akot commited on
Commit
07d1868
·
verified ·
1 Parent(s): 6231997

Add new SentenceTransformer model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,835 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: aari1995/German_Semantic_V3
3
+ datasets: []
4
+ language: []
5
+ library_name: sentence-transformers
6
+ metrics:
7
+ - cosine_accuracy@1
8
+ - cosine_accuracy@3
9
+ - cosine_accuracy@5
10
+ - cosine_accuracy@10
11
+ - cosine_precision@1
12
+ - cosine_precision@3
13
+ - cosine_precision@5
14
+ - cosine_precision@10
15
+ - cosine_recall@1
16
+ - cosine_recall@3
17
+ - cosine_recall@5
18
+ - cosine_recall@10
19
+ - cosine_ndcg@10
20
+ - cosine_mrr@10
21
+ - cosine_map@100
22
+ pipeline_tag: sentence-similarity
23
+ tags:
24
+ - sentence-transformers
25
+ - sentence-similarity
26
+ - feature-extraction
27
+ - generated_from_trainer
28
+ - dataset_size:4957
29
+ - loss:MatryoshkaLoss
30
+ - loss:MultipleNegativesRankingLoss
31
+ widget:
32
+ - source_sentence: 312 Aus steuerlicher Sicht ist es möglich, mehrere Versorgungszusagen
33
+ nebeneinander, also neben einer Altzusage auch eine Neuzusage zu erteilen (z.
34
+ B. „alte“ Direktversicherung und „neuer“ Pensionsfonds).
35
+ sentences:
36
+ - Wann liegt bei der betrieblichen Altersversorgung eine schädliche Verwendung vor?
37
+ - Welche steuerliche Behandlung erfahren Auszahlungen aus Altersvorsorgeverträgen
38
+ nach § 22 Nr. 5 EStG?
39
+ - Können verschiedene Versorgungszusagen wie Direktversicherung und Pensionsfonds
40
+ gleichzeitig bestehen?
41
+ - source_sentence: 5 Pflichtversicherte nach dem Gesetz über die Alterssicherung der
42
+ Landwirte gehören, soweit sie nicht als Pflichtversicherte der gesetzlichen Rentenversicherung
43
+ ohnehin bereits anspruchsberechtigt sind, in dieser Eigenschaft ebenfalls zum
44
+ begünstigten Personenkreis. Darunter fallen insbesondere die in Anlage 1 Abschnitt
45
+ B aufgeführten Personen.
46
+ sentences:
47
+ - Wann wird das Anrecht der ausgleichsberechtigten Person bei intern geteilter Altersvorsorge
48
+ als abgeschlossen betrachtet?
49
+ - Welche Personen sind in der Anlage 1 Abschnitt B bezüglich der Alterssicherung
50
+ der Landwirte aufgeführt?
51
+ - In welchen Fällen führt die Möglichkeit einer Beitragserstattung nicht zur Versagung
52
+ der Anerkennung als betriebliche Altersversorgung?
53
+ - source_sentence: 233 Voraussetzung für die Förderung durch Sonderausgabenabzug nach
54
+ § 10a EStG und Zulage nach Abschnitt XI EStG ist in den Fällen der Rz. 231 f.,
55
+ dass der Steuerpflichtige zum begünstigten Personenkreis gehört. Die zeitliche
56
+ Zuordnung dieser Altersvorsorgebeiträge richtet sich grundsätzlich nach § 11 Abs.
57
+ 2 EStG.
58
+ sentences:
59
+ - Wer gehört zum begünstigten Personenkreis für die Altersvorsorgeförderung?
60
+ - Wie werden erstattete Kosten eines Altersvorsorgevertrags besteuert, wenn sie
61
+ dem Steuerpflichtigen ausgezahlt werden?
62
+ - Ist der Übertragungswert einer betrieblichen Altersversorgung bei einem Arbeitgeberwechsel
63
+ steuerfrei?
64
+ - source_sentence: 127 Die Entnahme des Teilkapitalbetrags von bis zu 30 % des zur
65
+ Verfügung stehenden Kapitals aus dem Vertrag hat zu Beginn der Auszahlungsphase
66
+ zu erfolgen. Eine Verteilung über mehrere Auszahlungszeitpunkte ist nicht möglich.
67
+ sentences:
68
+ - Kann ich den Teilkapitalbetrag aus meiner Altersvorsorge zu verschiedenen Zeitpunkten
69
+ entnehmen?
70
+ - Welche Einkunftsarten können Leistungen aus einer Versorgungszusage des Arbeitgebers
71
+ sein?
72
+ - Was ist im Todesfall des Zulageberechtigten bezüglich der Förderbeiträge zu tun?
73
+ - source_sentence: '67 Abwandlung des Beispiels 1 in Rn. 66: A erhält zudem zwei Kinderzulagen
74
+ für seine in den Jahren 2004 und 2005 geborenen Kinder. Beitragspflichtige Einnahmen
75
+ 53.000 € 4 % 2.120 € höchstens 2.100 € anzusetzen 2.100 € abzüglich Zulage 175
76
+ € Mindesteigenbeitrag (§ 86 Abs. 1 Satz 2 EStG) 1.925 € Sockelbetrag (§ 86 Abs.
77
+ 1 Satz 4 EStG) 60 € maßgebend (§ 86 Abs. 1 Satz 5 EStG) 1.925 € Die von A geleisteten
78
+ Beiträge übersteigen den Mindesteigenbeitrag. Die Zulage wird nicht gekürzt.'
79
+ sentences:
80
+ - Wird die Zulage für A gekürzt, wenn die Beiträge den Mindesteigenbeitrag übersteigen?
81
+ - Was versteht man unter Sonderzahlungen des Arbeitgebers?
82
+ - Wie erfolgt die Besteuerung bei der ausgleichsberechtigten Person nach einer externen
83
+ Teilung?
84
+ model-index:
85
+ - name: SentenceTransformer based on aari1995/German_Semantic_V3
86
+ results:
87
+ - task:
88
+ type: information-retrieval
89
+ name: Information Retrieval
90
+ dataset:
91
+ name: dim 768
92
+ type: dim_768
93
+ metrics:
94
+ - type: cosine_accuracy@1
95
+ value: 0.02722323049001815
96
+ name: Cosine Accuracy@1
97
+ - type: cosine_accuracy@3
98
+ value: 0.19600725952813067
99
+ name: Cosine Accuracy@3
100
+ - type: cosine_accuracy@5
101
+ value: 0.3339382940108893
102
+ name: Cosine Accuracy@5
103
+ - type: cosine_accuracy@10
104
+ value: 0.5535390199637024
105
+ name: Cosine Accuracy@10
106
+ - type: cosine_precision@1
107
+ value: 0.02722323049001815
108
+ name: Cosine Precision@1
109
+ - type: cosine_precision@3
110
+ value: 0.06533575317604355
111
+ name: Cosine Precision@3
112
+ - type: cosine_precision@5
113
+ value: 0.06678765880217785
114
+ name: Cosine Precision@5
115
+ - type: cosine_precision@10
116
+ value: 0.05535390199637023
117
+ name: Cosine Precision@10
118
+ - type: cosine_recall@1
119
+ value: 0.02722323049001815
120
+ name: Cosine Recall@1
121
+ - type: cosine_recall@3
122
+ value: 0.19600725952813067
123
+ name: Cosine Recall@3
124
+ - type: cosine_recall@5
125
+ value: 0.3339382940108893
126
+ name: Cosine Recall@5
127
+ - type: cosine_recall@10
128
+ value: 0.5535390199637024
129
+ name: Cosine Recall@10
130
+ - type: cosine_ndcg@10
131
+ value: 0.26072465632924774
132
+ name: Cosine Ndcg@10
133
+ - type: cosine_mrr@10
134
+ value: 0.17108504018667361
135
+ name: Cosine Mrr@10
136
+ - type: cosine_map@100
137
+ value: 0.18770082835080207
138
+ name: Cosine Map@100
139
+ - task:
140
+ type: information-retrieval
141
+ name: Information Retrieval
142
+ dataset:
143
+ name: dim 512
144
+ type: dim_512
145
+ metrics:
146
+ - type: cosine_accuracy@1
147
+ value: 0.02722323049001815
148
+ name: Cosine Accuracy@1
149
+ - type: cosine_accuracy@3
150
+ value: 0.19600725952813067
151
+ name: Cosine Accuracy@3
152
+ - type: cosine_accuracy@5
153
+ value: 0.32304900181488205
154
+ name: Cosine Accuracy@5
155
+ - type: cosine_accuracy@10
156
+ value: 0.5626134301270418
157
+ name: Cosine Accuracy@10
158
+ - type: cosine_precision@1
159
+ value: 0.02722323049001815
160
+ name: Cosine Precision@1
161
+ - type: cosine_precision@3
162
+ value: 0.06533575317604355
163
+ name: Cosine Precision@3
164
+ - type: cosine_precision@5
165
+ value: 0.06460980036297641
166
+ name: Cosine Precision@5
167
+ - type: cosine_precision@10
168
+ value: 0.056261343012704176
169
+ name: Cosine Precision@10
170
+ - type: cosine_recall@1
171
+ value: 0.02722323049001815
172
+ name: Cosine Recall@1
173
+ - type: cosine_recall@3
174
+ value: 0.19600725952813067
175
+ name: Cosine Recall@3
176
+ - type: cosine_recall@5
177
+ value: 0.32304900181488205
178
+ name: Cosine Recall@5
179
+ - type: cosine_recall@10
180
+ value: 0.5626134301270418
181
+ name: Cosine Recall@10
182
+ - type: cosine_ndcg@10
183
+ value: 0.2619272501758391
184
+ name: Cosine Ndcg@10
185
+ - type: cosine_mrr@10
186
+ value: 0.17047791893526926
187
+ name: Cosine Mrr@10
188
+ - type: cosine_map@100
189
+ value: 0.18609576776317005
190
+ name: Cosine Map@100
191
+ - task:
192
+ type: information-retrieval
193
+ name: Information Retrieval
194
+ dataset:
195
+ name: dim 256
196
+ type: dim_256
197
+ metrics:
198
+ - type: cosine_accuracy@1
199
+ value: 0.021778584392014518
200
+ name: Cosine Accuracy@1
201
+ - type: cosine_accuracy@3
202
+ value: 0.1851179673321234
203
+ name: Cosine Accuracy@3
204
+ - type: cosine_accuracy@5
205
+ value: 0.3194192377495463
206
+ name: Cosine Accuracy@5
207
+ - type: cosine_accuracy@10
208
+ value: 0.5571687840290381
209
+ name: Cosine Accuracy@10
210
+ - type: cosine_precision@1
211
+ value: 0.021778584392014518
212
+ name: Cosine Precision@1
213
+ - type: cosine_precision@3
214
+ value: 0.06170598911070781
215
+ name: Cosine Precision@3
216
+ - type: cosine_precision@5
217
+ value: 0.06388384754990926
218
+ name: Cosine Precision@5
219
+ - type: cosine_precision@10
220
+ value: 0.05571687840290381
221
+ name: Cosine Precision@10
222
+ - type: cosine_recall@1
223
+ value: 0.021778584392014518
224
+ name: Cosine Recall@1
225
+ - type: cosine_recall@3
226
+ value: 0.1851179673321234
227
+ name: Cosine Recall@3
228
+ - type: cosine_recall@5
229
+ value: 0.3194192377495463
230
+ name: Cosine Recall@5
231
+ - type: cosine_recall@10
232
+ value: 0.5571687840290381
233
+ name: Cosine Recall@10
234
+ - type: cosine_ndcg@10
235
+ value: 0.25612468011654316
236
+ name: Cosine Ndcg@10
237
+ - type: cosine_mrr@10
238
+ value: 0.16426122778209898
239
+ name: Cosine Mrr@10
240
+ - type: cosine_map@100
241
+ value: 0.18028375195557364
242
+ name: Cosine Map@100
243
+ - task:
244
+ type: information-retrieval
245
+ name: Information Retrieval
246
+ dataset:
247
+ name: dim 128
248
+ type: dim_128
249
+ metrics:
250
+ - type: cosine_accuracy@1
251
+ value: 0.023593466424682397
252
+ name: Cosine Accuracy@1
253
+ - type: cosine_accuracy@3
254
+ value: 0.1869328493647913
255
+ name: Cosine Accuracy@3
256
+ - type: cosine_accuracy@5
257
+ value: 0.32304900181488205
258
+ name: Cosine Accuracy@5
259
+ - type: cosine_accuracy@10
260
+ value: 0.542649727767695
261
+ name: Cosine Accuracy@10
262
+ - type: cosine_precision@1
263
+ value: 0.023593466424682397
264
+ name: Cosine Precision@1
265
+ - type: cosine_precision@3
266
+ value: 0.06231094978826376
267
+ name: Cosine Precision@3
268
+ - type: cosine_precision@5
269
+ value: 0.06460980036297642
270
+ name: Cosine Precision@5
271
+ - type: cosine_precision@10
272
+ value: 0.054264972776769504
273
+ name: Cosine Precision@10
274
+ - type: cosine_recall@1
275
+ value: 0.023593466424682397
276
+ name: Cosine Recall@1
277
+ - type: cosine_recall@3
278
+ value: 0.1869328493647913
279
+ name: Cosine Recall@3
280
+ - type: cosine_recall@5
281
+ value: 0.32304900181488205
282
+ name: Cosine Recall@5
283
+ - type: cosine_recall@10
284
+ value: 0.542649727767695
285
+ name: Cosine Recall@10
286
+ - type: cosine_ndcg@10
287
+ value: 0.2520700332274149
288
+ name: Cosine Ndcg@10
289
+ - type: cosine_mrr@10
290
+ value: 0.16319390430098243
291
+ name: Cosine Mrr@10
292
+ - type: cosine_map@100
293
+ value: 0.17991374973589885
294
+ name: Cosine Map@100
295
+ - task:
296
+ type: information-retrieval
297
+ name: Information Retrieval
298
+ dataset:
299
+ name: dim 64
300
+ type: dim_64
301
+ metrics:
302
+ - type: cosine_accuracy@1
303
+ value: 0.025408348457350273
304
+ name: Cosine Accuracy@1
305
+ - type: cosine_accuracy@3
306
+ value: 0.18330308529945555
307
+ name: Cosine Accuracy@3
308
+ - type: cosine_accuracy@5
309
+ value: 0.3121597096188748
310
+ name: Cosine Accuracy@5
311
+ - type: cosine_accuracy@10
312
+ value: 0.5190562613430127
313
+ name: Cosine Accuracy@10
314
+ - type: cosine_precision@1
315
+ value: 0.025408348457350273
316
+ name: Cosine Precision@1
317
+ - type: cosine_precision@3
318
+ value: 0.06110102843315183
319
+ name: Cosine Precision@3
320
+ - type: cosine_precision@5
321
+ value: 0.062431941923774964
322
+ name: Cosine Precision@5
323
+ - type: cosine_precision@10
324
+ value: 0.051905626134301275
325
+ name: Cosine Precision@10
326
+ - type: cosine_recall@1
327
+ value: 0.025408348457350273
328
+ name: Cosine Recall@1
329
+ - type: cosine_recall@3
330
+ value: 0.18330308529945555
331
+ name: Cosine Recall@3
332
+ - type: cosine_recall@5
333
+ value: 0.3121597096188748
334
+ name: Cosine Recall@5
335
+ - type: cosine_recall@10
336
+ value: 0.5190562613430127
337
+ name: Cosine Recall@10
338
+ - type: cosine_ndcg@10
339
+ value: 0.2452921508851895
340
+ name: Cosine Ndcg@10
341
+ - type: cosine_mrr@10
342
+ value: 0.16116512545732162
343
+ name: Cosine Mrr@10
344
+ - type: cosine_map@100
345
+ value: 0.17937881548234963
346
+ name: Cosine Map@100
347
+ ---
348
+
349
+ # SentenceTransformer based on aari1995/German_Semantic_V3
350
+
351
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [aari1995/German_Semantic_V3](https://huggingface.co/aari1995/German_Semantic_V3). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
352
+
353
+ ## Model Details
354
+
355
+ ### Model Description
356
+ - **Model Type:** Sentence Transformer
357
+ - **Base model:** [aari1995/German_Semantic_V3](https://huggingface.co/aari1995/German_Semantic_V3) <!-- at revision 11b76103bdf441513d7fc14fefae28c1064d3d04 -->
358
+ - **Maximum Sequence Length:** 1024 tokens
359
+ - **Output Dimensionality:** 1024 tokens
360
+ - **Similarity Function:** Cosine Similarity
361
+ <!-- - **Training Dataset:** Unknown -->
362
+ <!-- - **Language:** Unknown -->
363
+ <!-- - **License:** Unknown -->
364
+
365
+ ### Model Sources
366
+
367
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
368
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
369
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
370
+
371
+ ### Full Model Architecture
372
+
373
+ ```
374
+ SentenceTransformer(
375
+ (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False}) with Transformer model: JinaBertModel
376
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
377
+ )
378
+ ```
379
+
380
+ ## Usage
381
+
382
+ ### Direct Usage (Sentence Transformers)
383
+
384
+ First install the Sentence Transformers library:
385
+
386
+ ```bash
387
+ pip install -U sentence-transformers
388
+ ```
389
+
390
+ Then you can load this model and run inference.
391
+ ```python
392
+ from sentence_transformers import SentenceTransformer
393
+
394
+ # Download from the 🤗 Hub
395
+ model = SentenceTransformer("akot/german-semantic-bmf-matryoshka")
396
+ # Run inference
397
+ sentences = [
398
+ '67 Abwandlung des Beispiels 1 in Rn. 66: A erhält zudem zwei Kinderzulagen für seine in den Jahren 2004 und 2005 geborenen Kinder. Beitragspflichtige Einnahmen 53.000 € 4 % 2.120 € höchstens 2.100 € anzusetzen 2.100 € abzüglich Zulage 175 € Mindesteigenbeitrag (§ 86 Abs. 1 Satz 2 EStG) 1.925 € Sockelbetrag (§ 86 Abs. 1 Satz 4 EStG) 60 € maßgebend (§ 86 Abs. 1 Satz 5 EStG) 1.925 € Die von A geleisteten Beiträge übersteigen den Mindesteigenbeitrag. Die Zulage wird nicht gekürzt.',
399
+ 'Wird die Zulage für A gekürzt, wenn die Beiträge den Mindesteigenbeitrag übersteigen?',
400
+ 'Wie erfolgt die Besteuerung bei der ausgleichsberechtigten Person nach einer externen Teilung?',
401
+ ]
402
+ embeddings = model.encode(sentences)
403
+ print(embeddings.shape)
404
+ # [3, 1024]
405
+
406
+ # Get the similarity scores for the embeddings
407
+ similarities = model.similarity(embeddings, embeddings)
408
+ print(similarities.shape)
409
+ # [3, 3]
410
+ ```
411
+
412
+ <!--
413
+ ### Direct Usage (Transformers)
414
+
415
+ <details><summary>Click to see the direct usage in Transformers</summary>
416
+
417
+ </details>
418
+ -->
419
+
420
+ <!--
421
+ ### Downstream Usage (Sentence Transformers)
422
+
423
+ You can finetune this model on your own dataset.
424
+
425
+ <details><summary>Click to expand</summary>
426
+
427
+ </details>
428
+ -->
429
+
430
+ <!--
431
+ ### Out-of-Scope Use
432
+
433
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
434
+ -->
435
+
436
+ ## Evaluation
437
+
438
+ ### Metrics
439
+
440
+ #### Information Retrieval
441
+ * Dataset: `dim_768`
442
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
443
+
444
+ | Metric | Value |
445
+ |:--------------------|:-----------|
446
+ | cosine_accuracy@1 | 0.0272 |
447
+ | cosine_accuracy@3 | 0.196 |
448
+ | cosine_accuracy@5 | 0.3339 |
449
+ | cosine_accuracy@10 | 0.5535 |
450
+ | cosine_precision@1 | 0.0272 |
451
+ | cosine_precision@3 | 0.0653 |
452
+ | cosine_precision@5 | 0.0668 |
453
+ | cosine_precision@10 | 0.0554 |
454
+ | cosine_recall@1 | 0.0272 |
455
+ | cosine_recall@3 | 0.196 |
456
+ | cosine_recall@5 | 0.3339 |
457
+ | cosine_recall@10 | 0.5535 |
458
+ | cosine_ndcg@10 | 0.2607 |
459
+ | cosine_mrr@10 | 0.1711 |
460
+ | **cosine_map@100** | **0.1877** |
461
+
462
+ #### Information Retrieval
463
+ * Dataset: `dim_512`
464
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
465
+
466
+ | Metric | Value |
467
+ |:--------------------|:-----------|
468
+ | cosine_accuracy@1 | 0.0272 |
469
+ | cosine_accuracy@3 | 0.196 |
470
+ | cosine_accuracy@5 | 0.323 |
471
+ | cosine_accuracy@10 | 0.5626 |
472
+ | cosine_precision@1 | 0.0272 |
473
+ | cosine_precision@3 | 0.0653 |
474
+ | cosine_precision@5 | 0.0646 |
475
+ | cosine_precision@10 | 0.0563 |
476
+ | cosine_recall@1 | 0.0272 |
477
+ | cosine_recall@3 | 0.196 |
478
+ | cosine_recall@5 | 0.323 |
479
+ | cosine_recall@10 | 0.5626 |
480
+ | cosine_ndcg@10 | 0.2619 |
481
+ | cosine_mrr@10 | 0.1705 |
482
+ | **cosine_map@100** | **0.1861** |
483
+
484
+ #### Information Retrieval
485
+ * Dataset: `dim_256`
486
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
487
+
488
+ | Metric | Value |
489
+ |:--------------------|:-----------|
490
+ | cosine_accuracy@1 | 0.0218 |
491
+ | cosine_accuracy@3 | 0.1851 |
492
+ | cosine_accuracy@5 | 0.3194 |
493
+ | cosine_accuracy@10 | 0.5572 |
494
+ | cosine_precision@1 | 0.0218 |
495
+ | cosine_precision@3 | 0.0617 |
496
+ | cosine_precision@5 | 0.0639 |
497
+ | cosine_precision@10 | 0.0557 |
498
+ | cosine_recall@1 | 0.0218 |
499
+ | cosine_recall@3 | 0.1851 |
500
+ | cosine_recall@5 | 0.3194 |
501
+ | cosine_recall@10 | 0.5572 |
502
+ | cosine_ndcg@10 | 0.2561 |
503
+ | cosine_mrr@10 | 0.1643 |
504
+ | **cosine_map@100** | **0.1803** |
505
+
506
+ #### Information Retrieval
507
+ * Dataset: `dim_128`
508
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
509
+
510
+ | Metric | Value |
511
+ |:--------------------|:-----------|
512
+ | cosine_accuracy@1 | 0.0236 |
513
+ | cosine_accuracy@3 | 0.1869 |
514
+ | cosine_accuracy@5 | 0.323 |
515
+ | cosine_accuracy@10 | 0.5426 |
516
+ | cosine_precision@1 | 0.0236 |
517
+ | cosine_precision@3 | 0.0623 |
518
+ | cosine_precision@5 | 0.0646 |
519
+ | cosine_precision@10 | 0.0543 |
520
+ | cosine_recall@1 | 0.0236 |
521
+ | cosine_recall@3 | 0.1869 |
522
+ | cosine_recall@5 | 0.323 |
523
+ | cosine_recall@10 | 0.5426 |
524
+ | cosine_ndcg@10 | 0.2521 |
525
+ | cosine_mrr@10 | 0.1632 |
526
+ | **cosine_map@100** | **0.1799** |
527
+
528
+ #### Information Retrieval
529
+ * Dataset: `dim_64`
530
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
531
+
532
+ | Metric | Value |
533
+ |:--------------------|:-----------|
534
+ | cosine_accuracy@1 | 0.0254 |
535
+ | cosine_accuracy@3 | 0.1833 |
536
+ | cosine_accuracy@5 | 0.3122 |
537
+ | cosine_accuracy@10 | 0.5191 |
538
+ | cosine_precision@1 | 0.0254 |
539
+ | cosine_precision@3 | 0.0611 |
540
+ | cosine_precision@5 | 0.0624 |
541
+ | cosine_precision@10 | 0.0519 |
542
+ | cosine_recall@1 | 0.0254 |
543
+ | cosine_recall@3 | 0.1833 |
544
+ | cosine_recall@5 | 0.3122 |
545
+ | cosine_recall@10 | 0.5191 |
546
+ | cosine_ndcg@10 | 0.2453 |
547
+ | cosine_mrr@10 | 0.1612 |
548
+ | **cosine_map@100** | **0.1794** |
549
+
550
+ <!--
551
+ ## Bias, Risks and Limitations
552
+
553
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
554
+ -->
555
+
556
+ <!--
557
+ ### Recommendations
558
+
559
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
560
+ -->
561
+
562
+ ## Training Details
563
+
564
+ ### Training Dataset
565
+
566
+ #### Unnamed Dataset
567
+
568
+
569
+ * Size: 4,957 training samples
570
+ * Columns: <code>positive</code> and <code>anchor</code>
571
+ * Approximate statistics based on the first 1000 samples:
572
+ | | positive | anchor |
573
+ |:--------|:-------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
574
+ | type | string | string |
575
+ | details | <ul><li>min: 5 tokens</li><li>mean: 158.11 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 21.11 tokens</li><li>max: 47 tokens</li></ul> |
576
+ * Samples:
577
+ | positive | anchor |
578
+ |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------|
579
+ | <code>134 Eine Rückzahlungsverpflichtung besteht nicht für den Teil der Zulagen, der auf nach § 1 Abs. 1 Nr. 2 AltZertG angespartes gefördertes Altersvorsorgevermögen entfällt, wenn es in Form einer Hinterbliebenenrente an die dort genannten Hinterbliebenen ausgezahlt wird. Dies gilt auch für den entsprechenden Teil der Steuerermäßigung.</code> | <code>Muss man Zulagen zurückzahlen, wenn das Altersvorsorgevermögen als Hinterbliebenenrente ausgezahlt wird?</code> |
580
+ | <code>140 Beendet der Zulageberechtigte vor der vollständigen Rückzahlung des AltersvorsorgeEigenheimbetrags die Nutzung zu eigenen Wohnzwecken, wird er so behandelt, als habe er den noch nicht zurückgezahlten Betrag schädlich verwendet. Die auf den noch ausstehenden Rückzahlungsbetrag entfallenden Zulagen sowie die nach § 10a Abs. 4 EStG gesondert festgestellten Steuerermäßigungen sind zurückzuzahlen (§ 92a Abs. 3 EStG). Die im noch ausstehenden Rückzahlungsbetrag enthaltenen Zuwächse (z.B. Zinserträge und Kursgewinne) Seite 41 sind als sonstige Einkünfte zu versteuern (§ 22 Nr. 5 Satz 5 Halbsatz 1 EStG). Außerdem hat der Zulageberechtigte den Vorteil zu versteuern, der sich aus der zinslosen Nutzung des noch nicht zurückgezahlten Betrags ergibt. Zugrunde gelegt wird hierbei eine Verzinsung von 5 % (Zins und Zinseszins) für jedes volle Kalenderjahr der Nutzung (§ 22 Nr. 5 Satz 5 Halbsatz 2 EStG). Diese Folgen treten nicht ein, wenn er den noch nicht zurückgezahlten Betrag in ein Folgeobjekt investiert (§ 92a Abs. 4 Satz 3 Nr. 1 EStG) oder zugunsten eines auf seinen Namen lautenden zertifizierten Altersvorsorgevertrags einzahlt (§ 92a Abs. 4 Satz 3 Nr. 2 EStG).</code> | <code>Was geschieht steuerlich, wenn der AltersvorsorgeEigenheimbetrag nicht vollständig zurückgezahlt wird und die Immobilie nicht mehr selbst genutzt wird?</code> |
581
+ | <code>144 Die als Einkünfte nach § 22 Nr. 5 Satz 3 EStG i.V.m. § 22 Nr. 5 Satz 2 EStG zu besteuernden Beträge muss der Anbieter gem. § 94 Abs. 1 Satz 4 EStG dem Zulageberechtigten bescheinigen und im Wege des Rentenbezugsmitteilungsverfahrens (§ 22a EStG) mitteilen. Ergeben sich insoweit steuerpflichtige Einkünfte nach § 22 Nr. 5 Satz 3 EStG für einen anderen Leistungsempfänger (z. B. Erben), ist für diesen eine entsprechende Rentenbezugsmitteilung der ZfA zu übermitteln.</code> | <code>Was muss im Falle eines anderen Leistungsempfängers, wie Erben, hinsichtlich der Rentenbezugsmitteilung getan werden?</code> |
582
+ * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
583
+ ```json
584
+ {
585
+ "loss": "MultipleNegativesRankingLoss",
586
+ "matryoshka_dims": [
587
+ 768,
588
+ 512,
589
+ 256,
590
+ 128,
591
+ 64
592
+ ],
593
+ "matryoshka_weights": [
594
+ 1,
595
+ 1,
596
+ 1,
597
+ 1,
598
+ 1
599
+ ],
600
+ "n_dims_per_step": -1
601
+ }
602
+ ```
603
+
604
+ ### Training Hyperparameters
605
+ #### Non-Default Hyperparameters
606
+
607
+ - `eval_strategy`: epoch
608
+ - `per_device_train_batch_size`: 16
609
+ - `per_device_eval_batch_size`: 16
610
+ - `gradient_accumulation_steps`: 16
611
+ - `learning_rate`: 2e-05
612
+ - `num_train_epochs`: 10
613
+ - `lr_scheduler_type`: cosine
614
+ - `warmup_ratio`: 0.1
615
+ - `bf16`: True
616
+ - `tf32`: True
617
+ - `load_best_model_at_end`: True
618
+ - `optim`: adamw_torch_fused
619
+ - `batch_sampler`: no_duplicates
620
+
621
+ #### All Hyperparameters
622
+ <details><summary>Click to expand</summary>
623
+
624
+ - `overwrite_output_dir`: False
625
+ - `do_predict`: False
626
+ - `eval_strategy`: epoch
627
+ - `prediction_loss_only`: True
628
+ - `per_device_train_batch_size`: 16
629
+ - `per_device_eval_batch_size`: 16
630
+ - `per_gpu_train_batch_size`: None
631
+ - `per_gpu_eval_batch_size`: None
632
+ - `gradient_accumulation_steps`: 16
633
+ - `eval_accumulation_steps`: None
634
+ - `learning_rate`: 2e-05
635
+ - `weight_decay`: 0.0
636
+ - `adam_beta1`: 0.9
637
+ - `adam_beta2`: 0.999
638
+ - `adam_epsilon`: 1e-08
639
+ - `max_grad_norm`: 1.0
640
+ - `num_train_epochs`: 10
641
+ - `max_steps`: -1
642
+ - `lr_scheduler_type`: cosine
643
+ - `lr_scheduler_kwargs`: {}
644
+ - `warmup_ratio`: 0.1
645
+ - `warmup_steps`: 0
646
+ - `log_level`: passive
647
+ - `log_level_replica`: warning
648
+ - `log_on_each_node`: True
649
+ - `logging_nan_inf_filter`: True
650
+ - `save_safetensors`: True
651
+ - `save_on_each_node`: False
652
+ - `save_only_model`: False
653
+ - `restore_callback_states_from_checkpoint`: False
654
+ - `no_cuda`: False
655
+ - `use_cpu`: False
656
+ - `use_mps_device`: False
657
+ - `seed`: 42
658
+ - `data_seed`: None
659
+ - `jit_mode_eval`: False
660
+ - `use_ipex`: False
661
+ - `bf16`: True
662
+ - `fp16`: False
663
+ - `fp16_opt_level`: O1
664
+ - `half_precision_backend`: auto
665
+ - `bf16_full_eval`: False
666
+ - `fp16_full_eval`: False
667
+ - `tf32`: True
668
+ - `local_rank`: 0
669
+ - `ddp_backend`: None
670
+ - `tpu_num_cores`: None
671
+ - `tpu_metrics_debug`: False
672
+ - `debug`: []
673
+ - `dataloader_drop_last`: False
674
+ - `dataloader_num_workers`: 0
675
+ - `dataloader_prefetch_factor`: None
676
+ - `past_index`: -1
677
+ - `disable_tqdm`: False
678
+ - `remove_unused_columns`: True
679
+ - `label_names`: None
680
+ - `load_best_model_at_end`: True
681
+ - `ignore_data_skip`: False
682
+ - `fsdp`: []
683
+ - `fsdp_min_num_params`: 0
684
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
685
+ - `fsdp_transformer_layer_cls_to_wrap`: None
686
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
687
+ - `deepspeed`: None
688
+ - `label_smoothing_factor`: 0.0
689
+ - `optim`: adamw_torch_fused
690
+ - `optim_args`: None
691
+ - `adafactor`: False
692
+ - `group_by_length`: False
693
+ - `length_column_name`: length
694
+ - `ddp_find_unused_parameters`: None
695
+ - `ddp_bucket_cap_mb`: None
696
+ - `ddp_broadcast_buffers`: False
697
+ - `dataloader_pin_memory`: True
698
+ - `dataloader_persistent_workers`: False
699
+ - `skip_memory_metrics`: True
700
+ - `use_legacy_prediction_loop`: False
701
+ - `push_to_hub`: False
702
+ - `resume_from_checkpoint`: None
703
+ - `hub_model_id`: None
704
+ - `hub_strategy`: every_save
705
+ - `hub_private_repo`: False
706
+ - `hub_always_push`: False
707
+ - `gradient_checkpointing`: False
708
+ - `gradient_checkpointing_kwargs`: None
709
+ - `include_inputs_for_metrics`: False
710
+ - `eval_do_concat_batches`: True
711
+ - `fp16_backend`: auto
712
+ - `push_to_hub_model_id`: None
713
+ - `push_to_hub_organization`: None
714
+ - `mp_parameters`:
715
+ - `auto_find_batch_size`: False
716
+ - `full_determinism`: False
717
+ - `torchdynamo`: None
718
+ - `ray_scope`: last
719
+ - `ddp_timeout`: 1800
720
+ - `torch_compile`: False
721
+ - `torch_compile_backend`: None
722
+ - `torch_compile_mode`: None
723
+ - `dispatch_batches`: None
724
+ - `split_batches`: None
725
+ - `include_tokens_per_second`: False
726
+ - `include_num_input_tokens_seen`: False
727
+ - `neftune_noise_alpha`: None
728
+ - `optim_target_modules`: None
729
+ - `batch_eval_metrics`: False
730
+ - `batch_sampler`: no_duplicates
731
+ - `multi_dataset_batch_sampler`: proportional
732
+
733
+ </details>
734
+
735
+ ### Training Logs
736
+ | Epoch | Step | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
737
+ |:----------:|:-------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
738
+ | 0.5161 | 10 | 7.3654 | - | - | - | - | - |
739
+ | 0.9806 | 19 | - | 0.1293 | 0.1314 | 0.1379 | 0.1080 | 0.1391 |
740
+ | 1.0323 | 20 | 4.6797 | - | - | - | - | - |
741
+ | 1.5484 | 30 | 2.7983 | - | - | - | - | - |
742
+ | 1.9613 | 38 | - | 0.1607 | 0.1703 | 0.1697 | 0.1546 | 0.1770 |
743
+ | 2.0645 | 40 | 2.0567 | - | - | - | - | - |
744
+ | 2.5806 | 50 | 1.4778 | - | - | - | - | - |
745
+ | 2.9935 | 58 | - | 0.1636 | 0.1734 | 0.1761 | 0.1586 | 0.1744 |
746
+ | 3.0968 | 60 | 1.2677 | - | - | - | - | - |
747
+ | 3.6129 | 70 | 0.9943 | - | - | - | - | - |
748
+ | 3.9742 | 77 | - | 0.1728 | 0.1783 | 0.1805 | 0.1741 | 0.1825 |
749
+ | 4.1290 | 80 | 0.7914 | - | - | - | - | - |
750
+ | 4.6452 | 90 | 0.7161 | - | - | - | - | - |
751
+ | 4.9548 | 96 | - | 0.1756 | 0.1780 | 0.1817 | 0.1702 | 0.1836 |
752
+ | 5.1613 | 100 | 0.582 | - | - | - | - | - |
753
+ | 5.6774 | 110 | 0.5094 | - | - | - | - | - |
754
+ | 5.9871 | 116 | - | 0.1769 | 0.1804 | 0.1793 | 0.1735 | 0.1847 |
755
+ | 6.1935 | 120 | 0.4562 | - | - | - | - | - |
756
+ | 6.7097 | 130 | 0.4102 | - | - | - | - | - |
757
+ | 6.9677 | 135 | - | 0.1790 | 0.1810 | 0.1857 | 0.1756 | 0.1897 |
758
+ | 7.2258 | 140 | 0.393 | - | - | - | - | - |
759
+ | 7.7419 | 150 | 0.3678 | - | - | - | - | - |
760
+ | 8.0 | 155 | - | 0.1789 | 0.1825 | 0.1828 | 0.1759 | 0.1863 |
761
+ | 8.2581 | 160 | 0.3357 | - | - | - | - | - |
762
+ | 8.7742 | 170 | 0.344 | - | - | - | - | - |
763
+ | **8.9806** | **174** | **-** | **0.181** | **0.1883** | **0.191** | **0.1796** | **0.1928** |
764
+ | 9.2903 | 180 | 0.3421 | - | - | - | - | - |
765
+ | 9.8065 | 190 | 0.3062 | 0.1799 | 0.1803 | 0.1861 | 0.1794 | 0.1877 |
766
+
767
+ * The bold row denotes the saved checkpoint.
768
+
769
+ ### Framework Versions
770
+ - Python: 3.11.4
771
+ - Sentence Transformers: 3.0.1
772
+ - Transformers: 4.41.2
773
+ - PyTorch: 2.1.2+cu121
774
+ - Accelerate: 0.33.0
775
+ - Datasets: 2.19.1
776
+ - Tokenizers: 0.19.1
777
+
778
+ ## Citation
779
+
780
+ ### BibTeX
781
+
782
+ #### Sentence Transformers
783
+ ```bibtex
784
+ @inproceedings{reimers-2019-sentence-bert,
785
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
786
+ author = "Reimers, Nils and Gurevych, Iryna",
787
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
788
+ month = "11",
789
+ year = "2019",
790
+ publisher = "Association for Computational Linguistics",
791
+ url = "https://arxiv.org/abs/1908.10084",
792
+ }
793
+ ```
794
+
795
+ #### MatryoshkaLoss
796
+ ```bibtex
797
+ @misc{kusupati2024matryoshka,
798
+ title={Matryoshka Representation Learning},
799
+ author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
800
+ year={2024},
801
+ eprint={2205.13147},
802
+ archivePrefix={arXiv},
803
+ primaryClass={cs.LG}
804
+ }
805
+ ```
806
+
807
+ #### MultipleNegativesRankingLoss
808
+ ```bibtex
809
+ @misc{henderson2017efficient,
810
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
811
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
812
+ year={2017},
813
+ eprint={1705.00652},
814
+ archivePrefix={arXiv},
815
+ primaryClass={cs.CL}
816
+ }
817
+ ```
818
+
819
+ <!--
820
+ ## Glossary
821
+
822
+ *Clearly define terms in order to be accessible across audiences.*
823
+ -->
824
+
825
+ <!--
826
+ ## Model Card Authors
827
+
828
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
829
+ -->
830
+
831
+ <!--
832
+ ## Model Card Contact
833
+
834
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
835
+ -->
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aari1995/German_Semantic_V3",
3
+ "architectures": [
4
+ "JinaBertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "attn_implementation": null,
8
+ "auto_map": {
9
+ "AutoConfig": "aari1995/German_Semantic_V3--configuration_bert.JinaBertConfig",
10
+ "AutoModel": "aari1995/German_Semantic_V3--modeling_bert.JinaBertModel",
11
+ "AutoModelForMaskedLM": "aari1995/German_Semantic_V3--modeling_bert.JinaBertForMaskedLM",
12
+ "AutoModelForSequenceClassification": "aari1995/German_Semantic_V3--modeling_bert.JinaBertForSequenceClassification"
13
+ },
14
+ "classifier_dropout": null,
15
+ "emb_pooler": null,
16
+ "feed_forward_type": "original",
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 8192,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "alibi",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.41.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 31102
34
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.1.2+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4acbaf7357100d3c839f4edd110e93c730490ae1c74d7ce23c8862239c193d
3
+ size 1340890848
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 1024,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "101": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "102": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "103": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 9999999999,
50
+ "max_length": 1000,
51
+ "model_max_length": 8192,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": false,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff