-Indonesian
|
74 |
metrics:
|
75 |
-
-
|
76 |
-
|
77 |
-
|
78 |
- task:
|
79 |
type: text-generation
|
80 |
dataset:
|
81 |
name: XCOPA-Vietnamese
|
82 |
type: XCOPA-Vietnamese
|
83 |
metrics:
|
84 |
-
-
|
85 |
-
|
86 |
-
|
87 |
- task:
|
88 |
type: text-generation
|
89 |
dataset:
|
90 |
name: M3Exam-Thai
|
91 |
type: M3Exam-Thai
|
92 |
metrics:
|
93 |
-
-
|
94 |
-
type: EM (3-Shot)
|
95 |
value: 27.88
|
|
|
96 |
- task:
|
97 |
type: text-generation
|
98 |
dataset:
|
99 |
name: M3Exam-Indonesian
|
100 |
type: M3Exam-Indonesian
|
101 |
metrics:
|
102 |
-
-
|
103 |
-
type: EM (3-Shot)
|
104 |
value: 31.27
|
|
|
105 |
- task:
|
106 |
type: text-generation
|
107 |
dataset:
|
108 |
name: M3Exam-Vietnamese
|
109 |
type: M3Exam-Vietnamese
|
110 |
metrics:
|
111 |
-
-
|
112 |
-
type: EM (3-Shot)
|
113 |
value: 40.69
|
|
|
114 |
- task:
|
115 |
type: text-generation
|
116 |
dataset:
|
117 |
name: BELEBELE-Thai
|
118 |
type: BELEBELE-Thai
|
119 |
metrics:
|
120 |
-
-
|
121 |
-
type: EM (3-Shot)
|
122 |
value: 36.11
|
|
|
123 |
- task:
|
124 |
type: text-generation
|
125 |
dataset:
|
126 |
name: BELEBELE-Indonesian
|
127 |
type: BELEBELE-Indonesian
|
128 |
metrics:
|
129 |
-
-
|
130 |
-
type: EM (3-Shot)
|
131 |
value: 41.33
|
|
|
132 |
- task:
|
133 |
type: text-generation
|
134 |
dataset:
|
135 |
name: BELEBELE-Vietnamese
|
136 |
type: BELEBELE-Vietnamese
|
137 |
metrics:
|
138 |
-
-
|
139 |
-
type: EM (3-Shot)
|
140 |
value: 38.89
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
141 |
---
|
142 |
|
143 |
<div align="center">
|
@@ -210,4 +310,17 @@ No restrict on the research and the commercial use, but should comply with the [
|
|
210 |
|
211 |
# Contact Us
|
212 |
|
213 |
-
If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]) or [[email protected]](mailto:[email protected]).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
- vi
|
8 |
- ms
|
9 |
- lo
|
10 |
+
license: apache-2.0
|
11 |
+
tags:
|
12 |
+
- multilingual
|
13 |
+
- sea
|
14 |
+
- sailor
|
15 |
datasets:
|
16 |
- cerebras/SlimPajama-627B
|
17 |
- Skywork/SkyPile-150B
|
18 |
- allenai/MADLAD-400
|
19 |
- cc100
|
|
|
|
|
|
|
|
|
|
|
20 |
base_model: Qwen/Qwen1.5-4B
|
21 |
model-index:
|
22 |
- name: Sailor-4B
|
|
|
27 |
name: XQuAD-Thai
|
28 |
type: XQuAD-Thai
|
29 |
metrics:
|
30 |
+
- type: EM (3-Shot)
|
|
|
31 |
value: 46.82
|
32 |
+
name: EM (3-Shot)
|
33 |
+
- type: F1 (3-Shot)
|
34 |
value: 63.34
|
35 |
+
name: F1 (3-Shot)
|
36 |
- task:
|
37 |
type: text-generation
|
38 |
dataset:
|
39 |
name: TyDiQA-Indonesian
|
40 |
type: TyDiQA-Indonesian
|
41 |
metrics:
|
42 |
+
- type: EM (3-Shot)
|
|
|
43 |
value: 53.98
|
44 |
+
name: EM (3-Shot)
|
45 |
+
- type: F1 (3-Shot)
|
46 |
value: 73.48
|
47 |
+
name: F1 (3-Shot)
|
48 |
- task:
|
49 |
type: text-generation
|
50 |
dataset:
|
51 |
name: XQuAD-Vietnamese
|
52 |
type: XQuAD-Vietnamese
|
53 |
metrics:
|
54 |
+
- type: EM (3-Shot)
|
|
|
55 |
value: 47.65
|
56 |
+
name: EM (3-Shot)
|
57 |
+
- type: F1 (3-Shot)
|
58 |
value: 67.09
|
59 |
+
name: F1 (3-Shot)
|
60 |
- task:
|
61 |
type: text-generation
|
62 |
dataset:
|
63 |
name: XCOPA-Thai
|
64 |
type: XCOPA-Thai
|
65 |
metrics:
|
66 |
+
- type: EM (3-Shot)
|
|
|
67 |
value: 53.4
|
68 |
+
name: EM (3-Shot)
|
69 |
- task:
|
70 |
type: text-generation
|
71 |
dataset:
|
72 |
name: XCOPA-Indonesian
|
73 |
type: XCOPA-Indonesian
|
74 |
metrics:
|
75 |
+
- type: EM (3-Shot)
|
76 |
+
value: 69.2
|
77 |
+
name: EM (3-Shot)
|
78 |
- task:
|
79 |
type: text-generation
|
80 |
dataset:
|
81 |
name: XCOPA-Vietnamese
|
82 |
type: XCOPA-Vietnamese
|
83 |
metrics:
|
84 |
+
- type: EM (3-Shot)
|
85 |
+
value: 68.2
|
86 |
+
name: EM (3-Shot)
|
87 |
- task:
|
88 |
type: text-generation
|
89 |
dataset:
|
90 |
name: M3Exam-Thai
|
91 |
type: M3Exam-Thai
|
92 |
metrics:
|
93 |
+
- type: EM (3-Shot)
|
|
|
94 |
value: 27.88
|
95 |
+
name: EM (3-Shot)
|
96 |
- task:
|
97 |
type: text-generation
|
98 |
dataset:
|
99 |
name: M3Exam-Indonesian
|
100 |
type: M3Exam-Indonesian
|
101 |
metrics:
|
102 |
+
- type: EM (3-Shot)
|
|
|
103 |
value: 31.27
|
104 |
+
name: EM (3-Shot)
|
105 |
- task:
|
106 |
type: text-generation
|
107 |
dataset:
|
108 |
name: M3Exam-Vietnamese
|
109 |
type: M3Exam-Vietnamese
|
110 |
metrics:
|
111 |
+
- type: EM (3-Shot)
|
|
|
112 |
value: 40.69
|
113 |
+
name: EM (3-Shot)
|
114 |
- task:
|
115 |
type: text-generation
|
116 |
dataset:
|
117 |
name: BELEBELE-Thai
|
118 |
type: BELEBELE-Thai
|
119 |
metrics:
|
120 |
+
- type: EM (3-Shot)
|
|
|
121 |
value: 36.11
|
122 |
+
name: EM (3-Shot)
|
123 |
- task:
|
124 |
type: text-generation
|
125 |
dataset:
|
126 |
name: BELEBELE-Indonesian
|
127 |
type: BELEBELE-Indonesian
|
128 |
metrics:
|
129 |
+
- type: EM (3-Shot)
|
|
|
130 |
value: 41.33
|
131 |
+
name: EM (3-Shot)
|
132 |
- task:
|
133 |
type: text-generation
|
134 |
dataset:
|
135 |
name: BELEBELE-Vietnamese
|
136 |
type: BELEBELE-Vietnamese
|
137 |
metrics:
|
138 |
+
- type: EM (3-Shot)
|
|
|
139 |
value: 38.89
|
140 |
+
name: EM (3-Shot)
|
141 |
+
- task:
|
142 |
+
type: text-generation
|
143 |
+
name: Text Generation
|
144 |
+
dataset:
|
145 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
146 |
+
type: ai2_arc
|
147 |
+
config: ARC-Challenge
|
148 |
+
split: test
|
149 |
+
args:
|
150 |
+
num_few_shot: 25
|
151 |
+
metrics:
|
152 |
+
- type: acc_norm
|
153 |
+
value: 44.45
|
154 |
+
name: normalized accuracy
|
155 |
+
source:
|
156 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
|
157 |
+
name: Open LLM Leaderboard
|
158 |
+
- task:
|
159 |
+
type: text-generation
|
160 |
+
name: Text Generation
|
161 |
+
dataset:
|
162 |
+
name: HellaSwag (10-Shot)
|
163 |
+
type: hellaswag
|
164 |
+
split: validation
|
165 |
+
args:
|
166 |
+
num_few_shot: 10
|
167 |
+
metrics:
|
168 |
+
- type: acc_norm
|
169 |
+
value: 69.53
|
170 |
+
name: normalized accuracy
|
171 |
+
source:
|
172 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
|
173 |
+
name: Open LLM Leaderboard
|
174 |
+
- task:
|
175 |
+
type: text-generation
|
176 |
+
name: Text Generation
|
177 |
+
dataset:
|
178 |
+
name: MMLU (5-Shot)
|
179 |
+
type: cais/mmlu
|
180 |
+
config: all
|
181 |
+
split: test
|
182 |
+
args:
|
183 |
+
num_few_shot: 5
|
184 |
+
metrics:
|
185 |
+
- type: acc
|
186 |
+
value: 38.99
|
187 |
+
name: accuracy
|
188 |
+
source:
|
189 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
|
190 |
+
name: Open LLM Leaderboard
|
191 |
+
- task:
|
192 |
+
type: text-generation
|
193 |
+
name: Text Generation
|
194 |
+
dataset:
|
195 |
+
name: TruthfulQA (0-shot)
|
196 |
+
type: truthful_qa
|
197 |
+
config: multiple_choice
|
198 |
+
split: validation
|
199 |
+
args:
|
200 |
+
num_few_shot: 0
|
201 |
+
metrics:
|
202 |
+
- type: mc2
|
203 |
+
value: 37.02
|
204 |
+
source:
|
205 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
|
206 |
+
name: Open LLM Leaderboard
|
207 |
+
- task:
|
208 |
+
type: text-generation
|
209 |
+
name: Text Generation
|
210 |
+
dataset:
|
211 |
+
name: Winogrande (5-shot)
|
212 |
+
type: winogrande
|
213 |
+
config: winogrande_xl
|
214 |
+
split: validation
|
215 |
+
args:
|
216 |
+
num_few_shot: 5
|
217 |
+
metrics:
|
218 |
+
- type: acc
|
219 |
+
value: 66.06
|
220 |
+
name: accuracy
|
221 |
+
source:
|
222 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
|
223 |
+
name: Open LLM Leaderboard
|
224 |
+
- task:
|
225 |
+
type: text-generation
|
226 |
+
name: Text Generation
|
227 |
+
dataset:
|
228 |
+
name: GSM8k (5-shot)
|
229 |
+
type: gsm8k
|
230 |
+
config: main
|
231 |
+
split: test
|
232 |
+
args:
|
233 |
+
num_few_shot: 5
|
234 |
+
metrics:
|
235 |
+
- type: acc
|
236 |
+
value: 9.1
|
237 |
+
name: accuracy
|
238 |
+
source:
|
239 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sail/Sailor-4B
|
240 |
+
name: Open LLM Leaderboard
|
241 |
---
|
242 |
|
243 |
<div align="center">
|
|
|
310 |
|
311 |
# Contact Us
|
312 |
|
313 |
+
If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]) or [[email protected]](mailto:[email protected]).
|
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_sail__Sailor-4B)
|
316 |
+
|
317 |
+
| Metric |Value|
|
318 |
+
|---------------------------------|----:|
|
319 |
+
|Avg. |44.19|
|
320 |
+
|AI2 Reasoning Challenge (25-Shot)|44.45|
|
321 |
+
|HellaSwag (10-Shot) |69.53|
|
322 |
+
|MMLU (5-Shot) |38.99|
|
323 |
+
|TruthfulQA (0-shot) |37.02|
|
324 |
+
|Winogrande (5-shot) |66.06|
|
325 |
+
|GSM8k (5-shot) | 9.10|
|
326 |
+
|