Hugging Face's logo

FINGU-AI
/
FingUEm_V3

Sentence Similarity
sentence-transformers
Safetensors
qwen2
feature-extraction
Generated from Trainer
dataset_size:245133
loss:MultipleNegativesRankingLoss
loss:MultipleNegativesSymmetricRankingLoss
loss:CoSENTLoss
custom_code
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
2
FINGU-AI commited on
Commit
b0be664
•
1 Parent(s): 06860ac

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +346 -0
README.md CHANGED
@@ -13,6 +13,352 @@ tags:
13
  - loss:MultipleNegativesRankingLoss
14
  - loss:MultipleNegativesSymmetricRankingLoss
15
  - loss:CoSENTLoss
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  widget:
17
  - source_sentence: Ramjipura Khurd
18
  sentences:
 
13
  - loss:MultipleNegativesRankingLoss
14
  - loss:MultipleNegativesSymmetricRankingLoss
15
  - loss:CoSENTLoss
16
+ model-index:
17
+ - name: FINGU-AI/FingUEm_V3
18
+ results:
19
+ - dataset:
20
+ config: en
21
+ name: MTEB AmazonCounterfactualClassification (en)
22
+ revision: e8379541af4e31359cca9fbcf4b00f2671dba205
23
+ split: test
24
+ type: mteb/amazon_counterfactual
25
+ metrics:
26
+ - type: accuracy
27
+ value: 67.56716417910448
28
+ - type: ap
29
+ value: 30.02471979440035
30
+ - type: ap_weighted
31
+ value: 30.02471979440035
32
+ - type: f1
33
+ value: 61.36476131114457
34
+ - type: f1_weighted
35
+ value: 70.71966866655379
36
+ - type: main_score
37
+ value: 67.56716417910448
38
+ task:
39
+ type: Classification
40
+ - dataset:
41
+ config: en
42
+ name: MTEB AmazonCounterfactualClassification (en)
43
+ revision: e8379541af4e31359cca9fbcf4b00f2671dba205
44
+ split: validation
45
+ type: mteb/amazon_counterfactual
46
+ metrics:
47
+ - type: accuracy
48
+ value: 66.6865671641791
49
+ - type: ap
50
+ value: 27.152380257287113
51
+ - type: ap_weighted
52
+ value: 27.152380257287113
53
+ - type: f1
54
+ value: 59.72007766256577
55
+ - type: f1_weighted
56
+ value: 70.61181328653
57
+ - type: main_score
58
+ value: 66.6865671641791
59
+ task:
60
+ type: Classification
61
+ - dataset:
62
+ config: default
63
+ name: MTEB AmazonPolarityClassification (default)
64
+ revision: e2d317d38cd51312af73b3d32a06d1a08b442046
65
+ split: test
66
+ type: mteb/amazon_polarity
67
+ metrics:
68
+ - type: accuracy
69
+ value: 92.25822500000001
70
+ - type: ap
71
+ value: 89.56517644032817
72
+ - type: ap_weighted
73
+ value: 89.56517644032817
74
+ - type: f1
75
+ value: 92.25315581436197
76
+ - type: f1_weighted
77
+ value: 92.25315581436197
78
+ - type: main_score
79
+ value: 92.25822500000001
80
+ task:
81
+ type: Classification
82
+ - dataset:
83
+ config: en
84
+ name: MTEB AmazonReviewsClassification (en)
85
+ revision: 1399c76144fd37290681b995c656ef9b2e06e26d
86
+ split: test
87
+ type: mteb/amazon_reviews_multi
88
+ metrics:
89
+ - type: accuracy
90
+ value: 45.126
91
+ - type: f1
92
+ value: 43.682985571986556
93
+ - type: f1_weighted
94
+ value: 43.682985571986556
95
+ - type: main_score
96
+ value: 45.126
97
+ task:
98
+ type: Classification
99
+ - dataset:
100
+ config: en
101
+ name: MTEB AmazonReviewsClassification (en)
102
+ revision: 1399c76144fd37290681b995c656ef9b2e06e26d
103
+ split: validation
104
+ type: mteb/amazon_reviews_multi
105
+ metrics:
106
+ - type: accuracy
107
+ value: 45.164
108
+ - type: f1
109
+ value: 43.65297652493158
110
+ - type: f1_weighted
111
+ value: 43.65297652493158
112
+ - type: main_score
113
+ value: 45.164
114
+ task:
115
+ type: Classification
116
+ - dataset:
117
+ config: default
118
+ name: MTEB Banking77Classification (default)
119
+ revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
120
+ split: test
121
+ type: mteb/banking77
122
+ metrics:
123
+ - type: accuracy
124
+ value: 79.83441558441558
125
+ - type: f1
126
+ value: 79.09907222314298
127
+ - type: f1_weighted
128
+ value: 79.099072223143
129
+ - type: main_score
130
+ value: 79.83441558441558
131
+ task:
132
+ type: Classification
133
+ - dataset:
134
+ config: default
135
+ name: MTEB EmotionClassification (default)
136
+ revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
137
+ split: test
138
+ type: mteb/emotion
139
+ metrics:
140
+ - type: accuracy
141
+ value: 54.50999999999999
142
+ - type: f1
143
+ value: 48.99139408155793
144
+ - type: f1_weighted
145
+ value: 56.45912892127605
146
+ - type: main_score
147
+ value: 54.50999999999999
148
+ task:
149
+ type: Classification
150
+ - dataset:
151
+ config: default
152
+ name: MTEB EmotionClassification (default)
153
+ revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
154
+ split: validation
155
+ type: mteb/emotion
156
+ metrics:
157
+ - type: accuracy
158
+ value: 54.50000000000001
159
+ - type: f1
160
+ value: 50.275823093483815
161
+ - type: f1_weighted
162
+ value: 55.979686603747425
163
+ - type: main_score
164
+ value: 54.50000000000001
165
+ task:
166
+ type: Classification
167
+ - dataset:
168
+ config: default
169
+ name: MTEB ImdbClassification (default)
170
+ revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
171
+ split: test
172
+ type: mteb/imdb
173
+ metrics:
174
+ - type: accuracy
175
+ value: 90.9104
176
+ - type: ap
177
+ value: 87.34741582218639
178
+ - type: ap_weighted
179
+ value: 87.34741582218639
180
+ - type: f1
181
+ value: 90.90089555573083
182
+ - type: f1_weighted
183
+ value: 90.90089555573083
184
+ - type: main_score
185
+ value: 90.9104
186
+ task:
187
+ type: Classification
188
+ - dataset:
189
+ config: en
190
+ name: MTEB MTOPDomainClassification (en)
191
+ revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
192
+ split: test
193
+ type: mteb/mtop_domain
194
+ metrics:
195
+ - type: accuracy
196
+ value: 90.71363429092567
197
+ - type: f1
198
+ value: 90.48838884632374
199
+ - type: f1_weighted
200
+ value: 90.6757419789302
201
+ - type: main_score
202
+ value: 90.71363429092567
203
+ task:
204
+ type: Classification
205
+ - dataset:
206
+ config: en
207
+ name: MTEB MTOPDomainClassification (en)
208
+ revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
209
+ split: validation
210
+ type: mteb/mtop_domain
211
+ metrics:
212
+ - type: accuracy
213
+ value: 90.5771812080537
214
+ - type: f1
215
+ value: 90.75440480842857
216
+ - type: f1_weighted
217
+ value: 90.52002736015308
218
+ - type: main_score
219
+ value: 90.5771812080537
220
+ task:
221
+ type: Classification
222
+ - dataset:
223
+ config: en
224
+ name: MTEB MTOPIntentClassification (en)
225
+ revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
226
+ split: test
227
+ type: mteb/mtop_intent
228
+ metrics:
229
+ - type: accuracy
230
+ value: 63.6388508891929
231
+ - type: f1
232
+ value: 46.797425199843055
233
+ - type: f1_weighted
234
+ value: 66.06923770534857
235
+ - type: main_score
236
+ value: 63.6388508891929
237
+ task:
238
+ type: Classification
239
+ - dataset:
240
+ config: en
241
+ name: MTEB MTOPIntentClassification (en)
242
+ revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
243
+ split: validation
244
+ type: mteb/mtop_intent
245
+ metrics:
246
+ - type: accuracy
247
+ value: 64.40715883668904
248
+ - type: f1
249
+ value: 46.16190436869664
250
+ - type: f1_weighted
251
+ value: 67.35202429204169
252
+ - type: main_score
253
+ value: 64.40715883668904
254
+ task:
255
+ type: Classification
256
+ - dataset:
257
+ config: en
258
+ name: MTEB MassiveIntentClassification (en)
259
+ revision: 4672e20407010da34463acc759c162ca9734bca6
260
+ split: test
261
+ type: mteb/amazon_massive_intent
262
+ metrics:
263
+ - type: accuracy
264
+ value: 69.59314055144587
265
+ - type: f1
266
+ value: 68.79212819626133
267
+ - type: f1_weighted
268
+ value: 68.69206463617618
269
+ - type: main_score
270
+ value: 69.59314055144587
271
+ task:
272
+ type: Classification
273
+ - dataset:
274
+ config: en
275
+ name: MTEB MassiveIntentClassification (en)
276
+ revision: 4672e20407010da34463acc759c162ca9734bca6
277
+ split: validation
278
+ type: mteb/amazon_massive_intent
279
+ metrics:
280
+ - type: accuracy
281
+ value: 69.59173635022135
282
+ - type: f1
283
+ value: 67.52854688868585
284
+ - type: f1_weighted
285
+ value: 68.43317662845128
286
+ - type: main_score
287
+ value: 69.59173635022135
288
+ task:
289
+ type: Classification
290
+ - dataset:
291
+ config: en
292
+ name: MTEB MassiveScenarioClassification (en)
293
+ revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
294
+ split: test
295
+ type: mteb/amazon_massive_scenario
296
+ metrics:
297
+ - type: accuracy
298
+ value: 73.7794216543376
299
+ - type: f1
300
+ value: 73.98844357082736
301
+ - type: f1_weighted
302
+ value: 73.60582907171401
303
+ - type: main_score
304
+ value: 73.7794216543376
305
+ task:
306
+ type: Classification
307
+ - dataset:
308
+ config: en
309
+ name: MTEB MassiveScenarioClassification (en)
310
+ revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
311
+ split: validation
312
+ type: mteb/amazon_massive_scenario
313
+ metrics:
314
+ - type: accuracy
315
+ value: 73.98425971470732
316
+ - type: f1
317
+ value: 73.76511807299376
318
+ - type: f1_weighted
319
+ value: 73.78920853484385
320
+ - type: main_score
321
+ value: 73.98425971470732
322
+ task:
323
+ type: Classification
324
+ - dataset:
325
+ config: default
326
+ name: MTEB ToxicConversationsClassification (default)
327
+ revision: edfaf9da55d3dd50d43143d90c1ac476895ae6de
328
+ split: test
329
+ type: mteb/toxic_conversations_50k
330
+ metrics:
331
+ - type: accuracy
332
+ value: 64.1259765625
333
+ - type: ap
334
+ value: 12.280449516326373
335
+ - type: ap_weighted
336
+ value: 12.280449516326373
337
+ - type: f1
338
+ value: 49.874354210101345
339
+ - type: f1_weighted
340
+ value: 71.91204958735288
341
+ - type: main_score
342
+ value: 64.1259765625
343
+ task:
344
+ type: Classification
345
+ - dataset:
346
+ config: default
347
+ name: MTEB TweetSentimentExtractionClassification (default)
348
+ revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
349
+ split: test
350
+ type: mteb/tweet_sentiment_extraction
351
+ metrics:
352
+ - type: accuracy
353
+ value: 63.17770232031692
354
+ - type: f1
355
+ value: 63.33879583206008
356
+ - type: f1_weighted
357
+ value: 62.27745749800532
358
+ - type: main_score
359
+ value: 63.17770232031692
360
+ task:
361
+ type: Classification
362
  widget:
363
  - source_sentence: Ramjipura Khurd
364
  sentences: