Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,339 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
## Model Details
|
5 |
Lim is a general text embedding model(chinese),We are continuously optimizing it.
|
@@ -23,7 +357,7 @@ model_name="liujiarik/lim_base_zh"
|
|
23 |
from sentence_transformers import SentenceTransformer
|
24 |
sentences = ['我换手机号了', '如果我换手机怎么办?']
|
25 |
|
26 |
-
model = SentenceTransformer(
|
27 |
embeddings = model.encode(sentences)
|
28 |
print(embeddings)
|
29 |
```
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- mteb
|
5 |
+
model-index:
|
6 |
+
- name: kim_base_zh_v0
|
7 |
+
results:
|
8 |
+
- task:
|
9 |
+
type: Classification
|
10 |
+
dataset:
|
11 |
+
type: mteb/amazon_reviews_multi
|
12 |
+
name: MTEB AmazonReviewsClassification (zh)
|
13 |
+
config: zh
|
14 |
+
split: test
|
15 |
+
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
|
16 |
+
metrics:
|
17 |
+
- type: accuracy
|
18 |
+
value: 46.66600000000001
|
19 |
+
- type: f1
|
20 |
+
value: 43.88121213919628
|
21 |
+
- task:
|
22 |
+
type: Clustering
|
23 |
+
dataset:
|
24 |
+
type: C-MTEB/CLSClusteringP2P
|
25 |
+
name: MTEB CLSClusteringP2P
|
26 |
+
config: default
|
27 |
+
split: test
|
28 |
+
revision: None
|
29 |
+
metrics:
|
30 |
+
- type: v_measure
|
31 |
+
value: 33.55469933811146
|
32 |
+
- task:
|
33 |
+
type: Clustering
|
34 |
+
dataset:
|
35 |
+
type: C-MTEB/CLSClusteringS2S
|
36 |
+
name: MTEB CLSClusteringS2S
|
37 |
+
config: default
|
38 |
+
split: test
|
39 |
+
revision: None
|
40 |
+
metrics:
|
41 |
+
- type: v_measure
|
42 |
+
value: 36.17977796122646
|
43 |
+
- task:
|
44 |
+
type: Reranking
|
45 |
+
dataset:
|
46 |
+
type: C-MTEB/CMedQAv1-reranking
|
47 |
+
name: MTEB CMedQAv1
|
48 |
+
config: default
|
49 |
+
split: test
|
50 |
+
revision: None
|
51 |
+
metrics:
|
52 |
+
- type: map
|
53 |
+
value: 83.84687250720238
|
54 |
+
- type: mrr
|
55 |
+
value: 86.34579365079364
|
56 |
+
- task:
|
57 |
+
type: Reranking
|
58 |
+
dataset:
|
59 |
+
type: C-MTEB/CMedQAv2-reranking
|
60 |
+
name: MTEB CMedQAv2
|
61 |
+
config: default
|
62 |
+
split: test
|
63 |
+
revision: None
|
64 |
+
metrics:
|
65 |
+
- type: map
|
66 |
+
value: 84.7457752094449
|
67 |
+
- type: mrr
|
68 |
+
value: 87.41591269841268
|
69 |
+
- task:
|
70 |
+
type: PairClassification
|
71 |
+
dataset:
|
72 |
+
type: C-MTEB/CMNLI
|
73 |
+
name: MTEB Cmnli
|
74 |
+
config: default
|
75 |
+
split: validation
|
76 |
+
revision: None
|
77 |
+
metrics:
|
78 |
+
- type: cos_sim_accuracy
|
79 |
+
value: 70.99218280216476
|
80 |
+
- type: cos_sim_ap
|
81 |
+
value: 79.5838273070596
|
82 |
+
- type: cos_sim_f1
|
83 |
+
value: 73.01215092730762
|
84 |
+
- type: cos_sim_precision
|
85 |
+
value: 67.09108716944172
|
86 |
+
- type: cos_sim_recall
|
87 |
+
value: 80.07949497311199
|
88 |
+
- type: dot_accuracy
|
89 |
+
value: 70.99218280216476
|
90 |
+
- type: dot_ap
|
91 |
+
value: 79.58744690895374
|
92 |
+
- type: dot_f1
|
93 |
+
value: 73.01215092730762
|
94 |
+
- type: dot_precision
|
95 |
+
value: 67.09108716944172
|
96 |
+
- type: dot_recall
|
97 |
+
value: 80.07949497311199
|
98 |
+
- type: euclidean_accuracy
|
99 |
+
value: 70.99218280216476
|
100 |
+
- type: euclidean_ap
|
101 |
+
value: 79.5838273070596
|
102 |
+
- type: euclidean_f1
|
103 |
+
value: 73.01215092730762
|
104 |
+
- type: euclidean_precision
|
105 |
+
value: 67.09108716944172
|
106 |
+
- type: euclidean_recall
|
107 |
+
value: 80.07949497311199
|
108 |
+
- type: manhattan_accuracy
|
109 |
+
value: 70.88394467829224
|
110 |
+
- type: manhattan_ap
|
111 |
+
value: 79.42301231718942
|
112 |
+
- type: manhattan_f1
|
113 |
+
value: 72.72536687631029
|
114 |
+
- type: manhattan_precision
|
115 |
+
value: 65.91297738932168
|
116 |
+
- type: manhattan_recall
|
117 |
+
value: 81.10825344867898
|
118 |
+
- type: max_accuracy
|
119 |
+
value: 70.99218280216476
|
120 |
+
- type: max_ap
|
121 |
+
value: 79.58744690895374
|
122 |
+
- type: max_f1
|
123 |
+
value: 73.01215092730762
|
124 |
+
- task:
|
125 |
+
type: Classification
|
126 |
+
dataset:
|
127 |
+
type: C-MTEB/IFlyTek-classification
|
128 |
+
name: MTEB IFlyTek
|
129 |
+
config: default
|
130 |
+
split: validation
|
131 |
+
revision: None
|
132 |
+
metrics:
|
133 |
+
- type: accuracy
|
134 |
+
value: 47.34128510965756
|
135 |
+
- type: f1
|
136 |
+
value: 35.49963469301016
|
137 |
+
- task:
|
138 |
+
type: Classification
|
139 |
+
dataset:
|
140 |
+
type: C-MTEB/JDReview-classification
|
141 |
+
name: MTEB JDReview
|
142 |
+
config: default
|
143 |
+
split: test
|
144 |
+
revision: None
|
145 |
+
metrics:
|
146 |
+
- type: accuracy
|
147 |
+
value: 85.66604127579738
|
148 |
+
- type: ap
|
149 |
+
value: 53.038152290755555
|
150 |
+
- type: f1
|
151 |
+
value: 80.14685686902159
|
152 |
+
- task:
|
153 |
+
type: Reranking
|
154 |
+
dataset:
|
155 |
+
type: C-MTEB/Mmarco-reranking
|
156 |
+
name: MTEB MMarcoReranking
|
157 |
+
config: default
|
158 |
+
split: dev
|
159 |
+
revision: None
|
160 |
+
metrics:
|
161 |
+
- type: map
|
162 |
+
value: 20.56449688140155
|
163 |
+
- type: mrr
|
164 |
+
value: 19.60753968253968
|
165 |
+
- task:
|
166 |
+
type: Classification
|
167 |
+
dataset:
|
168 |
+
type: mteb/amazon_massive_intent
|
169 |
+
name: MTEB MassiveIntentClassification (zh-CN)
|
170 |
+
config: zh-CN
|
171 |
+
split: test
|
172 |
+
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
|
173 |
+
metrics:
|
174 |
+
- type: accuracy
|
175 |
+
value: 72.38399462004035
|
176 |
+
- type: f1
|
177 |
+
value: 70.33023134666634
|
178 |
+
- task:
|
179 |
+
type: Classification
|
180 |
+
dataset:
|
181 |
+
type: mteb/amazon_massive_scenario
|
182 |
+
name: MTEB MassiveScenarioClassification (zh-CN)
|
183 |
+
config: zh-CN
|
184 |
+
split: test
|
185 |
+
revision: 7d571f92784cd94a019292a1f45445077d0ef634
|
186 |
+
metrics:
|
187 |
+
- type: accuracy
|
188 |
+
value: 74.87222595830531
|
189 |
+
- type: f1
|
190 |
+
value: 74.25722751562503
|
191 |
+
- task:
|
192 |
+
type: Classification
|
193 |
+
dataset:
|
194 |
+
type: C-MTEB/MultilingualSentiment-classification
|
195 |
+
name: MTEB MultilingualSentiment
|
196 |
+
config: default
|
197 |
+
split: validation
|
198 |
+
revision: None
|
199 |
+
metrics:
|
200 |
+
- type: accuracy
|
201 |
+
value: 76.27000000000001
|
202 |
+
- type: f1
|
203 |
+
value: 75.9660773461064
|
204 |
+
- task:
|
205 |
+
type: PairClassification
|
206 |
+
dataset:
|
207 |
+
type: C-MTEB/OCNLI
|
208 |
+
name: MTEB Ocnli
|
209 |
+
config: default
|
210 |
+
split: validation
|
211 |
+
revision: None
|
212 |
+
metrics:
|
213 |
+
- type: cos_sim_accuracy
|
214 |
+
value: 67.35246345425013
|
215 |
+
- type: cos_sim_ap
|
216 |
+
value: 69.69618171375657
|
217 |
+
- type: cos_sim_f1
|
218 |
+
value: 71.70665459483928
|
219 |
+
- type: cos_sim_precision
|
220 |
+
value: 62.75752773375595
|
221 |
+
- type: cos_sim_recall
|
222 |
+
value: 83.6325237592397
|
223 |
+
- type: dot_accuracy
|
224 |
+
value: 67.35246345425013
|
225 |
+
- type: dot_ap
|
226 |
+
value: 69.69618171375657
|
227 |
+
- type: dot_f1
|
228 |
+
value: 71.70665459483928
|
229 |
+
- type: dot_precision
|
230 |
+
value: 62.75752773375595
|
231 |
+
- type: dot_recall
|
232 |
+
value: 83.6325237592397
|
233 |
+
- type: euclidean_accuracy
|
234 |
+
value: 67.35246345425013
|
235 |
+
- type: euclidean_ap
|
236 |
+
value: 69.69618171375657
|
237 |
+
- type: euclidean_f1
|
238 |
+
value: 71.70665459483928
|
239 |
+
- type: euclidean_precision
|
240 |
+
value: 62.75752773375595
|
241 |
+
- type: euclidean_recall
|
242 |
+
value: 83.6325237592397
|
243 |
+
- type: manhattan_accuracy
|
244 |
+
value: 66.81104493773688
|
245 |
+
- type: manhattan_ap
|
246 |
+
value: 69.33781930832232
|
247 |
+
- type: manhattan_f1
|
248 |
+
value: 71.6342082980525
|
249 |
+
- type: manhattan_precision
|
250 |
+
value: 59.78798586572438
|
251 |
+
- type: manhattan_recall
|
252 |
+
value: 89.33474128827878
|
253 |
+
- type: max_accuracy
|
254 |
+
value: 67.35246345425013
|
255 |
+
- type: max_ap
|
256 |
+
value: 69.69618171375657
|
257 |
+
- type: max_f1
|
258 |
+
value: 71.70665459483928
|
259 |
+
- task:
|
260 |
+
type: Classification
|
261 |
+
dataset:
|
262 |
+
type: C-MTEB/OnlineShopping-classification
|
263 |
+
name: MTEB OnlineShopping
|
264 |
+
config: default
|
265 |
+
split: test
|
266 |
+
revision: None
|
267 |
+
metrics:
|
268 |
+
- type: accuracy
|
269 |
+
value: 93.05
|
270 |
+
- type: ap
|
271 |
+
value: 91.26069801777923
|
272 |
+
- type: f1
|
273 |
+
value: 93.04149818231389
|
274 |
+
- task:
|
275 |
+
type: Reranking
|
276 |
+
dataset:
|
277 |
+
type: C-MTEB/T2Reranking
|
278 |
+
name: MTEB T2Reranking
|
279 |
+
config: default
|
280 |
+
split: dev
|
281 |
+
revision: None
|
282 |
+
metrics:
|
283 |
+
- type: map
|
284 |
+
value: 65.74883739850293
|
285 |
+
- type: mrr
|
286 |
+
value: 75.47326869136282
|
287 |
+
- task:
|
288 |
+
type: Classification
|
289 |
+
dataset:
|
290 |
+
type: C-MTEB/TNews-classification
|
291 |
+
name: MTEB TNews
|
292 |
+
config: default
|
293 |
+
split: validation
|
294 |
+
revision: None
|
295 |
+
metrics:
|
296 |
+
- type: accuracy
|
297 |
+
value: 53.269999999999996
|
298 |
+
- type: f1
|
299 |
+
value: 51.410630382886445
|
300 |
+
- task:
|
301 |
+
type: Clustering
|
302 |
+
dataset:
|
303 |
+
type: C-MTEB/ThuNewsClusteringP2P
|
304 |
+
name: MTEB ThuNewsClusteringP2P
|
305 |
+
config: default
|
306 |
+
split: test
|
307 |
+
revision: None
|
308 |
+
metrics:
|
309 |
+
- type: v_measure
|
310 |
+
value: 63.344532225921434
|
311 |
+
- task:
|
312 |
+
type: Clustering
|
313 |
+
dataset:
|
314 |
+
type: C-MTEB/ThuNewsClusteringS2S
|
315 |
+
name: MTEB ThuNewsClusteringS2S
|
316 |
+
config: default
|
317 |
+
split: test
|
318 |
+
revision: None
|
319 |
+
metrics:
|
320 |
+
- type: v_measure
|
321 |
+
value: 60.33437882010517
|
322 |
+
- task:
|
323 |
+
type: Classification
|
324 |
+
dataset:
|
325 |
+
type: C-MTEB/waimai-classification
|
326 |
+
name: MTEB Waimai
|
327 |
+
config: default
|
328 |
+
split: test
|
329 |
+
revision: None
|
330 |
+
metrics:
|
331 |
+
- type: accuracy
|
332 |
+
value: 87.96000000000002
|
333 |
+
- type: ap
|
334 |
+
value: 72.43737061465443
|
335 |
+
- type: f1
|
336 |
+
value: 86.48668399738767
|
337 |
---
|
338 |
## Model Details
|
339 |
Lim is a general text embedding model(chinese),We are continuously optimizing it.
|
|
|
357 |
from sentence_transformers import SentenceTransformer
|
358 |
sentences = ['我换手机号了', '如果我换手机怎么办?']
|
359 |
|
360 |
+
model = SentenceTransformer(model_name)
|
361 |
embeddings = model.encode(sentences)
|
362 |
print(embeddings)
|
363 |
```
|