tomaarsen HF staff commited on
Commit
3207540
1 Parent(s): 8a4a2da

Add new SentenceTransformer model.

Browse files
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 +1,686 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: microsoft/mpnet-base
3
+ datasets:
4
+ - sentence-transformers/natural-questions
5
+ language:
6
+ - en
7
+ library_name: sentence-transformers
8
+ license: apache-2.0
9
+ metrics:
10
+ - cosine_accuracy@1
11
+ - cosine_accuracy@3
12
+ - cosine_accuracy@5
13
+ - cosine_accuracy@10
14
+ - cosine_precision@1
15
+ - cosine_precision@3
16
+ - cosine_precision@5
17
+ - cosine_precision@10
18
+ - cosine_recall@1
19
+ - cosine_recall@3
20
+ - cosine_recall@5
21
+ - cosine_recall@10
22
+ - cosine_ndcg@10
23
+ - cosine_mrr@10
24
+ - cosine_map@100
25
+ - dot_accuracy@1
26
+ - dot_accuracy@3
27
+ - dot_accuracy@5
28
+ - dot_accuracy@10
29
+ - dot_precision@1
30
+ - dot_precision@3
31
+ - dot_precision@5
32
+ - dot_precision@10
33
+ - dot_recall@1
34
+ - dot_recall@3
35
+ - dot_recall@5
36
+ - dot_recall@10
37
+ - dot_ndcg@10
38
+ - dot_mrr@10
39
+ - dot_map@100
40
+ pipeline_tag: sentence-similarity
41
+ tags:
42
+ - sentence-transformers
43
+ - sentence-similarity
44
+ - feature-extraction
45
+ - generated_from_trainer
46
+ - dataset_size:100231
47
+ - loss:MultipleNegativesSymmetricRankingLoss
48
+ widget:
49
+ - source_sentence: when did the british leave new york city
50
+ sentences:
51
+ - Golden State Warriors The Golden State Warriors are an American professional basketball
52
+ team based in Oakland, California. The Warriors compete in the National Basketball
53
+ Association (NBA) as a member of the league's Western Conference Pacific Division.
54
+ The Warriors play their home games at the Oracle Arena in Oakland. The Warriors
55
+ have reached nine NBA Finals, winning five NBA championships in 1947,[b] 1956,
56
+ 1975, 2015 and 2017. Golden State's five NBA championships are tied for fourth-most
57
+ in NBA history with the San Antonio Spurs, and behind only the Boston Celtics
58
+ (17), Los Angeles Lakers (16) and Chicago Bulls (6). As of 2017, the Warriors
59
+ are the third most valuable NBA franchise according to Forbes, with an estimated
60
+ value of $2.6 billion.[6]
61
+ - Evacuation Day (New York) Evacuation Day on November 25 marks the day in 1783
62
+ when British troops departed from New York City on Manhattan Island, after the
63
+ end of the American Revolutionary War. After this British Army evacuation, General
64
+ George Washington triumphantly led the Continental Army from his former headquarters,
65
+ north of the city, across the Harlem River south down Manhattan through the town
66
+ to The Battery at the foot of Broadway.[1]
67
+ - Biochemical oxygen demand BOD can be used as a gauge of the effectiveness of wastewater
68
+ treatment plants. It is listed as a conventional pollutant in the U.S. Clean Water
69
+ Act.[2]
70
+ - source_sentence: what is the newest generation of the ipad
71
+ sentences:
72
+ - Alex Karev Alex is fired by Dr. Lebackes when Maggie Pierce accidentally reveals
73
+ to him that Karev was thinking about leaving the job. Webber recommended Bailey
74
+ to fill Yang's board seat after she left, so Bailey and Alex fight over the chair.
75
+ They both make presentations to the board and eventually Bailey wins, with a unanimous
76
+ vote in her favor. He is hired back as an attending Peds surgeon and takes over
77
+ full-time as Arizona pursues a fellowship with Dr. Herman. Alex continues to date
78
+ Jo and his friendship with Meredith grows stronger than ever, with him taking
79
+ on the role of her new person. When Derek dies and Meredith runs away, Alex is
80
+ upset by her leaving without telling him where she went and calls her everyday.
81
+ Eventually she calls him, tells him she is okay, and to stop calling. When she
82
+ goes into labor and gives birth to Ellis Shepherd, Alex goes to see her since
83
+ he is her emergency contact. He brings Meredith and her kids back to her house.
84
+ She asks to move back in with him in her old house. Alex sells Meredith back the
85
+ house and he and Jo rent a loft.
86
+ - List of presidents of the United States by age The median age upon accession to
87
+ the presidency is 55 years and 3 months. This is how old Lyndon B. Johnson was
88
+ at the time of his inauguration. The youngest person to assume the office was
89
+ Theodore Roosevelt, who became president at the age of 42 years, 322 days, following
90
+ William McKinley's assassination; the oldest was Donald Trump, who was 70 years,
91
+ 220 days old at his inauguration. The youngest person to be elected president
92
+ was John F. Kennedy, at 43 years, 163 days of age on election day; the oldest
93
+ was Ronald Reagan, who was 73 years, 274 days old at the time of his election
94
+ to a second term.
95
+ - iPad (2018) The iPad (officially sixth-generation iPad) is a 9.7-inch (25cm) tablet
96
+ computer designed, developed, and marketed by Apple Inc. It was announced on March
97
+ 27, 2018 during an education-focused event in Chicago and it is a revision of
98
+ the 2017 model, upgraded with the Apple A10 Fusion SoC and support for styluses
99
+ such as Apple Pencil.[2] The iPad is marketed towards educators and schools.
100
+ - source_sentence: what is the average speed of passenger airplane
101
+ sentences:
102
+ - Fixed exchange-rate system In the 21st century, the currencies associated with
103
+ large economies typically do not fix or peg exchange rates to other currencies.
104
+ The last large economy to use a fixed exchange rate system was the People's Republic
105
+ of China which, in July 2005, adopted a slightly more flexible exchange rate system
106
+ called a managed exchange rate.[2] The European Exchange Rate Mechanism is also
107
+ used on a temporary basis to establish a final conversion rate against the Euro
108
+ (€) from the local currencies of countries joining the Eurozone.
109
+ - Tenth Doctor The Tenth Doctor is an incarnation of the Doctor, the protagonist
110
+ of the BBC science fiction television programme Doctor Who, who is played by David
111
+ Tennant in three series as well as nine specials. As with previous incarnations
112
+ of the Doctor, the character has also appeared in other Doctor Who spin-offs.
113
+ In the programme's narrative, the Doctor is a centuries-old Time Lord alien from
114
+ the planet Gallifrey who travels in time in his TARDIS, frequently with companions.
115
+ When the Doctor is critically injured beyond medical repair, he can regenerate
116
+ his body; in doing so, his physical appearance and personality change, and a new
117
+ actor assumes the role. Tennant's portrayal of the Doctor is of an outwardly charismatic
118
+ and charming adventurer whose likable and easygoing attitude can quickly turn
119
+ to righteous fury when provoked.
120
+ - Cruise (aeronautics) The typical cruising airspeed for a long-distance commercial
121
+ passenger aircraft is approximately 475–500 knots (878–926 km/h; 546–575 mph).
122
+ - source_sentence: when is cars three going to be released
123
+ sentences:
124
+ - Benedict's reagent The color of the obtained precipitate gives an idea about the
125
+ quantity of sugar present in the solution, hence the test is semi-quantitative.
126
+ A greenish precipitate indicates about 0.5 g% concentration; yellow precipitate
127
+ indicates 1 g% concentration; orange indicates 1.5 g% and red indicates 2 g% or
128
+ higher concentration.
129
+ - Cars 3 The film was released on June 16, 2017, has grossed over $362 million worldwide
130
+ and received generally positive reviews, with many critics considering it an improvement
131
+ over its predecessor, as well as praising its emotional story and animation.[7]
132
+ - Sleeping Beauty At the christening of a king and queen's long-wished-for child,
133
+ seven good fairies are invited to be godmothers to the infant princess. The fairies
134
+ attend the banquet at the palace. Each fairy is presented with a golden plate
135
+ and drinking cups adorned with jewels. Soon after, an old fairy enters the palace
136
+ and is seated with a plate of fine china and a crystal drinking glass. This old
137
+ fairy is overlooked because she has been within a tower for many years and everyone
138
+ had believed her to be deceased. Six of the other seven fairies then offer their
139
+ gifts of beauty, wit, grace, dance, song, and goodness to the infant princess.
140
+ The evil fairy is very angry about having been forgotten, and as her gift, enchants
141
+ the infant princess so that she will one day prick her finger on a spindle of
142
+ a spinning wheel and die. The seventh fairy, who hasn't yet given her gift, attempts
143
+ to reverse the evil fairy's curse. However, she can only do so partially. Instead
144
+ of dying, the Princess will fall into a deep sleep for 100 years and be awakened
145
+ by a kiss from a king's son.
146
+ - source_sentence: who was ancient china's main enemy that lived to the north
147
+ sentences:
148
+ - Betty Lynn Elizabeth Ann Theresa "Betty" Lynn[1] (born August 29, 1926) is a former
149
+ American actress. She is best known for her role as Thelma Lou, Deputy Barney
150
+ Fife's girlfriend, on The Andy Griffith Show.
151
+ - Sampath Bank Sampath Bank PLC is a licensed commercial bank incorporated in Sri
152
+ Lanka in 1986 with 229 branches and 373 ATMs island wide. It has won the "Bank
153
+ of the Year" award by "The Banker" of Financial Times Limited – London, for
154
+ the second consecutive year and the "National Business Excellence Awards 2010".[citation
155
+ needed] It has become the third largest private sector bank in Sri Lanka with
156
+ Rs. 453 billion in deposits as of 30 June 2016.[1]
157
+ - 'Sui dynasty The Sui Dynasty (Chinese: 隋朝; pinyin: Suí cháo) was a short-lived
158
+ imperial dynasty of China of pivotal significance. The Sui unified the Northern
159
+ and Southern dynasties and reinstalled the rule of ethnic Han Chinese in the entirety
160
+ of China proper, along with sinicization of former nomadic ethnic minorities (the
161
+ Five Barbarians) within its territory. It was succeeded by the Tang dynasty, which
162
+ largely inherited its foundation.'
163
+ co2_eq_emissions:
164
+ emissions: 165.0033810952838
165
+ energy_consumed: 0.42449841033821234
166
+ source: codecarbon
167
+ training_type: fine-tuning
168
+ on_cloud: false
169
+ cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
170
+ ram_total_size: 31.777088165283203
171
+ hours_used: 1.092
172
+ hardware_used: 1 x NVIDIA GeForce RTX 3090
173
+ model-index:
174
+ - name: MPNet base trained on Natural Questions pairs
175
+ results:
176
+ - task:
177
+ type: information-retrieval
178
+ name: Information Retrieval
179
+ dataset:
180
+ name: natural questions dev
181
+ type: natural-questions-dev
182
+ metrics:
183
+ - type: cosine_accuracy@1
184
+ value: 0.5860619685270257
185
+ name: Cosine Accuracy@1
186
+ - type: cosine_accuracy@3
187
+ value: 0.8133124816733457
188
+ name: Cosine Accuracy@3
189
+ - type: cosine_accuracy@5
190
+ value: 0.8825139282572574
191
+ name: Cosine Accuracy@5
192
+ - type: cosine_accuracy@10
193
+ value: 0.9408659955038609
194
+ name: Cosine Accuracy@10
195
+ - type: cosine_precision@1
196
+ value: 0.5860619685270257
197
+ name: Cosine Precision@1
198
+ - type: cosine_precision@3
199
+ value: 0.2711041605577819
200
+ name: Cosine Precision@3
201
+ - type: cosine_precision@5
202
+ value: 0.1765027856514515
203
+ name: Cosine Precision@5
204
+ - type: cosine_precision@10
205
+ value: 0.09408659955038609
206
+ name: Cosine Precision@10
207
+ - type: cosine_recall@1
208
+ value: 0.5860619685270257
209
+ name: Cosine Recall@1
210
+ - type: cosine_recall@3
211
+ value: 0.8133124816733457
212
+ name: Cosine Recall@3
213
+ - type: cosine_recall@5
214
+ value: 0.8825139282572574
215
+ name: Cosine Recall@5
216
+ - type: cosine_recall@10
217
+ value: 0.9408659955038609
218
+ name: Cosine Recall@10
219
+ - type: cosine_ndcg@10
220
+ value: 0.768255166297218
221
+ name: Cosine Ndcg@10
222
+ - type: cosine_mrr@10
223
+ value: 0.7122767251102616
224
+ name: Cosine Mrr@10
225
+ - type: cosine_map@100
226
+ value: 0.7149616399245906
227
+ name: Cosine Map@100
228
+ - type: dot_accuracy@1
229
+ value: 0.5611377186980745
230
+ name: Dot Accuracy@1
231
+ - type: dot_accuracy@3
232
+ value: 0.7913204965301535
233
+ name: Dot Accuracy@3
234
+ - type: dot_accuracy@5
235
+ value: 0.8638451764245919
236
+ name: Dot Accuracy@5
237
+ - type: dot_accuracy@10
238
+ value: 0.929039194604633
239
+ name: Dot Accuracy@10
240
+ - type: dot_precision@1
241
+ value: 0.5611377186980745
242
+ name: Dot Precision@1
243
+ - type: dot_precision@3
244
+ value: 0.26377349884338447
245
+ name: Dot Precision@3
246
+ - type: dot_precision@5
247
+ value: 0.1727690352849184
248
+ name: Dot Precision@5
249
+ - type: dot_precision@10
250
+ value: 0.09290391946046331
251
+ name: Dot Precision@10
252
+ - type: dot_recall@1
253
+ value: 0.5611377186980745
254
+ name: Dot Recall@1
255
+ - type: dot_recall@3
256
+ value: 0.7913204965301535
257
+ name: Dot Recall@3
258
+ - type: dot_recall@5
259
+ value: 0.8638451764245919
260
+ name: Dot Recall@5
261
+ - type: dot_recall@10
262
+ value: 0.929039194604633
263
+ name: Dot Recall@10
264
+ - type: dot_ndcg@10
265
+ value: 0.748422205969158
266
+ name: Dot Ndcg@10
267
+ - type: dot_mrr@10
268
+ value: 0.6900571403747948
269
+ name: Dot Mrr@10
270
+ - type: dot_map@100
271
+ value: 0.6933908770247191
272
+ name: Dot Map@100
273
+ ---
274
+
275
+ # MPNet base trained on Natural Questions pairs
276
+
277
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) dataset. 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.
278
+
279
+ ## Model Details
280
+
281
+ ### Model Description
282
+ - **Model Type:** Sentence Transformer
283
+ - **Base model:** [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) <!-- at revision 6996ce1e91bd2a9c7d7f61daec37463394f73f09 -->
284
+ - **Maximum Sequence Length:** 512 tokens
285
+ - **Output Dimensionality:** 768 tokens
286
+ - **Similarity Function:** Cosine Similarity
287
+ - **Training Dataset:**
288
+ - [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions)
289
+ - **Language:** en
290
+ - **License:** apache-2.0
291
+
292
+ ### Model Sources
293
+
294
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
295
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
296
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
297
+
298
+ ### Full Model Architecture
299
+
300
+ ```
301
+ SentenceTransformer(
302
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
303
+ (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})
304
+ )
305
+ ```
306
+
307
+ ## Usage
308
+
309
+ ### Direct Usage (Sentence Transformers)
310
+
311
+ First install the Sentence Transformers library:
312
+
313
+ ```bash
314
+ pip install -U sentence-transformers
315
+ ```
316
+
317
+ Then you can load this model and run inference.
318
+ ```python
319
+ from sentence_transformers import SentenceTransformer
320
+
321
+ # Download from the 🤗 Hub
322
+ model = SentenceTransformer("tomaarsen/mpnet-base-natural-questions-mnsrl")
323
+ # Run inference
324
+ sentences = [
325
+ "who was ancient china's main enemy that lived to the north",
326
+ 'Sui dynasty The Sui Dynasty (Chinese: 隋朝; pinyin: Suí cháo) was a short-lived imperial dynasty of China of pivotal significance. The Sui unified the Northern and Southern dynasties and reinstalled the rule of ethnic Han Chinese in the entirety of China proper, along with sinicization of former nomadic ethnic minorities (the Five Barbarians) within its territory. It was succeeded by the Tang dynasty, which largely inherited its foundation.',
327
+ 'Sampath Bank Sampath Bank PLC is a licensed commercial bank incorporated in Sri Lanka in 1986 with 229 branches and 373 ATMs island wide. It has won the "Bank of the Year" award by "The Banker" of Financial Times Limited – London, for the second consecutive year and the "National Business Excellence Awards 2010".[citation needed] It has become the third largest private sector bank in Sri Lanka with Rs. 453 billion in deposits as of 30 June 2016.[1]',
328
+ ]
329
+ embeddings = model.encode(sentences)
330
+ print(embeddings.shape)
331
+ # [3, 768]
332
+
333
+ # Get the similarity scores for the embeddings
334
+ similarities = model.similarity(embeddings, embeddings)
335
+ print(similarities.shape)
336
+ # [3, 3]
337
+ ```
338
+
339
+ <!--
340
+ ### Direct Usage (Transformers)
341
+
342
+ <details><summary>Click to see the direct usage in Transformers</summary>
343
+
344
+ </details>
345
+ -->
346
+
347
+ <!--
348
+ ### Downstream Usage (Sentence Transformers)
349
+
350
+ You can finetune this model on your own dataset.
351
+
352
+ <details><summary>Click to expand</summary>
353
+
354
+ </details>
355
+ -->
356
+
357
+ <!--
358
+ ### Out-of-Scope Use
359
+
360
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
361
+ -->
362
+
363
+ ## Evaluation
364
+
365
+ ### Metrics
366
+
367
+ #### Information Retrieval
368
+ * Dataset: `natural-questions-dev`
369
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
370
+
371
+ | Metric | Value |
372
+ |:--------------------|:----------|
373
+ | cosine_accuracy@1 | 0.5861 |
374
+ | cosine_accuracy@3 | 0.8133 |
375
+ | cosine_accuracy@5 | 0.8825 |
376
+ | cosine_accuracy@10 | 0.9409 |
377
+ | cosine_precision@1 | 0.5861 |
378
+ | cosine_precision@3 | 0.2711 |
379
+ | cosine_precision@5 | 0.1765 |
380
+ | cosine_precision@10 | 0.0941 |
381
+ | cosine_recall@1 | 0.5861 |
382
+ | cosine_recall@3 | 0.8133 |
383
+ | cosine_recall@5 | 0.8825 |
384
+ | cosine_recall@10 | 0.9409 |
385
+ | cosine_ndcg@10 | 0.7683 |
386
+ | cosine_mrr@10 | 0.7123 |
387
+ | **cosine_map@100** | **0.715** |
388
+ | dot_accuracy@1 | 0.5611 |
389
+ | dot_accuracy@3 | 0.7913 |
390
+ | dot_accuracy@5 | 0.8638 |
391
+ | dot_accuracy@10 | 0.929 |
392
+ | dot_precision@1 | 0.5611 |
393
+ | dot_precision@3 | 0.2638 |
394
+ | dot_precision@5 | 0.1728 |
395
+ | dot_precision@10 | 0.0929 |
396
+ | dot_recall@1 | 0.5611 |
397
+ | dot_recall@3 | 0.7913 |
398
+ | dot_recall@5 | 0.8638 |
399
+ | dot_recall@10 | 0.929 |
400
+ | dot_ndcg@10 | 0.7484 |
401
+ | dot_mrr@10 | 0.6901 |
402
+ | dot_map@100 | 0.6934 |
403
+
404
+ <!--
405
+ ## Bias, Risks and Limitations
406
+
407
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
408
+ -->
409
+
410
+ <!--
411
+ ### Recommendations
412
+
413
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
414
+ -->
415
+
416
+ ## Training Details
417
+
418
+ ### Training Dataset
419
+
420
+ #### natural-questions
421
+
422
+ * Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
423
+ * Size: 100,231 training samples
424
+ * Columns: <code>query</code> and <code>answer</code>
425
+ * Approximate statistics based on the first 1000 samples:
426
+ | | query | answer |
427
+ |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
428
+ | type | string | string |
429
+ | details | <ul><li>min: 10 tokens</li><li>mean: 11.74 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 135.66 tokens</li><li>max: 512 tokens</li></ul> |
430
+ * Samples:
431
+ | query | answer |
432
+ |:----------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
433
+ | <code>when did richmond last play in a preliminary final</code> | <code>Richmond Football Club Richmond began 2017 with 5 straight wins, a feat it had not achieved since 1995. A series of close losses hampered the Tigers throughout the middle of the season, including a 5-point loss to the Western Bulldogs, 2-point loss to Fremantle, and a 3-point loss to the Giants. Richmond ended the season strongly with convincing victories over Fremantle and St Kilda in the final two rounds, elevating the club to 3rd on the ladder. Richmond's first final of the season against the Cats at the MCG attracted a record qualifying final crowd of 95,028; the Tigers won by 51 points. Having advanced to the first preliminary finals for the first time since 2001, Richmond defeated Greater Western Sydney by 36 points in front of a crowd of 94,258 to progress to the Grand Final against Adelaide, their first Grand Final appearance since 1982. The attendance was 100,021, the largest crowd to a grand final since 1986. The Crows led at quarter time and led by as many as 13, but the Tigers took over the game as it progressed and scored seven straight goals at one point. They eventually would win by 48 points – 16.12 (108) to Adelaide's 8.12 (60) – to end their 37-year flag drought.[22] Dustin Martin also became the first player to win a Premiership medal, the Brownlow Medal and the Norm Smith Medal in the same season, while Damien Hardwick was named AFL Coaches Association Coach of the Year. Richmond's jump from 13th to premiers also marked the biggest jump from one AFL season to the next.</code> |
434
+ | <code>who sang what in the world's come over you</code> | <code>Jack Scott (singer) At the beginning of 1960, Scott again changed record labels, this time to Top Rank Records.[1] He then recorded four Billboard Hot 100 hits – "What in the World's Come Over You" (#5), "Burning Bridges" (#3) b/w "Oh Little One" (#34), and "It Only Happened Yesterday" (#38).[1] "What in the World's Come Over You" was Scott's second gold disc winner.[6] Scott continued to record and perform during the 1960s and 1970s.[1] His song "You're Just Gettin' Better" reached the country charts in 1974.[1] In May 1977, Scott recorded a Peel session for BBC Radio 1 disc jockey, John Peel.</code> |
435
+ | <code>who produces the most wool in the world</code> | <code>Wool Global wool production is about 2 million tonnes per year, of which 60% goes into apparel. Wool comprises ca 3% of the global textile market, but its value is higher owing to dying and other modifications of the material.[1] Australia is a leading producer of wool which is mostly from Merino sheep but has been eclipsed by China in terms of total weight.[30] New Zealand (2016) is the third-largest producer of wool, and the largest producer of crossbred wool. Breeds such as Lincoln, Romney, Drysdale, and Elliotdale produce coarser fibers, and wool from these sheep is usually used for making carpets.</code> |
436
+ * Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters:
437
+ ```json
438
+ {
439
+ "scale": 20.0,
440
+ "similarity_fct": "cos_sim"
441
+ }
442
+ ```
443
+
444
+ ### Evaluation Dataset
445
+
446
+ #### natural-questions
447
+
448
+ * Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
449
+ * Size: 100,231 evaluation samples
450
+ * Columns: <code>query</code> and <code>answer</code>
451
+ * Approximate statistics based on the first 1000 samples:
452
+ | | query | answer |
453
+ |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
454
+ | type | string | string |
455
+ | details | <ul><li>min: 10 tokens</li><li>mean: 11.79 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 142.78 tokens</li><li>max: 512 tokens</li></ul> |
456
+ * Samples:
457
+ | query | answer |
458
+ |:--------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
459
+ | <code>who betrayed siraj ud daula in the battle of plassey in 1757</code> | <code>Siraj ud-Daulah The Battle of Plassey (or Palashi) is widely considered the turning point in the history of the subcontinent, and opened the way to eventual British domination. After Siraj-ud-Daulah's conquest of Calcutta, the British sent fresh troops from Madras to recapture the fort and avenge the attack. A retreating Siraj-ud-Daulah met the British at Plassey. He had to make camp 27 miles away from Murshidabad. On 23 June 1757 Siraj-ud-Daulah called on Mir Jafar because he was saddened by the sudden fall of Mir Mardan who was a very dear companion of Siraj in battles. The Nawab asked for help from Mir Jafar. Mir Jafar advised Siraj to retreat for that day. The Nawab made the blunder in giving the order to stop the fight. Following his command, the soldiers of the Nawab were returning to their camps. At that time, Robert Clive attacked the soldiers with his army. At such a sudden attack, the army of Siraj became indisciplined and could think of no way to fight. So all fled away in such a situation. Betrayed by a conspiracy plotted by Jagat Seth, Mir Jafar, Krishna Chandra, Omichund etc., he lost the battle and had to escape. He went first to Murshidabad and then to Patna by boat, but was eventually arrested by Mir Jafar's soldiers.</code> |
460
+ | <code>what is the meaning of single malt whisky</code> | <code>Single malt whisky Single malt whisky is malt whisky from a single distillery, that is, whisky distilled from fermented mash made exclusively with malted grain (usually barley), as distinguished from unmalted grain.</code> |
461
+ | <code>when is despicable me 3 going to release</code> | <code>Despicable Me 3 Despicable Me 3 premiered on June 14, 2017, at the Annecy International Animated Film Festival, and was released in the United States on June 30, 2017, by Universal Pictures in 3D, RealD 3D, Dolby Cinema, and IMAX 3D. The film received mixed reviews from critics[7] and has grossed over $1 billion worldwide, making it the third highest-grossing film of 2017, the fifth highest-grossing animated film of all time and the 28th highest-grossing overall. It is Illumination's second film to gross over $1 billion, after Minions in 2015, becoming the first ever animated franchise to do so.</code> |
462
+ * Loss: [<code>MultipleNegativesSymmetricRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativessymmetricrankingloss) with these parameters:
463
+ ```json
464
+ {
465
+ "scale": 20.0,
466
+ "similarity_fct": "cos_sim"
467
+ }
468
+ ```
469
+
470
+ ### Training Hyperparameters
471
+ #### Non-Default Hyperparameters
472
+
473
+ - `eval_strategy`: steps
474
+ - `per_device_train_batch_size`: 32
475
+ - `per_device_eval_batch_size`: 32
476
+ - `learning_rate`: 2e-05
477
+ - `num_train_epochs`: 1
478
+ - `warmup_ratio`: 0.1
479
+ - `bf16`: True
480
+ - `batch_sampler`: no_duplicates
481
+
482
+ #### All Hyperparameters
483
+ <details><summary>Click to expand</summary>
484
+
485
+ - `overwrite_output_dir`: False
486
+ - `do_predict`: False
487
+ - `eval_strategy`: steps
488
+ - `prediction_loss_only`: True
489
+ - `per_device_train_batch_size`: 32
490
+ - `per_device_eval_batch_size`: 32
491
+ - `per_gpu_train_batch_size`: None
492
+ - `per_gpu_eval_batch_size`: None
493
+ - `gradient_accumulation_steps`: 1
494
+ - `eval_accumulation_steps`: None
495
+ - `learning_rate`: 2e-05
496
+ - `weight_decay`: 0.0
497
+ - `adam_beta1`: 0.9
498
+ - `adam_beta2`: 0.999
499
+ - `adam_epsilon`: 1e-08
500
+ - `max_grad_norm`: 1.0
501
+ - `num_train_epochs`: 1
502
+ - `max_steps`: -1
503
+ - `lr_scheduler_type`: linear
504
+ - `lr_scheduler_kwargs`: {}
505
+ - `warmup_ratio`: 0.1
506
+ - `warmup_steps`: 0
507
+ - `log_level`: passive
508
+ - `log_level_replica`: warning
509
+ - `log_on_each_node`: True
510
+ - `logging_nan_inf_filter`: True
511
+ - `save_safetensors`: True
512
+ - `save_on_each_node`: False
513
+ - `save_only_model`: False
514
+ - `restore_callback_states_from_checkpoint`: False
515
+ - `no_cuda`: False
516
+ - `use_cpu`: False
517
+ - `use_mps_device`: False
518
+ - `seed`: 42
519
+ - `data_seed`: None
520
+ - `jit_mode_eval`: False
521
+ - `use_ipex`: False
522
+ - `bf16`: True
523
+ - `fp16`: False
524
+ - `fp16_opt_level`: O1
525
+ - `half_precision_backend`: auto
526
+ - `bf16_full_eval`: False
527
+ - `fp16_full_eval`: False
528
+ - `tf32`: None
529
+ - `local_rank`: 0
530
+ - `ddp_backend`: None
531
+ - `tpu_num_cores`: None
532
+ - `tpu_metrics_debug`: False
533
+ - `debug`: []
534
+ - `dataloader_drop_last`: False
535
+ - `dataloader_num_workers`: 0
536
+ - `dataloader_prefetch_factor`: None
537
+ - `past_index`: -1
538
+ - `disable_tqdm`: False
539
+ - `remove_unused_columns`: True
540
+ - `label_names`: None
541
+ - `load_best_model_at_end`: False
542
+ - `ignore_data_skip`: False
543
+ - `fsdp`: []
544
+ - `fsdp_min_num_params`: 0
545
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
546
+ - `fsdp_transformer_layer_cls_to_wrap`: None
547
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
548
+ - `deepspeed`: None
549
+ - `label_smoothing_factor`: 0.0
550
+ - `optim`: adamw_torch
551
+ - `optim_args`: None
552
+ - `adafactor`: False
553
+ - `group_by_length`: False
554
+ - `length_column_name`: length
555
+ - `ddp_find_unused_parameters`: None
556
+ - `ddp_bucket_cap_mb`: None
557
+ - `ddp_broadcast_buffers`: False
558
+ - `dataloader_pin_memory`: True
559
+ - `dataloader_persistent_workers`: False
560
+ - `skip_memory_metrics`: True
561
+ - `use_legacy_prediction_loop`: False
562
+ - `push_to_hub`: False
563
+ - `resume_from_checkpoint`: None
564
+ - `hub_model_id`: None
565
+ - `hub_strategy`: every_save
566
+ - `hub_private_repo`: False
567
+ - `hub_always_push`: False
568
+ - `gradient_checkpointing`: False
569
+ - `gradient_checkpointing_kwargs`: None
570
+ - `include_inputs_for_metrics`: False
571
+ - `eval_do_concat_batches`: True
572
+ - `fp16_backend`: auto
573
+ - `push_to_hub_model_id`: None
574
+ - `push_to_hub_organization`: None
575
+ - `mp_parameters`:
576
+ - `auto_find_batch_size`: False
577
+ - `full_determinism`: False
578
+ - `torchdynamo`: None
579
+ - `ray_scope`: last
580
+ - `ddp_timeout`: 1800
581
+ - `torch_compile`: False
582
+ - `torch_compile_backend`: None
583
+ - `torch_compile_mode`: None
584
+ - `dispatch_batches`: None
585
+ - `split_batches`: None
586
+ - `include_tokens_per_second`: False
587
+ - `include_num_input_tokens_seen`: False
588
+ - `neftune_noise_alpha`: None
589
+ - `optim_target_modules`: None
590
+ - `batch_eval_metrics`: False
591
+ - `batch_sampler`: no_duplicates
592
+ - `multi_dataset_batch_sampler`: proportional
593
+
594
+ </details>
595
+
596
+ ### Training Logs
597
+ | Epoch | Step | Training Loss | loss | natural-questions-dev_cosine_map@100 |
598
+ |:------:|:----:|:-------------:|:------:|:------------------------------------:|
599
+ | 0 | 0 | - | - | 0.1228 |
600
+ | 0.0004 | 1 | 3.2095 | - | - |
601
+ | 0.0355 | 100 | 1.4827 | 0.1693 | 0.5042 |
602
+ | 0.0711 | 200 | 0.1299 | 0.0592 | 0.6293 |
603
+ | 0.1066 | 300 | 0.0633 | 0.0456 | 0.6516 |
604
+ | 0.1422 | 400 | 0.0516 | 0.0423 | 0.6512 |
605
+ | 0.1777 | 500 | 0.0616 | 0.0352 | 0.6649 |
606
+ | 0.2133 | 600 | 0.0424 | 0.0325 | 0.6758 |
607
+ | 0.2488 | 700 | 0.0475 | 0.0301 | 0.6756 |
608
+ | 0.2844 | 800 | 0.0394 | 0.0311 | 0.6861 |
609
+ | 0.3199 | 900 | 0.0382 | 0.0278 | 0.6868 |
610
+ | 0.3555 | 1000 | 0.0396 | 0.0250 | 0.6932 |
611
+ | 0.3910 | 1100 | 0.0236 | 0.0266 | 0.6861 |
612
+ | 0.4266 | 1200 | 0.0348 | 0.0241 | 0.6945 |
613
+ | 0.4621 | 1300 | 0.0361 | 0.0240 | 0.6958 |
614
+ | 0.4977 | 1400 | 0.0286 | 0.0224 | 0.6954 |
615
+ | 0.5332 | 1500 | 0.024 | 0.0213 | 0.7016 |
616
+ | 0.5688 | 1600 | 0.0325 | 0.0236 | 0.6923 |
617
+ | 0.6043 | 1700 | 0.0385 | 0.0217 | 0.6988 |
618
+ | 0.6399 | 1800 | 0.0258 | 0.0211 | 0.6974 |
619
+ | 0.6754 | 1900 | 0.0282 | 0.0198 | 0.7075 |
620
+ | 0.7110 | 2000 | 0.022 | 0.0201 | 0.7050 |
621
+ | 0.7465 | 2100 | 0.025 | 0.0193 | 0.7042 |
622
+ | 0.7821 | 2200 | 0.0248 | 0.0189 | 0.7069 |
623
+ | 0.8176 | 2300 | 0.0206 | 0.0193 | 0.7079 |
624
+ | 0.8532 | 2400 | 0.0228 | 0.0182 | 0.7122 |
625
+ | 0.8887 | 2500 | 0.0316 | 0.0178 | 0.7117 |
626
+ | 0.9243 | 2600 | 0.0296 | 0.0176 | 0.7130 |
627
+ | 0.9598 | 2700 | 0.025 | 0.0175 | 0.7135 |
628
+ | 0.9954 | 2800 | 0.0217 | 0.0174 | 0.7139 |
629
+ | 1.0 | 2813 | - | - | 0.7150 |
630
+
631
+
632
+ ### Environmental Impact
633
+ Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
634
+ - **Energy Consumed**: 0.424 kWh
635
+ - **Carbon Emitted**: 0.165 kg of CO2
636
+ - **Hours Used**: 1.092 hours
637
+
638
+ ### Training Hardware
639
+ - **On Cloud**: No
640
+ - **GPU Model**: 1 x NVIDIA GeForce RTX 3090
641
+ - **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
642
+ - **RAM Size**: 31.78 GB
643
+
644
+ ### Framework Versions
645
+ - Python: 3.11.6
646
+ - Sentence Transformers: 3.1.0.dev0
647
+ - Transformers: 4.41.2
648
+ - PyTorch: 2.3.1+cu121
649
+ - Accelerate: 0.31.0
650
+ - Datasets: 2.20.0
651
+ - Tokenizers: 0.19.1
652
+
653
+ ## Citation
654
+
655
+ ### BibTeX
656
+
657
+ #### Sentence Transformers
658
+ ```bibtex
659
+ @inproceedings{reimers-2019-sentence-bert,
660
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
661
+ author = "Reimers, Nils and Gurevych, Iryna",
662
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
663
+ month = "11",
664
+ year = "2019",
665
+ publisher = "Association for Computational Linguistics",
666
+ url = "https://arxiv.org/abs/1908.10084",
667
+ }
668
+ ```
669
+
670
+ <!--
671
+ ## Glossary
672
+
673
+ *Clearly define terms in order to be accessible across audiences.*
674
+ -->
675
+
676
+ <!--
677
+ ## Model Card Authors
678
+
679
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
680
+ -->
681
+
682
+ <!--
683
+ ## Model Card Contact
684
+
685
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
686
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mpnet-base",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
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-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.41.2",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.1.0.dev0",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.3.1+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:b91226771a76db743f93d13d6340b9558f94494922725708a08bbec4a10d904b
3
+ size 437967672
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": true,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "mask_token": "<mask>",
58
+ "model_max_length": 512,
59
+ "pad_token": "<pad>",
60
+ "sep_token": "</s>",
61
+ "strip_accents": null,
62
+ "tokenize_chinese_chars": true,
63
+ "tokenizer_class": "MPNetTokenizer",
64
+ "unk_token": "[UNK]"
65
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff