Hugging Face's logo

Mollel
/
swahili-serengeti-E250-nli-matryoshka

Sentence Similarity
sentence-transformers
Safetensors
electra
feature-extraction
Generated from Trainer
dataset_size:557850
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results
Model card Files
xet
Community
Mollel commited on
Commit
4ee5db8
·
verified ·
1 Parent(s): ac14fa1

Add new SentenceTransformer model.

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +811 -0
  3. config.json +30 -0
  4. config_sentence_transformers.json +10 -0
  5. model.safetensors +3 -0
  6. modules.json +14 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +37 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +58 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
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 +1,811 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: []
3
+ library_name: sentence-transformers
4
+ tags:
5
+ - sentence-transformers
6
+ - sentence-similarity
7
+ - feature-extraction
8
+ - generated_from_trainer
9
+ - dataset_size:557850
10
+ - loss:MatryoshkaLoss
11
+ - loss:MultipleNegativesRankingLoss
12
+ base_model: UBC-NLP/serengeti-E250
13
+ datasets: []
14
+ metrics:
15
+ - pearson_cosine
16
+ - spearman_cosine
17
+ - pearson_manhattan
18
+ - spearman_manhattan
19
+ - pearson_euclidean
20
+ - spearman_euclidean
21
+ - pearson_dot
22
+ - spearman_dot
23
+ - pearson_max
24
+ - spearman_max
25
+ widget:
26
+ - source_sentence: Mwanamume aliyepangwa vizuri anasimama kwa mguu mmoja karibu na
27
+ pwani safi ya bahari.
28
+ sentences:
29
+ - mtu anacheka wakati wa kufua nguo
30
+ - Mwanamume fulani yuko nje karibu na ufuo wa bahari.
31
+ - Mwanamume fulani ameketi kwenye sofa yake.
32
+ - source_sentence: Mwanamume mwenye ngozi nyeusi akivuta sigareti karibu na chombo
33
+ cha taka cha kijani.
34
+ sentences:
35
+ - Karibu na chombo cha taka mwanamume huyo alisimama na kuvuta sigareti
36
+ - Kitanda ni chafu.
37
+ - Alipokuwa kwenye dimbwi la kuogelea mvulana huyo mwenye ugonjwa wa albino alijihadhari
38
+ na jua kupita kiasi
39
+ - source_sentence: Mwanamume kijana mwenye nywele nyekundu anaketi ukutani akisoma
40
+ gazeti huku mwanamke na msichana mchanga wakipita.
41
+ sentences:
42
+ - Mwanamume aliyevalia shati la bluu amegonga ukuta kando ya barabara na gari la
43
+ bluu na gari nyekundu lenye maji nyuma.
44
+ - Mwanamume mchanga anatazama gazeti huku wanawake wawili wakipita karibu naye.
45
+ - Mwanamume huyo mchanga analala huku Mama akimwongoza binti yake kwenye bustani.
46
+ - source_sentence: Wasichana wako nje.
47
+ sentences:
48
+ - Wasichana wawili wakisafiri kwenye sehemu ya kusisimua.
49
+ - Kuna watu watatu wakiongoza gari linaloweza kugeuzwa-geuzwa wakipita watu wengine.
50
+ - Wasichana watatu wamesimama pamoja katika chumba, mmoja anasikiliza, mwingine
51
+ anaandika ukutani na wa tatu anaongea nao.
52
+ - source_sentence: Mwanamume aliyevalia koti la bluu la kuzuia upepo, amelala uso
53
+ chini kwenye benchi ya bustani, akiwa na chupa ya pombe iliyofungwa kwenye mojawapo
54
+ ya miguu ya benchi.
55
+ sentences:
56
+ - Mwanamume amelala uso chini kwenye benchi ya bustani.
57
+ - Mwanamke anaunganisha uzi katika mipira kando ya rundo la mipira
58
+ - Mwanamume fulani anacheza dansi kwenye klabu hiyo akifungua chupa.
59
+ pipeline_tag: sentence-similarity
60
+ model-index:
61
+ - name: SentenceTransformer based on UBC-NLP/serengeti-E250
62
+ results:
63
+ - task:
64
+ type: semantic-similarity
65
+ name: Semantic Similarity
66
+ dataset:
67
+ name: sts test 768
68
+ type: sts-test-768
69
+ metrics:
70
+ - type: pearson_cosine
71
+ value: 0.7113368462970326
72
+ name: Pearson Cosine
73
+ - type: spearman_cosine
74
+ value: 0.706531149090894
75
+ name: Spearman Cosine
76
+ - type: pearson_manhattan
77
+ value: 0.7134349154531519
78
+ name: Pearson Manhattan
79
+ - type: spearman_manhattan
80
+ value: 0.7023005843725415
81
+ name: Spearman Manhattan
82
+ - type: pearson_euclidean
83
+ value: 0.7137962920501839
84
+ name: Pearson Euclidean
85
+ - type: spearman_euclidean
86
+ value: 0.7020941994285994
87
+ name: Spearman Euclidean
88
+ - type: pearson_dot
89
+ value: 0.3920803758314358
90
+ name: Pearson Dot
91
+ - type: spearman_dot
92
+ value: 0.3601086266312748
93
+ name: Spearman Dot
94
+ - type: pearson_max
95
+ value: 0.7137962920501839
96
+ name: Pearson Max
97
+ - type: spearman_max
98
+ value: 0.706531149090894
99
+ name: Spearman Max
100
+ - task:
101
+ type: semantic-similarity
102
+ name: Semantic Similarity
103
+ dataset:
104
+ name: sts test 512
105
+ type: sts-test-512
106
+ metrics:
107
+ - type: pearson_cosine
108
+ value: 0.7090618585285485
109
+ name: Pearson Cosine
110
+ - type: spearman_cosine
111
+ value: 0.7045766195278508
112
+ name: Spearman Cosine
113
+ - type: pearson_manhattan
114
+ value: 0.7129955390384859
115
+ name: Pearson Manhattan
116
+ - type: spearman_manhattan
117
+ value: 0.7021695501159393
118
+ name: Spearman Manhattan
119
+ - type: pearson_euclidean
120
+ value: 0.7138697740168334
121
+ name: Pearson Euclidean
122
+ - type: spearman_euclidean
123
+ value: 0.7032055408694606
124
+ name: Spearman Euclidean
125
+ - type: pearson_dot
126
+ value: 0.39352767760073326
127
+ name: Pearson Dot
128
+ - type: spearman_dot
129
+ value: 0.3628376619678567
130
+ name: Spearman Dot
131
+ - type: pearson_max
132
+ value: 0.7138697740168334
133
+ name: Pearson Max
134
+ - type: spearman_max
135
+ value: 0.7045766195278508
136
+ name: Spearman Max
137
+ - task:
138
+ type: semantic-similarity
139
+ name: Semantic Similarity
140
+ dataset:
141
+ name: sts test 256
142
+ type: sts-test-256
143
+ metrics:
144
+ - type: pearson_cosine
145
+ value: 0.7067837420770313
146
+ name: Pearson Cosine
147
+ - type: spearman_cosine
148
+ value: 0.7044452613349608
149
+ name: Spearman Cosine
150
+ - type: pearson_manhattan
151
+ value: 0.7137425083925593
152
+ name: Pearson Manhattan
153
+ - type: spearman_manhattan
154
+ value: 0.7032345257234871
155
+ name: Spearman Manhattan
156
+ - type: pearson_euclidean
157
+ value: 0.7146861583047366
158
+ name: Pearson Euclidean
159
+ - type: spearman_euclidean
160
+ value: 0.7039212190752775
161
+ name: Spearman Euclidean
162
+ - type: pearson_dot
163
+ value: 0.37462153895392747
164
+ name: Pearson Dot
165
+ - type: spearman_dot
166
+ value: 0.34441190254194326
167
+ name: Spearman Dot
168
+ - type: pearson_max
169
+ value: 0.7146861583047366
170
+ name: Pearson Max
171
+ - type: spearman_max
172
+ value: 0.7044452613349608
173
+ name: Spearman Max
174
+ - task:
175
+ type: semantic-similarity
176
+ name: Semantic Similarity
177
+ dataset:
178
+ name: sts test 128
179
+ type: sts-test-128
180
+ metrics:
181
+ - type: pearson_cosine
182
+ value: 0.7046839100746249
183
+ name: Pearson Cosine
184
+ - type: spearman_cosine
185
+ value: 0.7050559450173808
186
+ name: Spearman Cosine
187
+ - type: pearson_manhattan
188
+ value: 0.7120431790616113
189
+ name: Pearson Manhattan
190
+ - type: spearman_manhattan
191
+ value: 0.7010054121016321
192
+ name: Spearman Manhattan
193
+ - type: pearson_euclidean
194
+ value: 0.7132280398983044
195
+ name: Pearson Euclidean
196
+ - type: spearman_euclidean
197
+ value: 0.701626975970973
198
+ name: Spearman Euclidean
199
+ - type: pearson_dot
200
+ value: 0.35455409787695585
201
+ name: Pearson Dot
202
+ - type: spearman_dot
203
+ value: 0.32292034736383524
204
+ name: Spearman Dot
205
+ - type: pearson_max
206
+ value: 0.7132280398983044
207
+ name: Pearson Max
208
+ - type: spearman_max
209
+ value: 0.7050559450173808
210
+ name: Spearman Max
211
+ - task:
212
+ type: semantic-similarity
213
+ name: Semantic Similarity
214
+ dataset:
215
+ name: sts test 64
216
+ type: sts-test-64
217
+ metrics:
218
+ - type: pearson_cosine
219
+ value: 0.7012310578605567
220
+ name: Pearson Cosine
221
+ - type: spearman_cosine
222
+ value: 0.7044132231714119
223
+ name: Spearman Cosine
224
+ - type: pearson_manhattan
225
+ value: 0.7091211798265005
226
+ name: Pearson Manhattan
227
+ - type: spearman_manhattan
228
+ value: 0.6972792688781575
229
+ name: Spearman Manhattan
230
+ - type: pearson_euclidean
231
+ value: 0.7103033981031003
232
+ name: Pearson Euclidean
233
+ - type: spearman_euclidean
234
+ value: 0.6985716335223231
235
+ name: Spearman Euclidean
236
+ - type: pearson_dot
237
+ value: 0.3379821887901175
238
+ name: Pearson Dot
239
+ - type: spearman_dot
240
+ value: 0.30513652558145304
241
+ name: Spearman Dot
242
+ - type: pearson_max
243
+ value: 0.7103033981031003
244
+ name: Pearson Max
245
+ - type: spearman_max
246
+ value: 0.7044132231714119
247
+ name: Spearman Max
248
+ ---
249
+
250
+ # SentenceTransformer based on UBC-NLP/serengeti-E250
251
+
252
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [UBC-NLP/serengeti-E250](https://huggingface.co/UBC-NLP/serengeti-E250). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
253
+
254
+ ## Model Details
255
+
256
+ ### Model Description
257
+ - **Model Type:** Sentence Transformer
258
+ - **Base model:** [UBC-NLP/serengeti-E250](https://huggingface.co/UBC-NLP/serengeti-E250) <!-- at revision 41b5b8b6179c4af2859768cbf4f0f03e928d651d -->
259
+ - **Maximum Sequence Length:** 512 tokens
260
+ - **Output Dimensionality:** 768 tokens
261
+ - **Similarity Function:** Cosine Similarity
262
+ <!-- - **Training Dataset:** Unknown -->
263
+ <!-- - **Language:** Unknown -->
264
+ <!-- - **License:** Unknown -->
265
+
266
+ ### Model Sources
267
+
268
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
269
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
270
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
271
+
272
+ ### Full Model Architecture
273
+
274
+ ```
275
+ SentenceTransformer(
276
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: ElectraModel
277
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
278
+ )
279
+ ```
280
+
281
+ ## Usage
282
+
283
+ ### Direct Usage (Sentence Transformers)
284
+
285
+ First install the Sentence Transformers library:
286
+
287
+ ```bash
288
+ pip install -U sentence-transformers
289
+ ```
290
+
291
+ Then you can load this model and run inference.
292
+ ```python
293
+ from sentence_transformers import SentenceTransformer
294
+
295
+ # Download from the 🤗 Hub
296
+ model = SentenceTransformer("Mollel/swahili-serengeti-E250-nli-matryoshka")
297
+ # Run inference
298
+ sentences = [
299
+ 'Mwanamume aliyevalia koti la bluu la kuzuia upepo, amelala uso chini kwenye benchi ya bustani, akiwa na chupa ya pombe iliyofungwa kwenye mojawapo ya miguu ya benchi.',
300
+ 'Mwanamume amelala uso chini kwenye benchi ya bustani.',
301
+ 'Mwanamume fulani anacheza dansi kwenye klabu hiyo akifungua chupa.',
302
+ ]
303
+ embeddings = model.encode(sentences)
304
+ print(embeddings.shape)
305
+ # [3, 768]
306
+
307
+ # Get the similarity scores for the embeddings
308
+ similarities = model.similarity(embeddings, embeddings)
309
+ print(similarities.shape)
310
+ # [3, 3]
311
+ ```
312
+
313
+ <!--
314
+ ### Direct Usage (Transformers)
315
+
316
+ <details><summary>Click to see the direct usage in Transformers</summary>
317
+
318
+ </details>
319
+ -->
320
+
321
+ <!--
322
+ ### Downstream Usage (Sentence Transformers)
323
+
324
+ You can finetune this model on your own dataset.
325
+
326
+ <details><summary>Click to expand</summary>
327
+
328
+ </details>
329
+ -->
330
+
331
+ <!--
332
+ ### Out-of-Scope Use
333
+
334
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
335
+ -->
336
+
337
+ ## Evaluation
338
+
339
+ ### Metrics
340
+
341
+ #### Semantic Similarity
342
+ * Dataset: `sts-test-768`
343
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
344
+
345
+ | Metric | Value |
346
+ |:--------------------|:-----------|
347
+ | pearson_cosine | 0.7113 |
348
+ | **spearman_cosine** | **0.7065** |
349
+ | pearson_manhattan | 0.7134 |
350
+ | spearman_manhattan | 0.7023 |
351
+ | pearson_euclidean | 0.7138 |
352
+ | spearman_euclidean | 0.7021 |
353
+ | pearson_dot | 0.3921 |
354
+ | spearman_dot | 0.3601 |
355
+ | pearson_max | 0.7138 |
356
+ | spearman_max | 0.7065 |
357
+
358
+ #### Semantic Similarity
359
+ * Dataset: `sts-test-512`
360
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
361
+
362
+ | Metric | Value |
363
+ |:--------------------|:-----------|
364
+ | pearson_cosine | 0.7091 |
365
+ | **spearman_cosine** | **0.7046** |
366
+ | pearson_manhattan | 0.713 |
367
+ | spearman_manhattan | 0.7022 |
368
+ | pearson_euclidean | 0.7139 |
369
+ | spearman_euclidean | 0.7032 |
370
+ | pearson_dot | 0.3935 |
371
+ | spearman_dot | 0.3628 |
372
+ | pearson_max | 0.7139 |
373
+ | spearman_max | 0.7046 |
374
+
375
+ #### Semantic Similarity
376
+ * Dataset: `sts-test-256`
377
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
378
+
379
+ | Metric | Value |
380
+ |:--------------------|:-----------|
381
+ | pearson_cosine | 0.7068 |
382
+ | **spearman_cosine** | **0.7044** |
383
+ | pearson_manhattan | 0.7137 |
384
+ | spearman_manhattan | 0.7032 |
385
+ | pearson_euclidean | 0.7147 |
386
+ | spearman_euclidean | 0.7039 |
387
+ | pearson_dot | 0.3746 |
388
+ | spearman_dot | 0.3444 |
389
+ | pearson_max | 0.7147 |
390
+ | spearman_max | 0.7044 |
391
+
392
+ #### Semantic Similarity
393
+ * Dataset: `sts-test-128`
394
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
395
+
396
+ | Metric | Value |
397
+ |:--------------------|:-----------|
398
+ | pearson_cosine | 0.7047 |
399
+ | **spearman_cosine** | **0.7051** |
400
+ | pearson_manhattan | 0.712 |
401
+ | spearman_manhattan | 0.701 |
402
+ | pearson_euclidean | 0.7132 |
403
+ | spearman_euclidean | 0.7016 |
404
+ | pearson_dot | 0.3546 |
405
+ | spearman_dot | 0.3229 |
406
+ | pearson_max | 0.7132 |
407
+ | spearman_max | 0.7051 |
408
+
409
+ #### Semantic Similarity
410
+ * Dataset: `sts-test-64`
411
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
412
+
413
+ | Metric | Value |
414
+ |:--------------------|:-----------|
415
+ | pearson_cosine | 0.7012 |
416
+ | **spearman_cosine** | **0.7044** |
417
+ | pearson_manhattan | 0.7091 |
418
+ | spearman_manhattan | 0.6973 |
419
+ | pearson_euclidean | 0.7103 |
420
+ | spearman_euclidean | 0.6986 |
421
+ | pearson_dot | 0.338 |
422
+ | spearman_dot | 0.3051 |
423
+ | pearson_max | 0.7103 |
424
+ | spearman_max | 0.7044 |
425
+
426
+ <!--
427
+ ## Bias, Risks and Limitations
428
+
429
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
430
+ -->
431
+
432
+ <!--
433
+ ### Recommendations
434
+
435
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
436
+ -->
437
+
438
+ ## Training Details
439
+
440
+ ### Training Hyperparameters
441
+ #### Non-Default Hyperparameters
442
+
443
+ - `per_device_train_batch_size`: 16
444
+ - `per_device_eval_batch_size`: 16
445
+ - `learning_rate`: 2e-05
446
+ - `num_train_epochs`: 1
447
+ - `warmup_ratio`: 0.1
448
+ - `bf16`: True
449
+ - `batch_sampler`: no_duplicates
450
+
451
+ #### All Hyperparameters
452
+ <details><summary>Click to expand</summary>
453
+
454
+ - `overwrite_output_dir`: False
455
+ - `do_predict`: False
456
+ - `prediction_loss_only`: True
457
+ - `per_device_train_batch_size`: 16
458
+ - `per_device_eval_batch_size`: 16
459
+ - `per_gpu_train_batch_size`: None
460
+ - `per_gpu_eval_batch_size`: None
461
+ - `gradient_accumulation_steps`: 1
462
+ - `eval_accumulation_steps`: None
463
+ - `learning_rate`: 2e-05
464
+ - `weight_decay`: 0.0
465
+ - `adam_beta1`: 0.9
466
+ - `adam_beta2`: 0.999
467
+ - `adam_epsilon`: 1e-08
468
+ - `max_grad_norm`: 1.0
469
+ - `num_train_epochs`: 1
470
+ - `max_steps`: -1
471
+ - `lr_scheduler_type`: linear
472
+ - `lr_scheduler_kwargs`: {}
473
+ - `warmup_ratio`: 0.1
474
+ - `warmup_steps`: 0
475
+ - `log_level`: passive
476
+ - `log_level_replica`: warning
477
+ - `log_on_each_node`: True
478
+ - `logging_nan_inf_filter`: True
479
+ - `save_safetensors`: True
480
+ - `save_on_each_node`: False
481
+ - `save_only_model`: False
482
+ - `no_cuda`: False
483
+ - `use_cpu`: False
484
+ - `use_mps_device`: False
485
+ - `seed`: 42
486
+ - `data_seed`: None
487
+ - `jit_mode_eval`: False
488
+ - `use_ipex`: False
489
+ - `bf16`: True
490
+ - `fp16`: False
491
+ - `fp16_opt_level`: O1
492
+ - `half_precision_backend`: auto
493
+ - `bf16_full_eval`: False
494
+ - `fp16_full_eval`: False
495
+ - `tf32`: None
496
+ - `local_rank`: 0
497
+ - `ddp_backend`: None
498
+ - `tpu_num_cores`: None
499
+ - `tpu_metrics_debug`: False
500
+ - `debug`: []
501
+ - `dataloader_drop_last`: False
502
+ - `dataloader_num_workers`: 0
503
+ - `dataloader_prefetch_factor`: None
504
+ - `past_index`: -1
505
+ - `disable_tqdm`: False
506
+ - `remove_unused_columns`: True
507
+ - `label_names`: None
508
+ - `load_best_model_at_end`: False
509
+ - `ignore_data_skip`: False
510
+ - `fsdp`: []
511
+ - `fsdp_min_num_params`: 0
512
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
513
+ - `fsdp_transformer_layer_cls_to_wrap`: None
514
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}
515
+ - `deepspeed`: None
516
+ - `label_smoothing_factor`: 0.0
517
+ - `optim`: adamw_torch
518
+ - `optim_args`: None
519
+ - `adafactor`: False
520
+ - `group_by_length`: False
521
+ - `length_column_name`: length
522
+ - `ddp_find_unused_parameters`: None
523
+ - `ddp_bucket_cap_mb`: None
524
+ - `ddp_broadcast_buffers`: False
525
+ - `dataloader_pin_memory`: True
526
+ - `dataloader_persistent_workers`: False
527
+ - `skip_memory_metrics`: True
528
+ - `use_legacy_prediction_loop`: False
529
+ - `push_to_hub`: False
530
+ - `resume_from_checkpoint`: None
531
+ - `hub_model_id`: None
532
+ - `hub_strategy`: every_save
533
+ - `hub_private_repo`: False
534
+ - `hub_always_push`: False
535
+ - `gradient_checkpointing`: False
536
+ - `gradient_checkpointing_kwargs`: None
537
+ - `include_inputs_for_metrics`: False
538
+ - `eval_do_concat_batches`: True
539
+ - `fp16_backend`: auto
540
+ - `push_to_hub_model_id`: None
541
+ - `push_to_hub_organization`: None
542
+ - `mp_parameters`:
543
+ - `auto_find_batch_size`: False
544
+ - `full_determinism`: False
545
+ - `torchdynamo`: None
546
+ - `ray_scope`: last
547
+ - `ddp_timeout`: 1800
548
+ - `torch_compile`: False
549
+ - `torch_compile_backend`: None
550
+ - `torch_compile_mode`: None
551
+ - `dispatch_batches`: None
552
+ - `split_batches`: None
553
+ - `include_tokens_per_second`: False
554
+ - `include_num_input_tokens_seen`: False
555
+ - `neftune_noise_alpha`: None
556
+ - `optim_target_modules`: None
557
+ - `batch_sampler`: no_duplicates
558
+ - `multi_dataset_batch_sampler`: proportional
559
+
560
+ </details>
561
+
562
+ ### Training Logs
563
+ <details><summary>Click to expand</summary>
564
+
565
+ | Epoch | Step | Training Loss | sts-test-128_spearman_cosine | sts-test-256_spearman_cosine | sts-test-512_spearman_cosine | sts-test-64_spearman_cosine | sts-test-768_spearman_cosine |
566
+ |:------:|:-----:|:-------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:----------------------------:|
567
+ | 0.0057 | 100 | 25.7713 | - | - | - | - | - |
568
+ | 0.0115 | 200 | 20.7886 | - | - | - | - | - |
569
+ | 0.0172 | 300 | 17.0398 | - | - | - | - | - |
570
+ | 0.0229 | 400 | 15.3913 | - | - | - | - | - |
571
+ | 0.0287 | 500 | 14.0214 | - | - | - | - | - |
572
+ | 0.0344 | 600 | 12.2125 | - | - | - | - | - |
573
+ | 0.0402 | 700 | 10.3033 | - | - | - | - | - |
574
+ | 0.0459 | 800 | 9.3822 | - | - | - | - | - |
575
+ | 0.0516 | 900 | 8.9276 | - | - | - | - | - |
576
+ | 0.0574 | 1000 | 8.552 | - | - | - | - | - |
577
+ | 0.0631 | 1100 | 8.6293 | - | - | - | - | - |
578
+ | 0.0688 | 1200 | 8.5353 | - | - | - | - | - |
579
+ | 0.0746 | 1300 | 8.6431 | - | - | - | - | - |
580
+ | 0.0803 | 1400 | 8.3192 | - | - | - | - | - |
581
+ | 0.0860 | 1500 | 7.1834 | - | - | - | - | - |
582
+ | 0.0918 | 1600 | 6.7834 | - | - | - | - | - |
583
+ | 0.0975 | 1700 | 6.4758 | - | - | - | - | - |
584
+ | 0.1033 | 1800 | 6.756 | - | - | - | - | - |
585
+ | 0.1090 | 1900 | 7.807 | - | - | - | - | - |
586
+ | 0.1147 | 2000 | 6.8836 | - | - | - | - | - |
587
+ | 0.1205 | 2100 | 6.9948 | - | - | - | - | - |
588
+ | 0.1262 | 2200 | 6.5031 | - | - | - | - | - |
589
+ | 0.1319 | 2300 | 6.3596 | - | - | - | - | - |
590
+ | 0.1377 | 2400 | 6.0257 | - | - | - | - | - |
591
+ | 0.1434 | 2500 | 5.9757 | - | - | - | - | - |
592
+ | 0.1491 | 2600 | 5.464 | - | - | - | - | - |
593
+ | 0.1549 | 2700 | 5.6518 | - | - | - | - | - |
594
+ | 0.1606 | 2800 | 6.2899 | - | - | - | - | - |
595
+ | 0.1664 | 2900 | 6.4876 | - | - | - | - | - |
596
+ | 0.1721 | 3000 | 6.9466 | - | - | - | - | - |
597
+ | 0.1778 | 3100 | 6.8439 | - | - | - | - | - |
598
+ | 0.1836 | 3200 | 6.2545 | - | - | - | - | - |
599
+ | 0.1893 | 3300 | 5.9795 | - | - | - | - | - |
600
+ | 0.1950 | 3400 | 5.3904 | - | - | - | - | - |
601
+ | 0.2008 | 3500 | 6.2798 | - | - | - | - | - |
602
+ | 0.2065 | 3600 | 5.6882 | - | - | - | - | - |
603
+ | 0.2122 | 3700 | 6.195 | - | - | - | - | - |
604
+ | 0.2180 | 3800 | 5.8728 | - | - | - | - | - |
605
+ | 0.2237 | 3900 | 6.2428 | - | - | - | - | - |
606
+ | 0.2294 | 4000 | 5.801 | - | - | - | - | - |
607
+ | 0.2352 | 4100 | 5.6918 | - | - | - | - | - |
608
+ | 0.2409 | 4200 | 5.3977 | - | - | - | - | - |
609
+ | 0.2467 | 4300 | 5.8792 | - | - | - | - | - |
610
+ | 0.2524 | 4400 | 5.9297 | - | - | - | - | - |
611
+ | 0.2581 | 4500 | 6.161 | - | - | - | - | - |
612
+ | 0.2639 | 4600 | 5.6571 | - | - | - | - | - |
613
+ | 0.2696 | 4700 | 5.5849 | - | - | - | - | - |
614
+ | 0.2753 | 4800 | 5.6382 | - | - | - | - | - |
615
+ | 0.2811 | 4900 | 5.2978 | - | - | - | - | - |
616
+ | 0.2868 | 5000 | 5.108 | - | - | - | - | - |
617
+ | 0.2925 | 5100 | 5.1158 | - | - | - | - | - |
618
+ | 0.2983 | 5200 | 5.6218 | - | - | - | - | - |
619
+ | 0.3040 | 5300 | 5.643 | - | - | - | - | - |
620
+ | 0.3098 | 5400 | 5.6894 | - | - | - | - | - |
621
+ | 0.3155 | 5500 | 5.373 | - | - | - | - | - |
622
+ | 0.3212 | 5600 | 5.0673 | - | - | - | - | - |
623
+ | 0.3270 | 5700 | 5.1915 | - | - | - | - | - |
624
+ | 0.3327 | 5800 | 5.3705 | - | - | - | - | - |
625
+ | 0.3384 | 5900 | 5.6432 | - | - | - | - | - |
626
+ | 0.3442 | 6000 | 5.2567 | - | - | - | - | - |
627
+ | 0.3499 | 6100 | 5.4516 | - | - | - | - | - |
628
+ | 0.3556 | 6200 | 5.4844 | - | - | - | - | - |
629
+ | 0.3614 | 6300 | 4.8238 | - | - | - | - | - |
630
+ | 0.3671 | 6400 | 4.8271 | - | - | - | - | - |
631
+ | 0.3729 | 6500 | 4.9863 | - | - | - | - | - |
632
+ | 0.3786 | 6600 | 5.4894 | - | - | - | - | - |
633
+ | 0.3843 | 6700 | 4.95 | - | - | - | - | - |
634
+ | 0.3901 | 6800 | 5.0881 | - | - | - | - | - |
635
+ | 0.3958 | 6900 | 5.249 | - | - | - | - | - |
636
+ | 0.4015 | 7000 | 5.0082 | - | - | - | - | - |
637
+ | 0.4073 | 7100 | 5.5064 | - | - | - | - | - |
638
+ | 0.4130 | 7200 | 5.0885 | - | - | - | - | - |
639
+ | 0.4187 | 7300 | 5.0321 | - | - | - | - | - |
640
+ | 0.4245 | 7400 | 4.8212 | - | - | - | - | - |
641
+ | 0.4302 | 7500 | 5.4231 | - | - | - | - | - |
642
+ | 0.4360 | 7600 | 4.7687 | - | - | - | - | - |
643
+ | 0.4417 | 7700 | 4.5707 | - | - | - | - | - |
644
+ | 0.4474 | 7800 | 5.2229 | - | - | - | - | - |
645
+ | 0.4532 | 7900 | 5.2446 | - | - | - | - | - |
646
+ | 0.4589 | 8000 | 4.682 | - | - | - | - | - |
647
+ | 0.4646 | 8100 | 4.888 | - | - | - | - | - |
648
+ | 0.4704 | 8200 | 5.0496 | - | - | - | - | - |
649
+ | 0.4761 | 8300 | 4.7089 | - | - | - | - | - |
650
+ | 0.4818 | 8400 | 4.9567 | - | - | - | - | - |
651
+ | 0.4876 | 8500 | 4.7913 | - | - | - | - | - |
652
+ | 0.4933 | 8600 | 4.8904 | - | - | - | - | - |
653
+ | 0.4991 | 8700 | 5.247 | - | - | - | - | - |
654
+ | 0.5048 | 8800 | 4.8254 | - | - | - | - | - |
655
+ | 0.5105 | 8900 | 4.973 | - | - | - | - | - |
656
+ | 0.5163 | 9000 | 4.6657 | - | - | - | - | - |
657
+ | 0.5220 | 9100 | 4.9224 | - | - | - | - | - |
658
+ | 0.5277 | 9200 | 4.8163 | - | - | - | - | - |
659
+ | 0.5335 | 9300 | 4.3673 | - | - | - | - | - |
660
+ | 0.5392 | 9400 | 4.6509 | - | - | - | - | - |
661
+ | 0.5449 | 9500 | 5.0667 | - | - | - | - | - |
662
+ | 0.5507 | 9600 | 4.8771 | - | - | - | - | - |
663
+ | 0.5564 | 9700 | 5.1056 | - | - | - | - | - |
664
+ | 0.5622 | 9800 | 4.8297 | - | - | - | - | - |
665
+ | 0.5679 | 9900 | 5.0156 | - | - | - | - | - |
666
+ | 0.5736 | 10000 | 5.0758 | - | - | - | - | - |
667
+ | 0.5794 | 10100 | 4.9551 | - | - | - | - | - |
668
+ | 0.5851 | 10200 | 4.9594 | - | - | - | - | - |
669
+ | 0.5908 | 10300 | 5.136 | - | - | - | - | - |
670
+ | 0.5966 | 10400 | 4.7873 | - | - | - | - | - |
671
+ | 0.6023 | 10500 | 4.5154 | - | - | - | - | - |
672
+ | 0.6080 | 10600 | 4.928 | - | - | - | - | - |
673
+ | 0.6138 | 10700 | 5.1825 | - | - | - | - | - |
674
+ | 0.6195 | 10800 | 5.046 | - | - | - | - | - |
675
+ | 0.6253 | 10900 | 5.0111 | - | - | - | - | - |
676
+ | 0.6310 | 11000 | 4.9458 | - | - | - | - | - |
677
+ | 0.6367 | 11100 | 5.188 | - | - | - | - | - |
678
+ | 0.6425 | 11200 | 4.6219 | - | - | - | - | - |
679
+ | 0.6482 | 11300 | 5.3367 | - | - | - | - | - |
680
+ | 0.6539 | 11400 | 4.9851 | - | - | - | - | - |
681
+ | 0.6597 | 11500 | 5.2068 | - | - | - | - | - |
682
+ | 0.6654 | 11600 | 4.3789 | - | - | - | - | - |
683
+ | 0.6711 | 11700 | 5.3533 | - | - | - | - | - |
684
+ | 0.6769 | 11800 | 5.3983 | - | - | - | - | - |
685
+ | 0.6826 | 11900 | 4.6 | - | - | - | - | - |
686
+ | 0.6883 | 12000 | 4.6668 | - | - | - | - | - |
687
+ | 0.6941 | 12100 | 5.0814 | - | - | - | - | - |
688
+ | 0.6998 | 12200 | 5.0787 | - | - | - | - | - |
689
+ | 0.7056 | 12300 | 4.6325 | - | - | - | - | - |
690
+ | 0.7113 | 12400 | 4.9415 | - | - | - | - | - |
691
+ | 0.7170 | 12500 | 4.7053 | - | - | - | - | - |
692
+ | 0.7228 | 12600 | 4.3212 | - | - | - | - | - |
693
+ | 0.7285 | 12700 | 4.8205 | - | - | - | - | - |
694
+ | 0.7342 | 12800 | 4.8602 | - | - | - | - | - |
695
+ | 0.7400 | 12900 | 4.6944 | - | - | - | - | - |
696
+ | 0.7457 | 13000 | 4.7785 | - | - | - | - | - |
697
+ | 0.7514 | 13100 | 4.3515 | - | - | - | - | - |
698
+ | 0.7572 | 13200 | 5.7561 | - | - | - | - | - |
699
+ | 0.7629 | 13300 | 5.3526 | - | - | - | - | - |
700
+ | 0.7687 | 13400 | 5.187 | - | - | - | - | - |
701
+ | 0.7744 | 13500 | 5.0143 | - | - | - | - | - |
702
+ | 0.7801 | 13600 | 4.515 | - | - | - | - | - |
703
+ | 0.7859 | 13700 | 4.639 | - | - | - | - | - |
704
+ | 0.7916 | 13800 | 4.5556 | - | - | - | - | - |
705
+ | 0.7973 | 13900 | 4.3526 | - | - | - | - | - |
706
+ | 0.8031 | 14000 | 4.3091 | - | - | - | - | - |
707
+ | 0.8088 | 14100 | 4.1761 | - | - | - | - | - |
708
+ | 0.8145 | 14200 | 4.0484 | - | - | - | - | - |
709
+ | 0.8203 | 14300 | 4.1886 | - | - | - | - | - |
710
+ | 0.8260 | 14400 | 4.237 | - | - | - | - | - |
711
+ | 0.8318 | 14500 | 4.2167 | - | - | - | - | - |
712
+ | 0.8375 | 14600 | 4.0329 | - | - | - | - | - |
713
+ | 0.8432 | 14700 | 3.9902 | - | - | - | - | - |
714
+ | 0.8490 | 14800 | 3.8211 | - | - | - | - | - |
715
+ | 0.8547 | 14900 | 4.0048 | - | - | - | - | - |
716
+ | 0.8604 | 15000 | 3.7979 | - | - | - | - | - |
717
+ | 0.8662 | 15100 | 3.8117 | - | - | - | - | - |
718
+ | 0.8719 | 15200 | 3.909 | - | - | - | - | - |
719
+ | 0.8776 | 15300 | 3.8526 | - | - | - | - | - |
720
+ | 0.8834 | 15400 | 3.79 | - | - | - | - | - |
721
+ | 0.8891 | 15500 | 3.7792 | - | - | - | - | - |
722
+ | 0.8949 | 15600 | 3.7469 | - | - | - | - | - |
723
+ | 0.9006 | 15700 | 3.8387 | - | - | - | - | - |
724
+ | 0.9063 | 15800 | 3.6418 | - | - | - | - | - |
725
+ | 0.9121 | 15900 | 3.645 | - | - | - | - | - |
726
+ | 0.9178 | 16000 | 3.4861 | - | - | - | - | - |
727
+ | 0.9235 | 16100 | 3.6416 | - | - | - | - | - |
728
+ | 0.9293 | 16200 | 3.6665 | - | - | - | - | - |
729
+ | 0.9350 | 16300 | 3.6809 | - | - | - | - | - |
730
+ | 0.9407 | 16400 | 3.7944 | - | - | - | - | - |
731
+ | 0.9465 | 16500 | 3.6585 | - | - | - | - | - |
732
+ | 0.9522 | 16600 | 3.5398 | - | - | - | - | - |
733
+ | 0.9580 | 16700 | 3.7036 | - | - | - | - | - |
734
+ | 0.9637 | 16800 | 3.6386 | - | - | - | - | - |
735
+ | 0.9694 | 16900 | 3.5501 | - | - | - | - | - |
736
+ | 0.9752 | 17000 | 3.7957 | - | - | - | - | - |
737
+ | 0.9809 | 17100 | 3.6076 | - | - | - | - | - |
738
+ | 0.9866 | 17200 | 3.4653 | - | - | - | - | - |
739
+ | 0.9924 | 17300 | 3.6768 | - | - | - | - | - |
740
+ | 0.9981 | 17400 | 3.49 | - | - | - | - | - |
741
+ | 1.0 | 17433 | - | 0.7051 | 0.7044 | 0.7046 | 0.7044 | 0.7065 |
742
+
743
+ </details>
744
+
745
+ ### Framework Versions
746
+ - Python: 3.11.9
747
+ - Sentence Transformers: 3.0.1
748
+ - Transformers: 4.40.1
749
+ - PyTorch: 2.3.0+cu121
750
+ - Accelerate: 0.29.3
751
+ - Datasets: 2.19.0
752
+ - Tokenizers: 0.19.1
753
+
754
+ ## Citation
755
+
756
+ ### BibTeX
757
+
758
+ #### Sentence Transformers
759
+ ```bibtex
760
+ @inproceedings{reimers-2019-sentence-bert,
761
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
762
+ author = "Reimers, Nils and Gurevych, Iryna",
763
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
764
+ month = "11",
765
+ year = "2019",
766
+ publisher = "Association for Computational Linguistics",
767
+ url = "https://arxiv.org/abs/1908.10084",
768
+ }
769
+ ```
770
+
771
+ #### MatryoshkaLoss
772
+ ```bibtex
773
+ @misc{kusupati2024matryoshka,
774
+ title={Matryoshka Representation Learning},
775
+ 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},
776
+ year={2024},
777
+ eprint={2205.13147},
778
+ archivePrefix={arXiv},
779
+ primaryClass={cs.LG}
780
+ }
781
+ ```
782
+
783
+ #### MultipleNegativesRankingLoss
784
+ ```bibtex
785
+ @misc{henderson2017efficient,
786
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
787
+ 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},
788
+ year={2017},
789
+ eprint={1705.00652},
790
+ archivePrefix={arXiv},
791
+ primaryClass={cs.CL}
792
+ }
793
+ ```
794
+
795
+ <!--
796
+ ## Glossary
797
+
798
+ *Clearly define terms in order to be accessible across audiences.*
799
+ -->
800
+
801
+ <!--
802
+ ## Model Card Authors
803
+
804
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
805
+ -->
806
+
807
+ <!--
808
+ ## Model Card Contact
809
+
810
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
811
+ -->
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "UBC-NLP/serengeti-E250",
3
+ "architectures": [
4
+ "ElectraModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "electra",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "summary_activation": "gelu",
22
+ "summary_last_dropout": 0.1,
23
+ "summary_type": "first",
24
+ "summary_use_proj": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.40.1",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
+ "vocab_size": 250000
30
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.40.1",
5
+ "pytorch": "2.3.0+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 sha256:672730788a7bf59e91c2b6c69f6e53277912fb3625069536fe4c308f96103f59
3
+ size 1109825328
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": 512,
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "ElectraTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff