Hugging Face's logo

sentence-transformers-testing
/
stsb-bert-tiny-lora

Sentence Similarity
sentence-transformers
Safetensors
English
feature-extraction
Generated from Trainer
dataset_size:3012496
loss:MultipleNegativesRankingLoss
Eval Results
Inference Endpoints
Model card Files Community
tomaarsen HF staff commited on
Commit
f2b5359
•
1 Parent(s): f29746f

Add new SentenceTransformer model

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +1290 -0
  3. adapter_config.json +29 -0
  4. adapter_model.safetensors +3 -0
  5. config_sentence_transformers.json +10 -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 +64 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 128,
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 +1,1290 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - sentence-transformers
7
+ - sentence-similarity
8
+ - feature-extraction
9
+ - generated_from_trainer
10
+ - dataset_size:3012496
11
+ - loss:MultipleNegativesRankingLoss
12
+ base_model: sentence-transformers-testing/stsb-bert-tiny-safetensors
13
+ widget:
14
+ - source_sentence: how to sign legal documents as power of attorney?
15
+ sentences:
16
+ - 'After the principal''s name, write “by” and then sign your own name. Under or
17
+ after the signature line, indicate your status as POA by including any of the
18
+ following identifiers: as POA, as Agent, as Attorney in Fact or as Power of Attorney.'
19
+ - '[''From the Home screen, swipe left to Apps.'', ''Tap Transfer my Data.'', ''Tap
20
+ Menu (...).'', ''Tap Export to SD card.'']'
21
+ - Ginger Dank Nugs (Grape) - 350mg. Feast your eyes on these unique and striking
22
+ gourmet chocolates; Coco Nugs created by Ginger Dank. Crafted to resemble perfect
23
+ nugs of cannabis, each of the 10 buds contains 35mg of THC. ... This is a perfect
24
+ product for both cannabis and chocolate lovers, who appreciate a little twist.
25
+ - source_sentence: how to delete vdom in fortigate?
26
+ sentences:
27
+ - Go to System -> VDOM -> VDOM2 and select 'Delete'. This VDOM is now successfully
28
+ removed from the configuration.
29
+ - 'Both combination birth control pills and progestin-only pills may cause headaches
30
+ as a side effect. Additional side effects of birth control pills may include:
31
+ breast tenderness. nausea.'
32
+ - White cheese tends to show imperfections more readily and as consumers got more
33
+ used to yellow-orange cheese, it became an expected option. Today, many cheddars
34
+ are yellow. While most cheesemakers use annatto, some use an artificial coloring
35
+ agent instead, according to Sachs.
36
+ - source_sentence: where are earthquakes most likely to occur on earth?
37
+ sentences:
38
+ - Zelle in the Bank of the America app is a fast, safe, and easy way to send and
39
+ receive money with family and friends who have a bank account in the U.S., all
40
+ with no fees. Money moves in minutes directly between accounts that are already
41
+ enrolled with Zelle.
42
+ - It takes about 3 days for a spacecraft to reach the Moon. During that time a spacecraft
43
+ travels at least 240,000 miles (386,400 kilometers) which is the distance between
44
+ Earth and the Moon.
45
+ - Most earthquakes occur along the edge of the oceanic and continental plates. The
46
+ earth's crust (the outer layer of the planet) is made up of several pieces, called
47
+ plates. The plates under the oceans are called oceanic plates and the rest are
48
+ continental plates.
49
+ - source_sentence: fix iphone is disabled connect to itunes without itunes?
50
+ sentences:
51
+ - To fix a disabled iPhone or iPad without iTunes, you have to erase your device.
52
+ Click on the "Erase iPhone" option and confirm your selection. Wait for a while
53
+ as the "Find My iPhone" feature will remotely erase your iOS device. Needless
54
+ to say, it will also disable its lock.
55
+ - How Māui brought fire to the world. One evening, after eating a hearty meal, Māui
56
+ lay beside his fire staring into the flames. ... In the middle of the night, while
57
+ everyone was sleeping, Māui went from village to village and extinguished all
58
+ the fires until not a single fire burned in the world.
59
+ - Angry Orchard makes a variety of year-round craft cider styles, including Angry
60
+ Orchard Crisp Apple, a fruit-forward hard cider that balances the sweetness of
61
+ culinary apples with dryness and bright acidity of bittersweet apples for a complex,
62
+ refreshing taste.
63
+ - source_sentence: how to reverse a video on tiktok that's not yours?
64
+ sentences:
65
+ - '[''Tap "Effects" at the bottom of your screen — it\''s an icon that looks like
66
+ a clock. Open the Effects menu. ... '', ''At the end of the new list that appears,
67
+ tap "Time." Select "Time" at the end. ... '', ''Select "Reverse" — you\''ll then
68
+ see a preview of your new, reversed video appear on the screen.'']'
69
+ - Franchise Facts Poke Bar has a franchise fee of up to $30,000, with a total initial
70
+ investment range of $157,800 to $438,000. The initial cost of a franchise includes
71
+ several fees -- Unlock this franchise to better understand the costs such as training
72
+ and territory fees.
73
+ - Relative age is the age of a rock layer (or the fossils it contains) compared
74
+ to other layers. It can be determined by looking at the position of rock layers.
75
+ Absolute age is the numeric age of a layer of rocks or fossils. Absolute age can
76
+ be determined by using radiometric dating.
77
+ datasets:
78
+ - sentence-transformers/gooaq
79
+ pipeline_tag: sentence-similarity
80
+ library_name: sentence-transformers
81
+ metrics:
82
+ - cosine_accuracy@1
83
+ - cosine_accuracy@3
84
+ - cosine_accuracy@5
85
+ - cosine_accuracy@10
86
+ - cosine_precision@1
87
+ - cosine_precision@3
88
+ - cosine_precision@5
89
+ - cosine_precision@10
90
+ - cosine_recall@1
91
+ - cosine_recall@3
92
+ - cosine_recall@5
93
+ - cosine_recall@10
94
+ - cosine_ndcg@10
95
+ - cosine_mrr@10
96
+ - cosine_map@100
97
+ co2_eq_emissions:
98
+ emissions: 9.679189270737199
99
+ energy_consumed: 0.024901310697493708
100
+ source: codecarbon
101
+ training_type: fine-tuning
102
+ on_cloud: false
103
+ cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
104
+ ram_total_size: 31.777088165283203
105
+ hours_used: 0.15
106
+ hardware_used: 1 x NVIDIA GeForce RTX 3090
107
+ model-index:
108
+ - name: stsb-bert-tiny adapter finetuned on GooAQ pairs
109
+ results:
110
+ - task:
111
+ type: information-retrieval
112
+ name: Information Retrieval
113
+ dataset:
114
+ name: NanoClimateFEVER
115
+ type: NanoClimateFEVER
116
+ metrics:
117
+ - type: cosine_accuracy@1
118
+ value: 0.14
119
+ name: Cosine Accuracy@1
120
+ - type: cosine_accuracy@3
121
+ value: 0.22
122
+ name: Cosine Accuracy@3
123
+ - type: cosine_accuracy@5
124
+ value: 0.26
125
+ name: Cosine Accuracy@5
126
+ - type: cosine_accuracy@10
127
+ value: 0.38
128
+ name: Cosine Accuracy@10
129
+ - type: cosine_precision@1
130
+ value: 0.14
131
+ name: Cosine Precision@1
132
+ - type: cosine_precision@3
133
+ value: 0.07999999999999999
134
+ name: Cosine Precision@3
135
+ - type: cosine_precision@5
136
+ value: 0.05600000000000001
137
+ name: Cosine Precision@5
138
+ - type: cosine_precision@10
139
+ value: 0.05
140
+ name: Cosine Precision@10
141
+ - type: cosine_recall@1
142
+ value: 0.056666666666666664
143
+ name: Cosine Recall@1
144
+ - type: cosine_recall@3
145
+ value: 0.08666666666666668
146
+ name: Cosine Recall@3
147
+ - type: cosine_recall@5
148
+ value: 0.11166666666666666
149
+ name: Cosine Recall@5
150
+ - type: cosine_recall@10
151
+ value: 0.17833333333333332
152
+ name: Cosine Recall@10
153
+ - type: cosine_ndcg@10
154
+ value: 0.1412311142763055
155
+ name: Cosine Ndcg@10
156
+ - type: cosine_mrr@10
157
+ value: 0.19938095238095235
158
+ name: Cosine Mrr@10
159
+ - type: cosine_map@100
160
+ value: 0.11363345611144926
161
+ name: Cosine Map@100
162
+ - task:
163
+ type: information-retrieval
164
+ name: Information Retrieval
165
+ dataset:
166
+ name: NanoDBPedia
167
+ type: NanoDBPedia
168
+ metrics:
169
+ - type: cosine_accuracy@1
170
+ value: 0.42
171
+ name: Cosine Accuracy@1
172
+ - type: cosine_accuracy@3
173
+ value: 0.62
174
+ name: Cosine Accuracy@3
175
+ - type: cosine_accuracy@5
176
+ value: 0.72
177
+ name: Cosine Accuracy@5
178
+ - type: cosine_accuracy@10
179
+ value: 0.86
180
+ name: Cosine Accuracy@10
181
+ - type: cosine_precision@1
182
+ value: 0.42
183
+ name: Cosine Precision@1
184
+ - type: cosine_precision@3
185
+ value: 0.34
186
+ name: Cosine Precision@3
187
+ - type: cosine_precision@5
188
+ value: 0.344
189
+ name: Cosine Precision@5
190
+ - type: cosine_precision@10
191
+ value: 0.29
192
+ name: Cosine Precision@10
193
+ - type: cosine_recall@1
194
+ value: 0.02634308391586433
195
+ name: Cosine Recall@1
196
+ - type: cosine_recall@3
197
+ value: 0.06038926804951766
198
+ name: Cosine Recall@3
199
+ - type: cosine_recall@5
200
+ value: 0.10265977040056268
201
+ name: Cosine Recall@5
202
+ - type: cosine_recall@10
203
+ value: 0.19610280190566398
204
+ name: Cosine Recall@10
205
+ - type: cosine_ndcg@10
206
+ value: 0.34151812101104584
207
+ name: Cosine Ndcg@10
208
+ - type: cosine_mrr@10
209
+ value: 0.5504126984126985
210
+ name: Cosine Mrr@10
211
+ - type: cosine_map@100
212
+ value: 0.21133731615809154
213
+ name: Cosine Map@100
214
+ - task:
215
+ type: information-retrieval
216
+ name: Information Retrieval
217
+ dataset:
218
+ name: NanoFEVER
219
+ type: NanoFEVER
220
+ metrics:
221
+ - type: cosine_accuracy@1
222
+ value: 0.12
223
+ name: Cosine Accuracy@1
224
+ - type: cosine_accuracy@3
225
+ value: 0.18
226
+ name: Cosine Accuracy@3
227
+ - type: cosine_accuracy@5
228
+ value: 0.22
229
+ name: Cosine Accuracy@5
230
+ - type: cosine_accuracy@10
231
+ value: 0.36
232
+ name: Cosine Accuracy@10
233
+ - type: cosine_precision@1
234
+ value: 0.12
235
+ name: Cosine Precision@1
236
+ - type: cosine_precision@3
237
+ value: 0.05999999999999999
238
+ name: Cosine Precision@3
239
+ - type: cosine_precision@5
240
+ value: 0.044000000000000004
241
+ name: Cosine Precision@5
242
+ - type: cosine_precision@10
243
+ value: 0.036000000000000004
244
+ name: Cosine Precision@10
245
+ - type: cosine_recall@1
246
+ value: 0.12
247
+ name: Cosine Recall@1
248
+ - type: cosine_recall@3
249
+ value: 0.18
250
+ name: Cosine Recall@3
251
+ - type: cosine_recall@5
252
+ value: 0.22
253
+ name: Cosine Recall@5
254
+ - type: cosine_recall@10
255
+ value: 0.34
256
+ name: Cosine Recall@10
257
+ - type: cosine_ndcg@10
258
+ value: 0.21218661613500586
259
+ name: Cosine Ndcg@10
260
+ - type: cosine_mrr@10
261
+ value: 0.17491269841269838
262
+ name: Cosine Mrr@10
263
+ - type: cosine_map@100
264
+ value: 0.18857101300669993
265
+ name: Cosine Map@100
266
+ - task:
267
+ type: information-retrieval
268
+ name: Information Retrieval
269
+ dataset:
270
+ name: NanoFiQA2018
271
+ type: NanoFiQA2018
272
+ metrics:
273
+ - type: cosine_accuracy@1
274
+ value: 0.06
275
+ name: Cosine Accuracy@1
276
+ - type: cosine_accuracy@3
277
+ value: 0.1
278
+ name: Cosine Accuracy@3
279
+ - type: cosine_accuracy@5
280
+ value: 0.2
281
+ name: Cosine Accuracy@5
282
+ - type: cosine_accuracy@10
283
+ value: 0.28
284
+ name: Cosine Accuracy@10
285
+ - type: cosine_precision@1
286
+ value: 0.06
287
+ name: Cosine Precision@1
288
+ - type: cosine_precision@3
289
+ value: 0.04
290
+ name: Cosine Precision@3
291
+ - type: cosine_precision@5
292
+ value: 0.04800000000000001
293
+ name: Cosine Precision@5
294
+ - type: cosine_precision@10
295
+ value: 0.032
296
+ name: Cosine Precision@10
297
+ - type: cosine_recall@1
298
+ value: 0.044000000000000004
299
+ name: Cosine Recall@1
300
+ - type: cosine_recall@3
301
+ value: 0.06199999999999999
302
+ name: Cosine Recall@3
303
+ - type: cosine_recall@5
304
+ value: 0.12488888888888887
305
+ name: Cosine Recall@5
306
+ - type: cosine_recall@10
307
+ value: 0.15574603174603174
308
+ name: Cosine Recall@10
309
+ - type: cosine_ndcg@10
310
+ value: 0.10395695406287388
311
+ name: Cosine Ndcg@10
312
+ - type: cosine_mrr@10
313
+ value: 0.10821428571428571
314
+ name: Cosine Mrr@10
315
+ - type: cosine_map@100
316
+ value: 0.08041090092126037
317
+ name: Cosine Map@100
318
+ - task:
319
+ type: information-retrieval
320
+ name: Information Retrieval
321
+ dataset:
322
+ name: NanoHotpotQA
323
+ type: NanoHotpotQA
324
+ metrics:
325
+ - type: cosine_accuracy@1
326
+ value: 0.36
327
+ name: Cosine Accuracy@1
328
+ - type: cosine_accuracy@3
329
+ value: 0.52
330
+ name: Cosine Accuracy@3
331
+ - type: cosine_accuracy@5
332
+ value: 0.54
333
+ name: Cosine Accuracy@5
334
+ - type: cosine_accuracy@10
335
+ value: 0.62
336
+ name: Cosine Accuracy@10
337
+ - type: cosine_precision@1
338
+ value: 0.36
339
+ name: Cosine Precision@1
340
+ - type: cosine_precision@3
341
+ value: 0.20666666666666667
342
+ name: Cosine Precision@3
343
+ - type: cosine_precision@5
344
+ value: 0.14
345
+ name: Cosine Precision@5
346
+ - type: cosine_precision@10
347
+ value: 0.07800000000000001
348
+ name: Cosine Precision@10
349
+ - type: cosine_recall@1
350
+ value: 0.18
351
+ name: Cosine Recall@1
352
+ - type: cosine_recall@3
353
+ value: 0.31
354
+ name: Cosine Recall@3
355
+ - type: cosine_recall@5
356
+ value: 0.35
357
+ name: Cosine Recall@5
358
+ - type: cosine_recall@10
359
+ value: 0.39
360
+ name: Cosine Recall@10
361
+ - type: cosine_ndcg@10
362
+ value: 0.3504958855767756
363
+ name: Cosine Ndcg@10
364
+ - type: cosine_mrr@10
365
+ value: 0.4476349206349205
366
+ name: Cosine Mrr@10
367
+ - type: cosine_map@100
368
+ value: 0.29308037158200173
369
+ name: Cosine Map@100
370
+ - task:
371
+ type: information-retrieval
372
+ name: Information Retrieval
373
+ dataset:
374
+ name: NanoMSMARCO
375
+ type: NanoMSMARCO
376
+ metrics:
377
+ - type: cosine_accuracy@1
378
+ value: 0.06
379
+ name: Cosine Accuracy@1
380
+ - type: cosine_accuracy@3
381
+ value: 0.26
382
+ name: Cosine Accuracy@3
383
+ - type: cosine_accuracy@5
384
+ value: 0.32
385
+ name: Cosine Accuracy@5
386
+ - type: cosine_accuracy@10
387
+ value: 0.36
388
+ name: Cosine Accuracy@10
389
+ - type: cosine_precision@1
390
+ value: 0.06
391
+ name: Cosine Precision@1
392
+ - type: cosine_precision@3
393
+ value: 0.08666666666666666
394
+ name: Cosine Precision@3
395
+ - type: cosine_precision@5
396
+ value: 0.064
397
+ name: Cosine Precision@5
398
+ - type: cosine_precision@10
399
+ value: 0.036000000000000004
400
+ name: Cosine Precision@10
401
+ - type: cosine_recall@1
402
+ value: 0.06
403
+ name: Cosine Recall@1
404
+ - type: cosine_recall@3
405
+ value: 0.26
406
+ name: Cosine Recall@3
407
+ - type: cosine_recall@5
408
+ value: 0.32
409
+ name: Cosine Recall@5
410
+ - type: cosine_recall@10
411
+ value: 0.36
412
+ name: Cosine Recall@10
413
+ - type: cosine_ndcg@10
414
+ value: 0.21417075898440763
415
+ name: Cosine Ndcg@10
416
+ - type: cosine_mrr@10
417
+ value: 0.16666666666666663
418
+ name: Cosine Mrr@10
419
+ - type: cosine_map@100
420
+ value: 0.19159156983842277
421
+ name: Cosine Map@100
422
+ - task:
423
+ type: information-retrieval
424
+ name: Information Retrieval
425
+ dataset:
426
+ name: NanoNFCorpus
427
+ type: NanoNFCorpus
428
+ metrics:
429
+ - type: cosine_accuracy@1
430
+ value: 0.2
431
+ name: Cosine Accuracy@1
432
+ - type: cosine_accuracy@3
433
+ value: 0.26
434
+ name: Cosine Accuracy@3
435
+ - type: cosine_accuracy@5
436
+ value: 0.3
437
+ name: Cosine Accuracy@5
438
+ - type: cosine_accuracy@10
439
+ value: 0.44
440
+ name: Cosine Accuracy@10
441
+ - type: cosine_precision@1
442
+ value: 0.2
443
+ name: Cosine Precision@1
444
+ - type: cosine_precision@3
445
+ value: 0.12
446
+ name: Cosine Precision@3
447
+ - type: cosine_precision@5
448
+ value: 0.09600000000000002
449
+ name: Cosine Precision@5
450
+ - type: cosine_precision@10
451
+ value: 0.07999999999999999
452
+ name: Cosine Precision@10
453
+ - type: cosine_recall@1
454
+ value: 0.00377949106046741
455
+ name: Cosine Recall@1
456
+ - type: cosine_recall@3
457
+ value: 0.007274949456892388
458
+ name: Cosine Recall@3
459
+ - type: cosine_recall@5
460
+ value: 0.012714784638321257
461
+ name: Cosine Recall@5
462
+ - type: cosine_recall@10
463
+ value: 0.019303285579015287
464
+ name: Cosine Recall@10
465
+ - type: cosine_ndcg@10
466
+ value: 0.09870502263453415
467
+ name: Cosine Ndcg@10
468
+ - type: cosine_mrr@10
469
+ value: 0.2538809523809524
470
+ name: Cosine Mrr@10
471
+ - type: cosine_map@100
472
+ value: 0.018928657854150332
473
+ name: Cosine Map@100
474
+ - task:
475
+ type: information-retrieval
476
+ name: Information Retrieval
477
+ dataset:
478
+ name: NanoNQ
479
+ type: NanoNQ
480
+ metrics:
481
+ - type: cosine_accuracy@1
482
+ value: 0.08
483
+ name: Cosine Accuracy@1
484
+ - type: cosine_accuracy@3
485
+ value: 0.18
486
+ name: Cosine Accuracy@3
487
+ - type: cosine_accuracy@5
488
+ value: 0.2
489
+ name: Cosine Accuracy@5
490
+ - type: cosine_accuracy@10
491
+ value: 0.42
492
+ name: Cosine Accuracy@10
493
+ - type: cosine_precision@1
494
+ value: 0.08
495
+ name: Cosine Precision@1
496
+ - type: cosine_precision@3
497
+ value: 0.06
498
+ name: Cosine Precision@3
499
+ - type: cosine_precision@5
500
+ value: 0.04
501
+ name: Cosine Precision@5
502
+ - type: cosine_precision@10
503
+ value: 0.042
504
+ name: Cosine Precision@10
505
+ - type: cosine_recall@1
506
+ value: 0.08
507
+ name: Cosine Recall@1
508
+ - type: cosine_recall@3
509
+ value: 0.17
510
+ name: Cosine Recall@3
511
+ - type: cosine_recall@5
512
+ value: 0.19
513
+ name: Cosine Recall@5
514
+ - type: cosine_recall@10
515
+ value: 0.4
516
+ name: Cosine Recall@10
517
+ - type: cosine_ndcg@10
518
+ value: 0.2051878697694875
519
+ name: Cosine Ndcg@10
520
+ - type: cosine_mrr@10
521
+ value: 0.1506904761904762
522
+ name: Cosine Mrr@10
523
+ - type: cosine_map@100
524
+ value: 0.16101738947158584
525
+ name: Cosine Map@100
526
+ - task:
527
+ type: information-retrieval
528
+ name: Information Retrieval
529
+ dataset:
530
+ name: NanoQuoraRetrieval
531
+ type: NanoQuoraRetrieval
532
+ metrics:
533
+ - type: cosine_accuracy@1
534
+ value: 0.7
535
+ name: Cosine Accuracy@1
536
+ - type: cosine_accuracy@3
537
+ value: 0.82
538
+ name: Cosine Accuracy@3
539
+ - type: cosine_accuracy@5
540
+ value: 0.88
541
+ name: Cosine Accuracy@5
542
+ - type: cosine_accuracy@10
543
+ value: 0.94
544
+ name: Cosine Accuracy@10
545
+ - type: cosine_precision@1
546
+ value: 0.7
547
+ name: Cosine Precision@1
548
+ - type: cosine_precision@3
549
+ value: 0.32
550
+ name: Cosine Precision@3
551
+ - type: cosine_precision@5
552
+ value: 0.22399999999999998
553
+ name: Cosine Precision@5
554
+ - type: cosine_precision@10
555
+ value: 0.11799999999999997
556
+ name: Cosine Precision@10
557
+ - type: cosine_recall@1
558
+ value: 0.624
559
+ name: Cosine Recall@1
560
+ - type: cosine_recall@3
561
+ value: 0.7719999999999999
562
+ name: Cosine Recall@3
563
+ - type: cosine_recall@5
564
+ value: 0.866
565
+ name: Cosine Recall@5
566
+ - type: cosine_recall@10
567
+ value: 0.8993333333333333
568
+ name: Cosine Recall@10
569
+ - type: cosine_ndcg@10
570
+ value: 0.7992844609162323
571
+ name: Cosine Ndcg@10
572
+ - type: cosine_mrr@10
573
+ value: 0.7798333333333335
574
+ name: Cosine Mrr@10
575
+ - type: cosine_map@100
576
+ value: 0.7635205205527187
577
+ name: Cosine Map@100
578
+ - task:
579
+ type: information-retrieval
580
+ name: Information Retrieval
581
+ dataset:
582
+ name: NanoSCIDOCS
583
+ type: NanoSCIDOCS
584
+ metrics:
585
+ - type: cosine_accuracy@1
586
+ value: 0.18
587
+ name: Cosine Accuracy@1
588
+ - type: cosine_accuracy@3
589
+ value: 0.26
590
+ name: Cosine Accuracy@3
591
+ - type: cosine_accuracy@5
592
+ value: 0.32
593
+ name: Cosine Accuracy@5
594
+ - type: cosine_accuracy@10
595
+ value: 0.4
596
+ name: Cosine Accuracy@10
597
+ - type: cosine_precision@1
598
+ value: 0.18
599
+ name: Cosine Precision@1
600
+ - type: cosine_precision@3
601
+ value: 0.12
602
+ name: Cosine Precision@3
603
+ - type: cosine_precision@5
604
+ value: 0.09200000000000001
605
+ name: Cosine Precision@5
606
+ - type: cosine_precision@10
607
+ value: 0.066
608
+ name: Cosine Precision@10
609
+ - type: cosine_recall@1
610
+ value: 0.036000000000000004
611
+ name: Cosine Recall@1
612
+ - type: cosine_recall@3
613
+ value: 0.07466666666666667
614
+ name: Cosine Recall@3
615
+ - type: cosine_recall@5
616
+ value: 0.09466666666666666
617
+ name: Cosine Recall@5
618
+ - type: cosine_recall@10
619
+ value: 0.13466666666666666
620
+ name: Cosine Recall@10
621
+ - type: cosine_ndcg@10
622
+ value: 0.1348403477257659
623
+ name: Cosine Ndcg@10
624
+ - type: cosine_mrr@10
625
+ value: 0.24209523809523809
626
+ name: Cosine Mrr@10
627
+ - type: cosine_map@100
628
+ value: 0.10255365352032365
629
+ name: Cosine Map@100
630
+ - task:
631
+ type: information-retrieval
632
+ name: Information Retrieval
633
+ dataset:
634
+ name: NanoArguAna
635
+ type: NanoArguAna
636
+ metrics:
637
+ - type: cosine_accuracy@1
638
+ value: 0.08
639
+ name: Cosine Accuracy@1
640
+ - type: cosine_accuracy@3
641
+ value: 0.26
642
+ name: Cosine Accuracy@3
643
+ - type: cosine_accuracy@5
644
+ value: 0.32
645
+ name: Cosine Accuracy@5
646
+ - type: cosine_accuracy@10
647
+ value: 0.4
648
+ name: Cosine Accuracy@10
649
+ - type: cosine_precision@1
650
+ value: 0.08
651
+ name: Cosine Precision@1
652
+ - type: cosine_precision@3
653
+ value: 0.08666666666666666
654
+ name: Cosine Precision@3
655
+ - type: cosine_precision@5
656
+ value: 0.06400000000000002
657
+ name: Cosine Precision@5
658
+ - type: cosine_precision@10
659
+ value: 0.04
660
+ name: Cosine Precision@10
661
+ - type: cosine_recall@1
662
+ value: 0.08
663
+ name: Cosine Recall@1
664
+ - type: cosine_recall@3
665
+ value: 0.26
666
+ name: Cosine Recall@3
667
+ - type: cosine_recall@5
668
+ value: 0.32
669
+ name: Cosine Recall@5
670
+ - type: cosine_recall@10
671
+ value: 0.4
672
+ name: Cosine Recall@10
673
+ - type: cosine_ndcg@10
674
+ value: 0.2375425714519515
675
+ name: Cosine Ndcg@10
676
+ - type: cosine_mrr@10
677
+ value: 0.1856666666666667
678
+ name: Cosine Mrr@10
679
+ - type: cosine_map@100
680
+ value: 0.1985205474177431
681
+ name: Cosine Map@100
682
+ - task:
683
+ type: information-retrieval
684
+ name: Information Retrieval
685
+ dataset:
686
+ name: NanoSciFact
687
+ type: NanoSciFact
688
+ metrics:
689
+ - type: cosine_accuracy@1
690
+ value: 0.08
691
+ name: Cosine Accuracy@1
692
+ - type: cosine_accuracy@3
693
+ value: 0.22
694
+ name: Cosine Accuracy@3
695
+ - type: cosine_accuracy@5
696
+ value: 0.3
697
+ name: Cosine Accuracy@5
698
+ - type: cosine_accuracy@10
699
+ value: 0.32
700
+ name: Cosine Accuracy@10
701
+ - type: cosine_precision@1
702
+ value: 0.08
703
+ name: Cosine Precision@1
704
+ - type: cosine_precision@3
705
+ value: 0.07333333333333333
706
+ name: Cosine Precision@3
707
+ - type: cosine_precision@5
708
+ value: 0.064
709
+ name: Cosine Precision@5
710
+ - type: cosine_precision@10
711
+ value: 0.034
712
+ name: Cosine Precision@10
713
+ - type: cosine_recall@1
714
+ value: 0.08
715
+ name: Cosine Recall@1
716
+ - type: cosine_recall@3
717
+ value: 0.195
718
+ name: Cosine Recall@3
719
+ - type: cosine_recall@5
720
+ value: 0.28
721
+ name: Cosine Recall@5
722
+ - type: cosine_recall@10
723
+ value: 0.3
724
+ name: Cosine Recall@10
725
+ - type: cosine_ndcg@10
726
+ value: 0.19370675821369307
727
+ name: Cosine Ndcg@10
728
+ - type: cosine_mrr@10
729
+ value: 0.16466666666666668
730
+ name: Cosine Mrr@10
731
+ - type: cosine_map@100
732
+ value: 0.1653693334513147
733
+ name: Cosine Map@100
734
+ - task:
735
+ type: information-retrieval
736
+ name: Information Retrieval
737
+ dataset:
738
+ name: NanoTouche2020
739
+ type: NanoTouche2020
740
+ metrics:
741
+ - type: cosine_accuracy@1
742
+ value: 0.20408163265306123
743
+ name: Cosine Accuracy@1
744
+ - type: cosine_accuracy@3
745
+ value: 0.5102040816326531
746
+ name: Cosine Accuracy@3
747
+ - type: cosine_accuracy@5
748
+ value: 0.7551020408163265
749
+ name: Cosine Accuracy@5
750
+ - type: cosine_accuracy@10
751
+ value: 0.8775510204081632
752
+ name: Cosine Accuracy@10
753
+ - type: cosine_precision@1
754
+ value: 0.20408163265306123
755
+ name: Cosine Precision@1
756
+ - type: cosine_precision@3
757
+ value: 0.25170068027210885
758
+ name: Cosine Precision@3
759
+ - type: cosine_precision@5
760
+ value: 0.25306122448979596
761
+ name: Cosine Precision@5
762
+ - type: cosine_precision@10
763
+ value: 0.24489795918367346
764
+ name: Cosine Precision@10
765
+ - type: cosine_recall@1
766
+ value: 0.014397370082893721
767
+ name: Cosine Recall@1
768
+ - type: cosine_recall@3
769
+ value: 0.04876234248655414
770
+ name: Cosine Recall@3
771
+ - type: cosine_recall@5
772
+ value: 0.0792610922160282
773
+ name: Cosine Recall@5
774
+ - type: cosine_recall@10
775
+ value: 0.14648888406884147
776
+ name: Cosine Recall@10
777
+ - type: cosine_ndcg@10
778
+ value: 0.2485959675297849
779
+ name: Cosine Ndcg@10
780
+ - type: cosine_mrr@10
781
+ value: 0.4082118561710398
782
+ name: Cosine Mrr@10
783
+ - type: cosine_map@100
784
+ value: 0.16376385142142616
785
+ name: Cosine Map@100
786
+ - task:
787
+ type: nano-beir
788
+ name: Nano BEIR
789
+ dataset:
790
+ name: NanoBEIR mean
791
+ type: NanoBEIR_mean
792
+ metrics:
793
+ - type: cosine_accuracy@1
794
+ value: 0.20646781789638935
795
+ name: Cosine Accuracy@1
796
+ - type: cosine_accuracy@3
797
+ value: 0.33924646781789636
798
+ name: Cosine Accuracy@3
799
+ - type: cosine_accuracy@5
800
+ value: 0.41039246467817886
801
+ name: Cosine Accuracy@5
802
+ - type: cosine_accuracy@10
803
+ value: 0.5121193092621665
804
+ name: Cosine Accuracy@10
805
+ - type: cosine_precision@1
806
+ value: 0.20646781789638935
807
+ name: Cosine Precision@1
808
+ - type: cosine_precision@3
809
+ value: 0.1419256933542648
810
+ name: Cosine Precision@3
811
+ - type: cosine_precision@5
812
+ value: 0.11762009419152278
813
+ name: Cosine Precision@5
814
+ - type: cosine_precision@10
815
+ value: 0.08822291993720567
816
+ name: Cosine Precision@10
817
+ - type: cosine_recall@1
818
+ value: 0.10809127782506864
819
+ name: Cosine Recall@1
820
+ - type: cosine_recall@3
821
+ value: 0.19128922256356135
822
+ name: Cosine Recall@3
823
+ - type: cosine_recall@5
824
+ value: 0.2362967591905488
825
+ name: Cosine Recall@5
826
+ - type: cosine_recall@10
827
+ value: 0.30153648743329886
828
+ name: Cosine Recall@10
829
+ - type: cosine_ndcg@10
830
+ value: 0.25241711140675877
831
+ name: Cosine Ndcg@10
832
+ - type: cosine_mrr@10
833
+ value: 0.2947898009020458
834
+ name: Cosine Mrr@10
835
+ - type: cosine_map@100
836
+ value: 0.2040229677928606
837
+ name: Cosine Map@100
838
+ ---
839
+
840
+ # stsb-bert-tiny adapter finetuned on GooAQ pairs
841
+
842
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers-testing/stsb-bert-tiny-safetensors](https://huggingface.co/sentence-transformers-testing/stsb-bert-tiny-safetensors) on the [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) dataset. It maps sentences & paragraphs to a 128-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
843
+
844
+ ## Model Details
845
+
846
+ ### Model Description
847
+ - **Model Type:** Sentence Transformer
848
+ - **Base model:** [sentence-transformers-testing/stsb-bert-tiny-safetensors](https://huggingface.co/sentence-transformers-testing/stsb-bert-tiny-safetensors) <!-- at revision f3cb857cba53019a20df283396bcca179cf051a4 -->
849
+ - **Maximum Sequence Length:** 512 tokens
850
+ - **Output Dimensionality:** 128 dimensions
851
+ - **Similarity Function:** Cosine Similarity
852
+ - **Training Dataset:**
853
+ - [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq)
854
+ - **Language:** en
855
+ - **License:** apache-2.0
856
+
857
+ ### Model Sources
858
+
859
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
860
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
861
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
862
+
863
+ ### Full Model Architecture
864
+
865
+ ```
866
+ SentenceTransformer(
867
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
868
+ (1): Pooling({'word_embedding_dimension': 128, '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})
869
+ )
870
+ ```
871
+
872
+ ## Usage
873
+
874
+ ### Direct Usage (Sentence Transformers)
875
+
876
+ First install the Sentence Transformers library:
877
+
878
+ ```bash
879
+ pip install -U sentence-transformers
880
+ ```
881
+
882
+ Then you can load this model and run inference.
883
+ ```python
884
+ from sentence_transformers import SentenceTransformer
885
+
886
+ # Download from the 🤗 Hub
887
+ model = SentenceTransformer("sentence-transformers-testing/stsb-bert-tiny-lora")
888
+ # Run inference
889
+ sentences = [
890
+ "how to reverse a video on tiktok that's not yours?",
891
+ '[\'Tap "Effects" at the bottom of your screen — it\\\'s an icon that looks like a clock. Open the Effects menu. ... \', \'At the end of the new list that appears, tap "Time." Select "Time" at the end. ... \', \'Select "Reverse" — you\\\'ll then see a preview of your new, reversed video appear on the screen.\']',
892
+ 'Relative age is the age of a rock layer (or the fossils it contains) compared to other layers. It can be determined by looking at the position of rock layers. Absolute age is the numeric age of a layer of rocks or fossils. Absolute age can be determined by using radiometric dating.',
893
+ ]
894
+ embeddings = model.encode(sentences)
895
+ print(embeddings.shape)
896
+ # [3, 128]
897
+
898
+ # Get the similarity scores for the embeddings
899
+ similarities = model.similarity(embeddings, embeddings)
900
+ print(similarities.shape)
901
+ # [3, 3]
902
+ ```
903
+
904
+ <!--
905
+ ### Direct Usage (Transformers)
906
+
907
+ <details><summary>Click to see the direct usage in Transformers</summary>
908
+
909
+ </details>
910
+ -->
911
+
912
+ <!--
913
+ ### Downstream Usage (Sentence Transformers)
914
+
915
+ You can finetune this model on your own dataset.
916
+
917
+ <details><summary>Click to expand</summary>
918
+
919
+ </details>
920
+ -->
921
+
922
+ <!--
923
+ ### Out-of-Scope Use
924
+
925
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
926
+ -->
927
+
928
+ ## Evaluation
929
+
930
+ ### Metrics
931
+
932
+ #### Information Retrieval
933
+
934
+ * Datasets: `NanoClimateFEVER`, `NanoDBPedia`, `NanoFEVER`, `NanoFiQA2018`, `NanoHotpotQA`, `NanoMSMARCO`, `NanoNFCorpus`, `NanoNQ`, `NanoQuoraRetrieval`, `NanoSCIDOCS`, `NanoArguAna`, `NanoSciFact` and `NanoTouche2020`
935
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
936
+
937
+ | Metric | NanoClimateFEVER | NanoDBPedia | NanoFEVER | NanoFiQA2018 | NanoHotpotQA | NanoMSMARCO | NanoNFCorpus | NanoNQ | NanoQuoraRetrieval | NanoSCIDOCS | NanoArguAna | NanoSciFact | NanoTouche2020 |
938
+ |:--------------------|:-----------------|:------------|:-----------|:-------------|:-------------|:------------|:-------------|:-----------|:-------------------|:------------|:------------|:------------|:---------------|
939
+ | cosine_accuracy@1 | 0.14 | 0.42 | 0.12 | 0.06 | 0.36 | 0.06 | 0.2 | 0.08 | 0.7 | 0.18 | 0.08 | 0.08 | 0.2041 |
940
+ | cosine_accuracy@3 | 0.22 | 0.62 | 0.18 | 0.1 | 0.52 | 0.26 | 0.26 | 0.18 | 0.82 | 0.26 | 0.26 | 0.22 | 0.5102 |
941
+ | cosine_accuracy@5 | 0.26 | 0.72 | 0.22 | 0.2 | 0.54 | 0.32 | 0.3 | 0.2 | 0.88 | 0.32 | 0.32 | 0.3 | 0.7551 |
942
+ | cosine_accuracy@10 | 0.38 | 0.86 | 0.36 | 0.28 | 0.62 | 0.36 | 0.44 | 0.42 | 0.94 | 0.4 | 0.4 | 0.32 | 0.8776 |
943
+ | cosine_precision@1 | 0.14 | 0.42 | 0.12 | 0.06 | 0.36 | 0.06 | 0.2 | 0.08 | 0.7 | 0.18 | 0.08 | 0.08 | 0.2041 |
944
+ | cosine_precision@3 | 0.08 | 0.34 | 0.06 | 0.04 | 0.2067 | 0.0867 | 0.12 | 0.06 | 0.32 | 0.12 | 0.0867 | 0.0733 | 0.2517 |
945
+ | cosine_precision@5 | 0.056 | 0.344 | 0.044 | 0.048 | 0.14 | 0.064 | 0.096 | 0.04 | 0.224 | 0.092 | 0.064 | 0.064 | 0.2531 |
946
+ | cosine_precision@10 | 0.05 | 0.29 | 0.036 | 0.032 | 0.078 | 0.036 | 0.08 | 0.042 | 0.118 | 0.066 | 0.04 | 0.034 | 0.2449 |
947
+ | cosine_recall@1 | 0.0567 | 0.0263 | 0.12 | 0.044 | 0.18 | 0.06 | 0.0038 | 0.08 | 0.624 | 0.036 | 0.08 | 0.08 | 0.0144 |
948
+ | cosine_recall@3 | 0.0867 | 0.0604 | 0.18 | 0.062 | 0.31 | 0.26 | 0.0073 | 0.17 | 0.772 | 0.0747 | 0.26 | 0.195 | 0.0488 |
949
+ | cosine_recall@5 | 0.1117 | 0.1027 | 0.22 | 0.1249 | 0.35 | 0.32 | 0.0127 | 0.19 | 0.866 | 0.0947 | 0.32 | 0.28 | 0.0793 |
950
+ | cosine_recall@10 | 0.1783 | 0.1961 | 0.34 | 0.1557 | 0.39 | 0.36 | 0.0193 | 0.4 | 0.8993 | 0.1347 | 0.4 | 0.3 | 0.1465 |
951
+ | **cosine_ndcg@10** | **0.1412** | **0.3415** | **0.2122** | **0.104** | **0.3505** | **0.2142** | **0.0987** | **0.2052** | **0.7993** | **0.1348** | **0.2375** | **0.1937** | **0.2486** |
952
+ | cosine_mrr@10 | 0.1994 | 0.5504 | 0.1749 | 0.1082 | 0.4476 | 0.1667 | 0.2539 | 0.1507 | 0.7798 | 0.2421 | 0.1857 | 0.1647 | 0.4082 |
953
+ | cosine_map@100 | 0.1136 | 0.2113 | 0.1886 | 0.0804 | 0.2931 | 0.1916 | 0.0189 | 0.161 | 0.7635 | 0.1026 | 0.1985 | 0.1654 | 0.1638 |
954
+
955
+ #### Nano BEIR
956
+
957
+ * Dataset: `NanoBEIR_mean`
958
+ * Evaluated with [<code>NanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.NanoBEIREvaluator)
959
+
960
+ | Metric | Value |
961
+ |:--------------------|:-----------|
962
+ | cosine_accuracy@1 | 0.2065 |
963
+ | cosine_accuracy@3 | 0.3392 |
964
+ | cosine_accuracy@5 | 0.4104 |
965
+ | cosine_accuracy@10 | 0.5121 |
966
+ | cosine_precision@1 | 0.2065 |
967
+ | cosine_precision@3 | 0.1419 |
968
+ | cosine_precision@5 | 0.1176 |
969
+ | cosine_precision@10 | 0.0882 |
970
+ | cosine_recall@1 | 0.1081 |
971
+ | cosine_recall@3 | 0.1913 |
972
+ | cosine_recall@5 | 0.2363 |
973
+ | cosine_recall@10 | 0.3015 |
974
+ | **cosine_ndcg@10** | **0.2524** |
975
+ | cosine_mrr@10 | 0.2948 |
976
+ | cosine_map@100 | 0.204 |
977
+
978
+ <!--
979
+ ## Bias, Risks and Limitations
980
+
981
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
982
+ -->
983
+
984
+ <!--
985
+ ### Recommendations
986
+
987
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
988
+ -->
989
+
990
+ ## Training Details
991
+
992
+ ### Training Dataset
993
+
994
+ #### gooaq
995
+
996
+ * Dataset: [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) at [b089f72](https://huggingface.co/datasets/sentence-transformers/gooaq/tree/b089f728748a068b7bc5234e5bcf5b25e3c8279c)
997
+ * Size: 3,012,496 training samples
998
+ * Columns: <code>question</code> and <code>answer</code>
999
+ * Approximate statistics based on the first 1000 samples:
1000
+ | | question | answer |
1001
+ |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
1002
+ | type | string | string |
1003
+ | details | <ul><li>min: 8 tokens</li><li>mean: 11.86 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 60.48 tokens</li><li>max: 138 tokens</li></ul> |
1004
+ * Samples:
1005
+ | question | answer |
1006
+ |:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
1007
+ | <code>what is the difference between broilers and layers?</code> | <code>An egg laying poultry is called egger or layer whereas broilers are reared for obtaining meat. So a layer should be able to produce more number of large sized eggs, without growing too much. On the other hand, a broiler should yield more meat and hence should be able to grow well.</code> |
1008
+ | <code>what is the difference between chronological order and spatial order?</code> | <code>As a writer, you should always remember that unlike chronological order and the other organizational methods for data, spatial order does not take into account the time. Spatial order is primarily focused on the location. All it does is take into account the location of objects and not the time.</code> |
1009
+ | <code>is kamagra same as viagra?</code> | <code>Kamagra is thought to contain the same active ingredient as Viagra, sildenafil citrate. In theory, it should work in much the same way as Viagra, taking about 45 minutes to take effect, and lasting for around 4-6 hours. However, this will vary from person to person.</code> |
1010
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
1011
+ ```json
1012
+ {
1013
+ "scale": 20.0,
1014
+ "similarity_fct": "cos_sim"
1015
+ }
1016
+ ```
1017
+
1018
+ ### Evaluation Dataset
1019
+
1020
+ #### gooaq
1021
+
1022
+ * Dataset: [gooaq](https://huggingface.co/datasets/sentence-transformers/gooaq) at [b089f72](https://huggingface.co/datasets/sentence-transformers/gooaq/tree/b089f728748a068b7bc5234e5bcf5b25e3c8279c)
1023
+ * Size: 3,012,496 evaluation samples
1024
+ * Columns: <code>question</code> and <code>answer</code>
1025
+ * Approximate statistics based on the first 1000 samples:
1026
+ | | question | answer |
1027
+ |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
1028
+ | type | string | string |
1029
+ | details | <ul><li>min: 8 tokens</li><li>mean: 11.88 tokens</li><li>max: 22 tokens</li></ul> | <ul><li>min: 14 tokens</li><li>mean: 61.03 tokens</li><li>max: 127 tokens</li></ul> |
1030
+ * Samples:
1031
+ | question | answer |
1032
+ |:-----------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
1033
+ | <code>how do i program my directv remote with my tv?</code> | <code>['Press MENU on your remote.', 'Select Settings & Help > Settings > Remote Control > Program Remote.', 'Choose the device (TV, audio, DVD) you wish to program. ... ', 'Follow the on-screen prompts to complete programming.']</code> |
1034
+ | <code>are rodrigues fruit bats nocturnal?</code> | <code>Before its numbers were threatened by habitat destruction, storms, and hunting, some of those groups could number 500 or more members. Sunrise, sunset. Rodrigues fruit bats are most active at dawn, at dusk, and at night.</code> |
1035
+ | <code>why does your heart rate increase during exercise bbc bitesize?</code> | <code>During exercise there is an increase in physical activity and muscle cells respire more than they do when the body is at rest. The heart rate increases during exercise. The rate and depth of breathing increases - this makes sure that more oxygen is absorbed into the blood, and more carbon dioxide is removed from it.</code> |
1036
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
1037
+ ```json
1038
+ {
1039
+ "scale": 20.0,
1040
+ "similarity_fct": "cos_sim"
1041
+ }
1042
+ ```
1043
+
1044
+ ### Training Hyperparameters
1045
+ #### Non-Default Hyperparameters
1046
+
1047
+ - `eval_strategy`: steps
1048
+ - `per_device_train_batch_size`: 1024
1049
+ - `per_device_eval_batch_size`: 1024
1050
+ - `learning_rate`: 2e-05
1051
+ - `num_train_epochs`: 1
1052
+ - `warmup_ratio`: 0.1
1053
+ - `bf16`: True
1054
+ - `batch_sampler`: no_duplicates
1055
+
1056
+ #### All Hyperparameters
1057
+ <details><summary>Click to expand</summary>
1058
+
1059
+ - `overwrite_output_dir`: False
1060
+ - `do_predict`: False
1061
+ - `eval_strategy`: steps
1062
+ - `prediction_loss_only`: True
1063
+ - `per_device_train_batch_size`: 1024
1064
+ - `per_device_eval_batch_size`: 1024
1065
+ - `per_gpu_train_batch_size`: None
1066
+ - `per_gpu_eval_batch_size`: None
1067
+ - `gradient_accumulation_steps`: 1
1068
+ - `eval_accumulation_steps`: None
1069
+ - `torch_empty_cache_steps`: None
1070
+ - `learning_rate`: 2e-05
1071
+ - `weight_decay`: 0.0
1072
+ - `adam_beta1`: 0.9
1073
+ - `adam_beta2`: 0.999
1074
+ - `adam_epsilon`: 1e-08
1075
+ - `max_grad_norm`: 1.0
1076
+ - `num_train_epochs`: 1
1077
+ - `max_steps`: -1
1078
+ - `lr_scheduler_type`: linear
1079
+ - `lr_scheduler_kwargs`: {}
1080
+ - `warmup_ratio`: 0.1
1081
+ - `warmup_steps`: 0
1082
+ - `log_level`: passive
1083
+ - `log_level_replica`: warning
1084
+ - `log_on_each_node`: True
1085
+ - `logging_nan_inf_filter`: True
1086
+ - `save_safetensors`: True
1087
+ - `save_on_each_node`: False
1088
+ - `save_only_model`: False
1089
+ - `restore_callback_states_from_checkpoint`: False
1090
+ - `no_cuda`: False
1091
+ - `use_cpu`: False
1092
+ - `use_mps_device`: False
1093
+ - `seed`: 42
1094
+ - `data_seed`: None
1095
+ - `jit_mode_eval`: False
1096
+ - `use_ipex`: False
1097
+ - `bf16`: True
1098
+ - `fp16`: False
1099
+ - `fp16_opt_level`: O1
1100
+ - `half_precision_backend`: auto
1101
+ - `bf16_full_eval`: False
1102
+ - `fp16_full_eval`: False
1103
+ - `tf32`: None
1104
+ - `local_rank`: 0
1105
+ - `ddp_backend`: None
1106
+ - `tpu_num_cores`: None
1107
+ - `tpu_metrics_debug`: False
1108
+ - `debug`: []
1109
+ - `dataloader_drop_last`: False
1110
+ - `dataloader_num_workers`: 0
1111
+ - `dataloader_prefetch_factor`: None
1112
+ - `past_index`: -1
1113
+ - `disable_tqdm`: False
1114
+ - `remove_unused_columns`: True
1115
+ - `label_names`: None
1116
+ - `load_best_model_at_end`: False
1117
+ - `ignore_data_skip`: False
1118
+ - `fsdp`: []
1119
+ - `fsdp_min_num_params`: 0
1120
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
1121
+ - `fsdp_transformer_layer_cls_to_wrap`: None
1122
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
1123
+ - `deepspeed`: None
1124
+ - `label_smoothing_factor`: 0.0
1125
+ - `optim`: adamw_torch
1126
+ - `optim_args`: None
1127
+ - `adafactor`: False
1128
+ - `group_by_length`: False
1129
+ - `length_column_name`: length
1130
+ - `ddp_find_unused_parameters`: None
1131
+ - `ddp_bucket_cap_mb`: None
1132
+ - `ddp_broadcast_buffers`: False
1133
+ - `dataloader_pin_memory`: True
1134
+ - `dataloader_persistent_workers`: False
1135
+ - `skip_memory_metrics`: True
1136
+ - `use_legacy_prediction_loop`: False
1137
+ - `push_to_hub`: False
1138
+ - `resume_from_checkpoint`: None
1139
+ - `hub_model_id`: None
1140
+ - `hub_strategy`: every_save
1141
+ - `hub_private_repo`: False
1142
+ - `hub_always_push`: False
1143
+ - `gradient_checkpointing`: False
1144
+ - `gradient_checkpointing_kwargs`: None
1145
+ - `include_inputs_for_metrics`: False
1146
+ - `include_for_metrics`: []
1147
+ - `eval_do_concat_batches`: True
1148
+ - `fp16_backend`: auto
1149
+ - `push_to_hub_model_id`: None
1150
+ - `push_to_hub_organization`: None
1151
+ - `mp_parameters`:
1152
+ - `auto_find_batch_size`: False
1153
+ - `full_determinism`: False
1154
+ - `torchdynamo`: None
1155
+ - `ray_scope`: last
1156
+ - `ddp_timeout`: 1800
1157
+ - `torch_compile`: False
1158
+ - `torch_compile_backend`: None
1159
+ - `torch_compile_mode`: None
1160
+ - `dispatch_batches`: None
1161
+ - `split_batches`: None
1162
+ - `include_tokens_per_second`: False
1163
+ - `include_num_input_tokens_seen`: False
1164
+ - `neftune_noise_alpha`: None
1165
+ - `optim_target_modules`: None
1166
+ - `batch_eval_metrics`: False
1167
+ - `eval_on_start`: False
1168
+ - `use_liger_kernel`: False
1169
+ - `eval_use_gather_object`: False
1170
+ - `average_tokens_across_devices`: False
1171
+ - `prompts`: None
1172
+ - `batch_sampler`: no_duplicates
1173
+ - `multi_dataset_batch_sampler`: proportional
1174
+
1175
+ </details>
1176
+
1177
+ ### Training Logs
1178
+ | Epoch | Step | Training Loss | Validation Loss | NanoClimateFEVER_cosine_ndcg@10 | NanoDBPedia_cosine_ndcg@10 | NanoFEVER_cosine_ndcg@10 | NanoFiQA2018_cosine_ndcg@10 | NanoHotpotQA_cosine_ndcg@10 | NanoMSMARCO_cosine_ndcg@10 | NanoNFCorpus_cosine_ndcg@10 | NanoNQ_cosine_ndcg@10 | NanoQuoraRetrieval_cosine_ndcg@10 | NanoSCIDOCS_cosine_ndcg@10 | NanoArguAna_cosine_ndcg@10 | NanoSciFact_cosine_ndcg@10 | NanoTouche2020_cosine_ndcg@10 | NanoBEIR_mean_cosine_ndcg@10 |
1179
+ |:------:|:----:|:-------------:|:---------------:|:-------------------------------:|:--------------------------:|:------------------------:|:---------------------------:|:---------------------------:|:--------------------------:|:---------------------------:|:---------------------:|:---------------------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:-----------------------------:|:----------------------------:|
1180
+ | 0 | 0 | - | - | 0.1174 | 0.3053 | 0.1405 | 0.0440 | 0.2821 | 0.2297 | 0.0773 | 0.1708 | 0.7830 | 0.1181 | 0.2017 | 0.1447 | 0.1642 | 0.2138 |
1181
+ | 0.0010 | 1 | 3.6449 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1182
+ | 0.0256 | 25 | 3.6146 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1183
+ | 0.0512 | 50 | 3.6074 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1184
+ | 0.0768 | 75 | 3.5997 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1185
+ | 0.1024 | 100 | 3.5737 | 2.0205 | 0.1178 | 0.3061 | 0.1477 | 0.0461 | 0.2837 | 0.2291 | 0.0804 | 0.1713 | 0.7791 | 0.1205 | 0.2049 | 0.1534 | 0.1731 | 0.2164 |
1186
+ | 0.1279 | 125 | 3.5644 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1187
+ | 0.1535 | 150 | 3.4792 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1188
+ | 0.1791 | 175 | 3.4743 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1189
+ | 0.2047 | 200 | 3.4169 | 1.9114 | 0.1336 | 0.3084 | 0.1446 | 0.0604 | 0.2965 | 0.2350 | 0.0847 | 0.1650 | 0.7806 | 0.1270 | 0.2141 | 0.1633 | 0.1835 | 0.2228 |
1190
+ | 0.2303 | 225 | 3.3535 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1191
+ | 0.2559 | 250 | 3.3336 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1192
+ | 0.2815 | 275 | 3.3038 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1193
+ | 0.3071 | 300 | 3.2576 | 1.8114 | 0.1359 | 0.3260 | 0.1733 | 0.0752 | 0.3167 | 0.2323 | 0.0851 | 0.1753 | 0.7843 | 0.1266 | 0.2218 | 0.1752 | 0.2012 | 0.2330 |
1194
+ | 0.3327 | 325 | 3.2304 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1195
+ | 0.3582 | 350 | 3.2133 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1196
+ | 0.3838 | 375 | 3.1369 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1197
+ | 0.4094 | 400 | 3.1412 | 1.7379 | 0.1389 | 0.3298 | 0.1930 | 0.0934 | 0.3261 | 0.2310 | 0.0852 | 0.1760 | 0.7850 | 0.1349 | 0.2235 | 0.1863 | 0.2118 | 0.2396 |
1198
+ | 0.4350 | 425 | 3.0782 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1199
+ | 0.4606 | 450 | 3.0948 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1200
+ | 0.4862 | 475 | 3.0696 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1201
+ | 0.5118 | 500 | 3.0641 | 1.6850 | 0.1373 | 0.3307 | 0.1945 | 0.0937 | 0.3301 | 0.2365 | 0.0931 | 0.1950 | 0.7933 | 0.1359 | 0.2231 | 0.1885 | 0.2289 | 0.2447 |
1202
+ | 0.5374 | 525 | 3.0224 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1203
+ | 0.5629 | 550 | 2.9927 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1204
+ | 0.5885 | 575 | 2.9796 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1205
+ | 0.6141 | 600 | 2.9624 | 1.6475 | 0.1397 | 0.3321 | 0.2058 | 0.0999 | 0.3422 | 0.2276 | 0.1014 | 0.1901 | 0.7971 | 0.1393 | 0.2258 | 0.1918 | 0.2342 | 0.2482 |
1206
+ | 0.6397 | 625 | 2.9508 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1207
+ | 0.6653 | 650 | 2.958 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1208
+ | 0.6909 | 675 | 2.9428 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1209
+ | 0.7165 | 700 | 2.9589 | 1.6209 | 0.1425 | 0.3344 | 0.2061 | 0.1050 | 0.3427 | 0.2295 | 0.1001 | 0.1868 | 0.7955 | 0.1342 | 0.2298 | 0.1922 | 0.2343 | 0.2487 |
1210
+ | 0.7421 | 725 | 2.9152 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1211
+ | 0.7677 | 750 | 2.9056 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1212
+ | 0.7932 | 775 | 2.9111 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1213
+ | 0.8188 | 800 | 2.9107 | 1.6037 | 0.1415 | 0.3401 | 0.2064 | 0.1053 | 0.3523 | 0.2153 | 0.1001 | 0.1934 | 0.7976 | 0.1340 | 0.2302 | 0.1946 | 0.2461 | 0.2505 |
1214
+ | 0.8444 | 825 | 2.8675 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1215
+ | 0.8700 | 850 | 2.9175 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1216
+ | 0.8956 | 875 | 2.8592 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1217
+ | 0.9212 | 900 | 2.86 | 1.5941 | 0.1411 | 0.3415 | 0.2180 | 0.1048 | 0.3506 | 0.2210 | 0.0987 | 0.2052 | 0.7988 | 0.1349 | 0.2302 | 0.1946 | 0.2464 | 0.2528 |
1218
+ | 0.9468 | 925 | 2.8603 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1219
+ | 0.9724 | 950 | 2.8909 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1220
+ | 0.9980 | 975 | 2.8819 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - |
1221
+ | 1.0 | 977 | - | - | 0.1412 | 0.3415 | 0.2122 | 0.1040 | 0.3505 | 0.2142 | 0.0987 | 0.2052 | 0.7993 | 0.1348 | 0.2375 | 0.1937 | 0.2486 | 0.2524 |
1222
+
1223
+
1224
+ ### Environmental Impact
1225
+ Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
1226
+ - **Energy Consumed**: 0.025 kWh
1227
+ - **Carbon Emitted**: 0.010 kg of CO2
1228
+ - **Hours Used**: 0.15 hours
1229
+
1230
+ ### Training Hardware
1231
+ - **On Cloud**: No
1232
+ - **GPU Model**: 1 x NVIDIA GeForce RTX 3090
1233
+ - **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
1234
+ - **RAM Size**: 31.78 GB
1235
+
1236
+ ### Framework Versions
1237
+ - Python: 3.11.6
1238
+ - Sentence Transformers: 3.3.0.dev0
1239
+ - Transformers: 4.46.2
1240
+ - PyTorch: 2.5.0+cu121
1241
+ - Accelerate: 1.0.0
1242
+ - Datasets: 2.20.0
1243
+ - Tokenizers: 0.20.3
1244
+
1245
+ ## Citation
1246
+
1247
+ ### BibTeX
1248
+
1249
+ #### Sentence Transformers
1250
+ ```bibtex
1251
+ @inproceedings{reimers-2019-sentence-bert,
1252
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
1253
+ author = "Reimers, Nils and Gurevych, Iryna",
1254
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
1255
+ month = "11",
1256
+ year = "2019",
1257
+ publisher = "Association for Computational Linguistics",
1258
+ url = "https://arxiv.org/abs/1908.10084",
1259
+ }
1260
+ ```
1261
+
1262
+ #### MultipleNegativesRankingLoss
1263
+ ```bibtex
1264
+ @misc{henderson2017efficient,
1265
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
1266
+ 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},
1267
+ year={2017},
1268
+ eprint={1705.00652},
1269
+ archivePrefix={arXiv},
1270
+ primaryClass={cs.CL}
1271
+ }
1272
+ ```
1273
+
1274
+ <!--
1275
+ ## Glossary
1276
+
1277
+ *Clearly define terms in order to be accessible across audiences.*
1278
+ -->
1279
+
1280
+ <!--
1281
+ ## Model Card Authors
1282
+
1283
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
1284
+ -->
1285
+
1286
+ <!--
1287
+ ## Model Card Contact
1288
+
1289
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
1290
+ -->
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "sentence-transformers-testing/stsb-bert-tiny-safetensors",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": false,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "query",
24
+ "value"
25
+ ],
26
+ "task_type": "FEATURE_EXTRACTION",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99dc95d73813bfc4633aec5774b016e7a6209a7dd21189548099ac4d403a443
3
+ size 33848
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.0.dev0",
4
+ "transformers": "4.46.2",
5
+ "pytorch": "2.5.0+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff