Spaces:
Runtime error
Runtime error
Yilun Jin
commited on
Commit
·
b0464d1
1
Parent(s):
5459fa4
update overall leaderboard
Browse files- .DS_Store +0 -0
- ShoppingMMLU_overall.json +653 -0
- __pycache__/meta_data.cpython-38.pyc +0 -0
- app.py +2 -2
- meta_data.py +1 -1
.DS_Store
CHANGED
Binary files a/.DS_Store and b/.DS_Store differ
|
|
ShoppingMMLU_overall.json
ADDED
@@ -0,0 +1,653 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"time": "241031154353",
|
3 |
+
"results": {
|
4 |
+
"Claude3-Sonnet": {
|
5 |
+
"META": {
|
6 |
+
"Method": [
|
7 |
+
"Claude3-Sonnet",
|
8 |
+
"https://aws.amazon.com/bedrock/claude/"
|
9 |
+
],
|
10 |
+
"Parameters": "",
|
11 |
+
"Org": "Anthropic",
|
12 |
+
"OpenSource": "No",
|
13 |
+
"Verified": "Yes"
|
14 |
+
},
|
15 |
+
"Shopping Concept Understanding": {
|
16 |
+
"Overall": 80.75
|
17 |
+
},
|
18 |
+
"Shopping Knowledge Reasoning": {
|
19 |
+
"Overall": 71.63
|
20 |
+
},
|
21 |
+
"User Behavior Alignment": {
|
22 |
+
"Overall": 70.17
|
23 |
+
},
|
24 |
+
"Multi-lingual Abilities": {
|
25 |
+
"Overall": 67.76
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"Claude2": {
|
29 |
+
"META": {
|
30 |
+
"Method": [
|
31 |
+
"Claude2",
|
32 |
+
"https://aws.amazon.com/bedrock/claude/"
|
33 |
+
],
|
34 |
+
"Parameters": "",
|
35 |
+
"Org": "Anthropic",
|
36 |
+
"OpenSource": "No",
|
37 |
+
"Verified": "Yes"
|
38 |
+
},
|
39 |
+
"Shopping Concept Understanding": {
|
40 |
+
"Overall": 75.46
|
41 |
+
},
|
42 |
+
"Shopping Knowledge Reasoning": {
|
43 |
+
"Overall": 65.5
|
44 |
+
},
|
45 |
+
"User Behavior Alignment": {
|
46 |
+
"Overall": 63.53
|
47 |
+
},
|
48 |
+
"Multi-lingual Abilities": {
|
49 |
+
"Overall": 65.24
|
50 |
+
}
|
51 |
+
},
|
52 |
+
"ChatGPT": {
|
53 |
+
"META": {
|
54 |
+
"Method": [
|
55 |
+
"ChatGPT",
|
56 |
+
"https://platform.openai.com/docs/models#gpt-3-5-turbo"
|
57 |
+
],
|
58 |
+
"Parameters": "",
|
59 |
+
"Org": "OpenAI",
|
60 |
+
"OpenSource": "No",
|
61 |
+
"Verified": "Yes"
|
62 |
+
},
|
63 |
+
"Shopping Concept Understanding": {
|
64 |
+
"Overall": 75.63
|
65 |
+
},
|
66 |
+
"Shopping Knowledge Reasoning": {
|
67 |
+
"Overall": 64.97
|
68 |
+
},
|
69 |
+
"User Behavior Alignment": {
|
70 |
+
"Overall": 59.79
|
71 |
+
},
|
72 |
+
"Multi-lingual Abilities": {
|
73 |
+
"Overall": 60.81
|
74 |
+
}
|
75 |
+
},
|
76 |
+
"LLaMA3-70B-Instruct": {
|
77 |
+
"META": {
|
78 |
+
"Method": [
|
79 |
+
"LLaMA3-70B-Instruct",
|
80 |
+
"https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct"
|
81 |
+
],
|
82 |
+
"Parameters": "70B",
|
83 |
+
"Org": "Meta",
|
84 |
+
"OpenSource": "Yes",
|
85 |
+
"Verified": "Yes"
|
86 |
+
},
|
87 |
+
"Shopping Concept Understanding": {
|
88 |
+
"Overall": 75.24
|
89 |
+
},
|
90 |
+
"Shopping Knowledge Reasoning": {
|
91 |
+
"Overall": 69.29
|
92 |
+
},
|
93 |
+
"User Behavior Alignment": {
|
94 |
+
"Overall": 67.67
|
95 |
+
},
|
96 |
+
"Multi-lingual Abilities": {
|
97 |
+
"Overall": 62.0
|
98 |
+
}
|
99 |
+
},
|
100 |
+
"QWen1.5-72B": {
|
101 |
+
"META": {
|
102 |
+
"Method": [
|
103 |
+
"QWen1.5-72B",
|
104 |
+
"https://huggingface.co/Qwen/Qwen1.5-72B"
|
105 |
+
],
|
106 |
+
"Parameters": "72B",
|
107 |
+
"Org": "Alibaba",
|
108 |
+
"OpenSource": "Yes",
|
109 |
+
"Verified": "Yes"
|
110 |
+
},
|
111 |
+
"Shopping Concept Understanding": {
|
112 |
+
"Overall": 71.67
|
113 |
+
},
|
114 |
+
"Shopping Knowledge Reasoning": {
|
115 |
+
"Overall": 68.92
|
116 |
+
},
|
117 |
+
"User Behavior Alignment": {
|
118 |
+
"Overall": 64.12
|
119 |
+
},
|
120 |
+
"Multi-lingual Abilities": {
|
121 |
+
"Overall": 64.84
|
122 |
+
}
|
123 |
+
},
|
124 |
+
"LLaMA3-70B": {
|
125 |
+
"META": {
|
126 |
+
"Method": [
|
127 |
+
"LLaMA3-70B",
|
128 |
+
"https://huggingface.co/meta-llama/Meta-Llama-3-70B"
|
129 |
+
],
|
130 |
+
"Parameters": "70B",
|
131 |
+
"Org": "Meta",
|
132 |
+
"OpenSource": "Yes",
|
133 |
+
"Verified": "Yes"
|
134 |
+
},
|
135 |
+
"Shopping Concept Understanding": {
|
136 |
+
"Overall": 69.59
|
137 |
+
},
|
138 |
+
"Shopping Knowledge Reasoning": {
|
139 |
+
"Overall": 63.56
|
140 |
+
},
|
141 |
+
"User Behavior Alignment": {
|
142 |
+
"Overall": 55.77
|
143 |
+
},
|
144 |
+
"Multi-lingual Abilities": {
|
145 |
+
"Overall": 58.95
|
146 |
+
}
|
147 |
+
},
|
148 |
+
"LLaMA2-70B-Chat": {
|
149 |
+
"META": {
|
150 |
+
"Method": [
|
151 |
+
"LLaMA2-70B-Chat",
|
152 |
+
"https://huggingface.co/meta-llama/Llama-2-70b-chat-hf"
|
153 |
+
],
|
154 |
+
"Parameters": "70B",
|
155 |
+
"Org": "Meta",
|
156 |
+
"OpenSource": "Yes",
|
157 |
+
"Verified": "Yes"
|
158 |
+
},
|
159 |
+
"Shopping Concept Understanding": {
|
160 |
+
"Overall": 61.84
|
161 |
+
},
|
162 |
+
"Shopping Knowledge Reasoning": {
|
163 |
+
"Overall": 40.73
|
164 |
+
},
|
165 |
+
"User Behavior Alignment": {
|
166 |
+
"Overall": 44.2
|
167 |
+
},
|
168 |
+
"Multi-lingual Abilities": {
|
169 |
+
"Overall": 47.04
|
170 |
+
}
|
171 |
+
},
|
172 |
+
"LLaMA2-70B": {
|
173 |
+
"META": {
|
174 |
+
"Method": [
|
175 |
+
"LLaMA2-70B",
|
176 |
+
"https://huggingface.co/meta-llama/Llama-2-70b-hf"
|
177 |
+
],
|
178 |
+
"Parameters": "70B",
|
179 |
+
"Org": "Meta",
|
180 |
+
"OpenSource": "Yes",
|
181 |
+
"Verified": "Yes"
|
182 |
+
},
|
183 |
+
"Shopping Concept Understanding": {
|
184 |
+
"Overall": 61.05
|
185 |
+
},
|
186 |
+
"Shopping Knowledge Reasoning": {
|
187 |
+
"Overall": 55.87
|
188 |
+
},
|
189 |
+
"User Behavior Alignment": {
|
190 |
+
"Overall": 43.24
|
191 |
+
},
|
192 |
+
"Multi-lingual Abilities": {
|
193 |
+
"Overall": 47.85
|
194 |
+
}
|
195 |
+
},
|
196 |
+
"Mixtral-8x7B": {
|
197 |
+
"META": {
|
198 |
+
"Method": [
|
199 |
+
"Mixtral-8x7B",
|
200 |
+
"https://huggingface.co/mistralai/Mixtral-8x7B-v0.1"
|
201 |
+
],
|
202 |
+
"Parameters": "46.7B",
|
203 |
+
"Org": "MistralAI",
|
204 |
+
"OpenSource": "Yes",
|
205 |
+
"Verified": "Yes"
|
206 |
+
},
|
207 |
+
"Shopping Concept Understanding": {
|
208 |
+
"Overall": 59.43
|
209 |
+
},
|
210 |
+
"Shopping Knowledge Reasoning": {
|
211 |
+
"Overall": 54.32
|
212 |
+
},
|
213 |
+
"User Behavior Alignment": {
|
214 |
+
"Overall": 55.31
|
215 |
+
},
|
216 |
+
"Multi-lingual Abilities": {
|
217 |
+
"Overall": 44.69
|
218 |
+
}
|
219 |
+
},
|
220 |
+
"QWen1.5-14B": {
|
221 |
+
"META": {
|
222 |
+
"Method": [
|
223 |
+
"QWen1.5-14B",
|
224 |
+
"https://huggingface.co/Qwen/Qwen1.5-14B"
|
225 |
+
],
|
226 |
+
"Parameters": "14B",
|
227 |
+
"Org": "Alibaba",
|
228 |
+
"OpenSource": "Yes",
|
229 |
+
"Verified": "Yes"
|
230 |
+
},
|
231 |
+
"Shopping Concept Understanding": {
|
232 |
+
"Overall": 67.22
|
233 |
+
},
|
234 |
+
"Shopping Knowledge Reasoning": {
|
235 |
+
"Overall": 60.92
|
236 |
+
},
|
237 |
+
"User Behavior Alignment": {
|
238 |
+
"Overall": 54.92
|
239 |
+
},
|
240 |
+
"Multi-lingual Abilities": {
|
241 |
+
"Overall": 55.21
|
242 |
+
}
|
243 |
+
},
|
244 |
+
"eCeLLM-L": {
|
245 |
+
"META": {
|
246 |
+
"Method": [
|
247 |
+
"eCeLLM-L",
|
248 |
+
"https://huggingface.co/NingLab/eCeLLM-L"
|
249 |
+
],
|
250 |
+
"Parameters": "13B",
|
251 |
+
"Org": "OSU NingLab",
|
252 |
+
"OpenSource": "Yes",
|
253 |
+
"Verified": "Yes"
|
254 |
+
},
|
255 |
+
"Shopping Concept Understanding": {
|
256 |
+
"Overall": 61.54
|
257 |
+
},
|
258 |
+
"Shopping Knowledge Reasoning": {
|
259 |
+
"Overall": 54.84
|
260 |
+
},
|
261 |
+
"User Behavior Alignment": {
|
262 |
+
"Overall": 54.55
|
263 |
+
},
|
264 |
+
"Multi-lingual Abilities": {
|
265 |
+
"Overall": 59.64
|
266 |
+
}
|
267 |
+
},
|
268 |
+
"Vicuna-13B-v1.5": {
|
269 |
+
"META": {
|
270 |
+
"Method": [
|
271 |
+
"Vicuna-13B-v1.5",
|
272 |
+
"https://huggingface.co/lmsys/vicuna-13b-v1.5"
|
273 |
+
],
|
274 |
+
"Parameters": "13B",
|
275 |
+
"Org": "LMSys",
|
276 |
+
"OpenSource": "Yes",
|
277 |
+
"Verified": "Yes"
|
278 |
+
},
|
279 |
+
"Shopping Concept Understanding": {
|
280 |
+
"Overall": 59.64
|
281 |
+
},
|
282 |
+
"Shopping Knowledge Reasoning": {
|
283 |
+
"Overall": 52.63
|
284 |
+
},
|
285 |
+
"User Behavior Alignment": {
|
286 |
+
"Overall": 49.81
|
287 |
+
},
|
288 |
+
"Multi-lingual Abilities": {
|
289 |
+
"Overall": 49.64
|
290 |
+
}
|
291 |
+
},
|
292 |
+
"LLaMA2-13B-Chat": {
|
293 |
+
"META": {
|
294 |
+
"Method": [
|
295 |
+
"LLaMA2-13B-Chat",
|
296 |
+
"https://huggingface.co/meta-llama/Llama-2-13b-chat-hf"
|
297 |
+
],
|
298 |
+
"Parameters": "13B",
|
299 |
+
"Org": "Meta",
|
300 |
+
"OpenSource": "Yes",
|
301 |
+
"Verified": "Yes"
|
302 |
+
},
|
303 |
+
"Shopping Concept Understanding": {
|
304 |
+
"Overall": 51.79
|
305 |
+
},
|
306 |
+
"Shopping Knowledge Reasoning": {
|
307 |
+
"Overall": 45.01
|
308 |
+
},
|
309 |
+
"User Behavior Alignment": {
|
310 |
+
"Overall": 39.95
|
311 |
+
},
|
312 |
+
"Multi-lingual Abilities": {
|
313 |
+
"Overall": 42.99
|
314 |
+
}
|
315 |
+
},
|
316 |
+
"LLaMA2-13B": {
|
317 |
+
"META": {
|
318 |
+
"Method": [
|
319 |
+
"LLaMA2-13B",
|
320 |
+
"https://huggingface.co/meta-llama/Llama-2-13b-hf"
|
321 |
+
],
|
322 |
+
"Parameters": "13B",
|
323 |
+
"Org": "Meta",
|
324 |
+
"OpenSource": "Yes",
|
325 |
+
"Verified": "Yes"
|
326 |
+
},
|
327 |
+
"Shopping Concept Understanding": {
|
328 |
+
"Overall": 45.86
|
329 |
+
},
|
330 |
+
"Shopping Knowledge Reasoning": {
|
331 |
+
"Overall": 39.47
|
332 |
+
},
|
333 |
+
"User Behavior Alignment": {
|
334 |
+
"Overall": 39.43
|
335 |
+
},
|
336 |
+
"Multi-lingual Abilities": {
|
337 |
+
"Overall": 44.23
|
338 |
+
}
|
339 |
+
},
|
340 |
+
"LLaMA3-8B-Instruct": {
|
341 |
+
"META": {
|
342 |
+
"Method": [
|
343 |
+
"LLaMA3-8B-Instruct",
|
344 |
+
"https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct"
|
345 |
+
],
|
346 |
+
"Parameters": "8B",
|
347 |
+
"Org": "Meta",
|
348 |
+
"OpenSource": "Yes",
|
349 |
+
"Verified": "Yes"
|
350 |
+
},
|
351 |
+
"Shopping Concept Understanding": {
|
352 |
+
"Overall": 65.26
|
353 |
+
},
|
354 |
+
"Shopping Knowledge Reasoning": {
|
355 |
+
"Overall": 56.84
|
356 |
+
},
|
357 |
+
"User Behavior Alignment": {
|
358 |
+
"Overall": 54.88
|
359 |
+
},
|
360 |
+
"Multi-lingual Abilities": {
|
361 |
+
"Overall": 55.37
|
362 |
+
}
|
363 |
+
},
|
364 |
+
"LLaMA3-8B": {
|
365 |
+
"META": {
|
366 |
+
"Method": [
|
367 |
+
"LLaMA3-8B",
|
368 |
+
"https://huggingface.co/meta-llama/Meta-Llama-3-8B"
|
369 |
+
],
|
370 |
+
"Parameters": "8B",
|
371 |
+
"Org": "Meta",
|
372 |
+
"OpenSource": "Yes",
|
373 |
+
"Verified": "Yes"
|
374 |
+
},
|
375 |
+
"Shopping Concept Understanding": {
|
376 |
+
"Overall": 58.02
|
377 |
+
},
|
378 |
+
"Shopping Knowledge Reasoning": {
|
379 |
+
"Overall": 49.74
|
380 |
+
},
|
381 |
+
"User Behavior Alignment": {
|
382 |
+
"Overall": 44.16
|
383 |
+
},
|
384 |
+
"Multi-lingual Abilities": {
|
385 |
+
"Overall": 51.03
|
386 |
+
}
|
387 |
+
},
|
388 |
+
"QWen1.5-7B": {
|
389 |
+
"META": {
|
390 |
+
"Method": [
|
391 |
+
"QWen1.5-7B",
|
392 |
+
"https://huggingface.co/Qwen/Qwen1.5-7B"
|
393 |
+
],
|
394 |
+
"Parameters": "7B",
|
395 |
+
"Org": "Alibaba",
|
396 |
+
"OpenSource": "Yes",
|
397 |
+
"Verified": "Yes"
|
398 |
+
},
|
399 |
+
"Shopping Concept Understanding": {
|
400 |
+
"Overall": 58.89
|
401 |
+
},
|
402 |
+
"Shopping Knowledge Reasoning": {
|
403 |
+
"Overall": 52.34
|
404 |
+
},
|
405 |
+
"User Behavior Alignment": {
|
406 |
+
"Overall": 49.81
|
407 |
+
},
|
408 |
+
"Multi-lingual Abilities": {
|
409 |
+
"Overall": 50.14
|
410 |
+
}
|
411 |
+
},
|
412 |
+
"eCeLLM-M": {
|
413 |
+
"META": {
|
414 |
+
"Method": [
|
415 |
+
"eCeLLM-M",
|
416 |
+
"https://huggingface.co/NingLab/eCeLLM-M"
|
417 |
+
],
|
418 |
+
"Parameters": "7B",
|
419 |
+
"Org": "OSU NingLab",
|
420 |
+
"OpenSource": "Yes",
|
421 |
+
"Verified": "Yes"
|
422 |
+
},
|
423 |
+
"Shopping Concept Understanding": {
|
424 |
+
"Overall": 63.29
|
425 |
+
},
|
426 |
+
"Shopping Knowledge Reasoning": {
|
427 |
+
"Overall": 48.94
|
428 |
+
},
|
429 |
+
"User Behavior Alignment": {
|
430 |
+
"Overall": 53.78
|
431 |
+
},
|
432 |
+
"Multi-lingual Abilities": {
|
433 |
+
"Overall": 56.08
|
434 |
+
}
|
435 |
+
},
|
436 |
+
"Zephyr-Beta": {
|
437 |
+
"META": {
|
438 |
+
"Method": [
|
439 |
+
"Zephyr-Beta",
|
440 |
+
"https://huggingface.co/HuggingFaceH4/zephyr-7b-beta"
|
441 |
+
],
|
442 |
+
"Parameters": "7B",
|
443 |
+
"Org": "HuggingFace H4",
|
444 |
+
"OpenSource": "Yes",
|
445 |
+
"Verified": "Yes"
|
446 |
+
},
|
447 |
+
"Shopping Concept Understanding": {
|
448 |
+
"Overall": 61.65
|
449 |
+
},
|
450 |
+
"Shopping Knowledge Reasoning": {
|
451 |
+
"Overall": 52.57
|
452 |
+
},
|
453 |
+
"User Behavior Alignment": {
|
454 |
+
"Overall": 44.73
|
455 |
+
},
|
456 |
+
"Multi-lingual Abilities": {
|
457 |
+
"Overall": 45.35
|
458 |
+
}
|
459 |
+
},
|
460 |
+
"Mistral-7B-Instruct": {
|
461 |
+
"META": {
|
462 |
+
"Method": [
|
463 |
+
"Mistral-7B-Instruct",
|
464 |
+
"https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2"
|
465 |
+
],
|
466 |
+
"Parameters": "7B",
|
467 |
+
"Org": "MistralAI",
|
468 |
+
"OpenSource": "Yes",
|
469 |
+
"Verified": "Yes"
|
470 |
+
},
|
471 |
+
"Shopping Concept Understanding": {
|
472 |
+
"Overall": 62.03
|
473 |
+
},
|
474 |
+
"Shopping Knowledge Reasoning": {
|
475 |
+
"Overall": 46.36
|
476 |
+
},
|
477 |
+
"User Behavior Alignment": {
|
478 |
+
"Overall": 42.21
|
479 |
+
},
|
480 |
+
"Multi-lingual Abilities": {
|
481 |
+
"Overall": 43.32
|
482 |
+
}
|
483 |
+
},
|
484 |
+
"Mistral-7B": {
|
485 |
+
"META": {
|
486 |
+
"Method": [
|
487 |
+
"Mistral-7B",
|
488 |
+
"https://huggingface.co/mistralai/Mistral-7B-v0.1"
|
489 |
+
],
|
490 |
+
"Parameters": "7B",
|
491 |
+
"Org": "MistralAI",
|
492 |
+
"OpenSource": "Yes",
|
493 |
+
"Verified": "Yes"
|
494 |
+
},
|
495 |
+
"Shopping Concept Understanding": {
|
496 |
+
"Overall": 55.82
|
497 |
+
},
|
498 |
+
"Shopping Knowledge Reasoning": {
|
499 |
+
"Overall": 46.69
|
500 |
+
},
|
501 |
+
"User Behavior Alignment": {
|
502 |
+
"Overall": 46.27
|
503 |
+
},
|
504 |
+
"Multi-lingual Abilities": {
|
505 |
+
"Overall": 41.47
|
506 |
+
}
|
507 |
+
},
|
508 |
+
"Vicuna-7B-v1.5": {
|
509 |
+
"META": {
|
510 |
+
"Method": [
|
511 |
+
"Vicuna-7B-v1.5",
|
512 |
+
"https://huggingface.co/lmsys/vicuna-7b-v1.5"
|
513 |
+
],
|
514 |
+
"Parameters": "7B",
|
515 |
+
"Org": "LMSys",
|
516 |
+
"OpenSource": "Yes",
|
517 |
+
"Verified": "Yes"
|
518 |
+
},
|
519 |
+
"Shopping Concept Understanding": {
|
520 |
+
"Overall": 53.46
|
521 |
+
},
|
522 |
+
"Shopping Knowledge Reasoning": {
|
523 |
+
"Overall": 45.06
|
524 |
+
},
|
525 |
+
"User Behavior Alignment": {
|
526 |
+
"Overall": 41.11
|
527 |
+
},
|
528 |
+
"Multi-lingual Abilities": {
|
529 |
+
"Overall": 43.82
|
530 |
+
}
|
531 |
+
},
|
532 |
+
"LLaMA2-7B-Chat": {
|
533 |
+
"META": {
|
534 |
+
"Method": [
|
535 |
+
"LLaMA2-7B-Chat",
|
536 |
+
"https://huggingface.co/meta-llama/Llama-2-7b-chat-hf"
|
537 |
+
],
|
538 |
+
"Parameters": "7B",
|
539 |
+
"Org": "Meta",
|
540 |
+
"OpenSource": "Yes",
|
541 |
+
"Verified": "Yes"
|
542 |
+
},
|
543 |
+
"Shopping Concept Understanding": {
|
544 |
+
"Overall": 51.67
|
545 |
+
},
|
546 |
+
"Shopping Knowledge Reasoning": {
|
547 |
+
"Overall": 43.48
|
548 |
+
},
|
549 |
+
"User Behavior Alignment": {
|
550 |
+
"Overall": 41.42
|
551 |
+
},
|
552 |
+
"Multi-lingual Abilities": {
|
553 |
+
"Overall": 40.43
|
554 |
+
}
|
555 |
+
},
|
556 |
+
"LLaMA2-7B": {
|
557 |
+
"META": {
|
558 |
+
"Method": [
|
559 |
+
"LLaMA2-7B",
|
560 |
+
"https://huggingface.co/meta-llama/Llama-2-7b-hf"
|
561 |
+
],
|
562 |
+
"Parameters": "7B",
|
563 |
+
"Org": "Meta",
|
564 |
+
"OpenSource": "Yes",
|
565 |
+
"Verified": "Yes"
|
566 |
+
},
|
567 |
+
"Shopping Concept Understanding": {
|
568 |
+
"Overall": 38.22
|
569 |
+
},
|
570 |
+
"Shopping Knowledge Reasoning": {
|
571 |
+
"Overall": 32.81
|
572 |
+
},
|
573 |
+
"User Behavior Alignment": {
|
574 |
+
"Overall": 32.56
|
575 |
+
},
|
576 |
+
"Multi-lingual Abilities": {
|
577 |
+
"Overall": 27.71
|
578 |
+
}
|
579 |
+
},
|
580 |
+
"QWen1.5-4B": {
|
581 |
+
"META": {
|
582 |
+
"Method": [
|
583 |
+
"QWen1.5-4B",
|
584 |
+
"https://huggingface.co/Qwen/Qwen1.5-4B"
|
585 |
+
],
|
586 |
+
"Parameters": "4B",
|
587 |
+
"Org": "Alibaba",
|
588 |
+
"OpenSource": "Yes",
|
589 |
+
"Verified": "Yes"
|
590 |
+
},
|
591 |
+
"Shopping Concept Understanding": {
|
592 |
+
"Overall": 57.21
|
593 |
+
},
|
594 |
+
"Shopping Knowledge Reasoning": {
|
595 |
+
"Overall": 52.56
|
596 |
+
},
|
597 |
+
"User Behavior Alignment": {
|
598 |
+
"Overall": 42.74
|
599 |
+
},
|
600 |
+
"Multi-lingual Abilities": {
|
601 |
+
"Overall": 49.78
|
602 |
+
}
|
603 |
+
},
|
604 |
+
"Phi-2": {
|
605 |
+
"META": {
|
606 |
+
"Method": [
|
607 |
+
"Phi-2",
|
608 |
+
"https://huggingface.co/microsoft/phi-2"
|
609 |
+
],
|
610 |
+
"Parameters": "2.8B",
|
611 |
+
"Org": "Microsoft",
|
612 |
+
"OpenSource": "Yes",
|
613 |
+
"Verified": "Yes"
|
614 |
+
},
|
615 |
+
"Shopping Concept Understanding": {
|
616 |
+
"Overall": 49.34
|
617 |
+
},
|
618 |
+
"Shopping Knowledge Reasoning": {
|
619 |
+
"Overall": 42.83
|
620 |
+
},
|
621 |
+
"User Behavior Alignment": {
|
622 |
+
"Overall": 36.38
|
623 |
+
},
|
624 |
+
"Multi-lingual Abilities": {
|
625 |
+
"Overall": 32.91
|
626 |
+
}
|
627 |
+
},
|
628 |
+
"eCeLLM-S": {
|
629 |
+
"META": {
|
630 |
+
"Method": [
|
631 |
+
"eCeLLM-S",
|
632 |
+
"https://huggingface.co/NingLab/eCeLLM-S"
|
633 |
+
],
|
634 |
+
"Parameters": "2.8B",
|
635 |
+
"Org": "OSU NingLab",
|
636 |
+
"OpenSource": "Yes",
|
637 |
+
"Verified": "Yes"
|
638 |
+
},
|
639 |
+
"Shopping Concept Understanding": {
|
640 |
+
"Overall": 49.4
|
641 |
+
},
|
642 |
+
"Shopping Knowledge Reasoning": {
|
643 |
+
"Overall": 39.06
|
644 |
+
},
|
645 |
+
"User Behavior Alignment": {
|
646 |
+
"Overall": 36.33
|
647 |
+
},
|
648 |
+
"Multi-lingual Abilities": {
|
649 |
+
"Overall": 32.79
|
650 |
+
}
|
651 |
+
}
|
652 |
+
}
|
653 |
+
}
|
__pycache__/meta_data.cpython-38.pyc
CHANGED
Binary files a/__pycache__/meta_data.cpython-38.pyc and b/__pycache__/meta_data.cpython-38.pyc differ
|
|
app.py
CHANGED
@@ -11,8 +11,8 @@ with gr.Blocks() as demo:
|
|
11 |
EVAL_TIME = format_timestamp(timestamp)
|
12 |
results = struct['results']
|
13 |
N_MODEL = len(results)
|
14 |
-
N_DATA = len(results['
|
15 |
-
DATASETS = list(results['
|
16 |
DATASETS.remove('META')
|
17 |
print(DATASETS)
|
18 |
|
|
|
11 |
EVAL_TIME = format_timestamp(timestamp)
|
12 |
results = struct['results']
|
13 |
N_MODEL = len(results)
|
14 |
+
N_DATA = len(results['Claude3-Sonnet']) - 1
|
15 |
+
DATASETS = list(results['Claude3-Sonnet'])
|
16 |
DATASETS.remove('META')
|
17 |
print(DATASETS)
|
18 |
|
meta_data.py
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
# CONSTANTS-URL
|
2 |
URL = "http://opencompass.openxlab.space/assets/OpenVLM.json"
|
3 |
-
RESULTS = '
|
4 |
SHOPPINGMMLU_README = 'https://raw.githubusercontent.com/KL4805/ShoppingMMLU/refs/heads/main/README.md'
|
5 |
# CONSTANTS-CITATION
|
6 |
CITATION_BUTTON_TEXT = r"""@article{jin2024shopping,
|
|
|
1 |
# CONSTANTS-URL
|
2 |
URL = "http://opencompass.openxlab.space/assets/OpenVLM.json"
|
3 |
+
RESULTS = 'ShoppingMMLU_overall.json'
|
4 |
SHOPPINGMMLU_README = 'https://raw.githubusercontent.com/KL4805/ShoppingMMLU/refs/heads/main/README.md'
|
5 |
# CONSTANTS-CITATION
|
6 |
CITATION_BUTTON_TEXT = r"""@article{jin2024shopping,
|