antonkirk commited on
Commit
53919ff
1 Parent(s): f65d90d

Upload folder using huggingface_hub

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md CHANGED
@@ -1,3 +1,868 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: []
3
+ library_name: sentence-transformers
4
+ tags:
5
+ - sentence-transformers
6
+ - sentence-similarity
7
+ - feature-extraction
8
+ - generated_from_trainer
9
+ - dataset_size:95159
10
+ - loss:MultipleNegativesRankingLoss
11
+ base_model: sentence-transformers/multi-qa-mpnet-base-dot-v1
12
+ datasets: []
13
+ metrics:
14
+ - cosine_accuracy@1
15
+ - cosine_accuracy@3
16
+ - cosine_accuracy@5
17
+ - cosine_accuracy@10
18
+ - cosine_precision@1
19
+ - cosine_precision@3
20
+ - cosine_precision@5
21
+ - cosine_precision@10
22
+ - cosine_recall@1
23
+ - cosine_recall@3
24
+ - cosine_recall@5
25
+ - cosine_recall@10
26
+ - cosine_ndcg@10
27
+ - cosine_mrr@10
28
+ - cosine_map@100
29
+ - dot_accuracy@1
30
+ - dot_accuracy@3
31
+ - dot_accuracy@5
32
+ - dot_accuracy@10
33
+ - dot_precision@1
34
+ - dot_precision@3
35
+ - dot_precision@5
36
+ - dot_precision@10
37
+ - dot_recall@1
38
+ - dot_recall@3
39
+ - dot_recall@5
40
+ - dot_recall@10
41
+ - dot_ndcg@10
42
+ - dot_mrr@10
43
+ - dot_map@100
44
+ widget:
45
+ - source_sentence: medial deviation, first metatarsal misalignment
46
+ sentences:
47
+ - "Deviation of the first toe away from the rest of the foot\n\nHallux varus \n\
48
+ Other namesSandal gap[1] \nRadiography of the left foot of a young male showing\
49
+ \ progressive hallux varus \nSpecialtyOrthopedic \n \nHallux varus is a deformity\
50
+ \ of the great toe joint where the hallux (great toe) is deviated medially (towards\
51
+ \ the midline of the body) away from the first metatarsal bone. The hallux usually\
52
+ \ moves in the transverse plane. Unlike hallux valgus, also known as hallux abducto\
53
+ \ valgus or bunion, hallux varus is uncommon in the West but it is common in cultures\
54
+ \ where the population remains unshod.\n\n## Photos[edit]\n\n * \n\n## References[edit]\n\
55
+ \n 1. ^ Weerakkody, Yuranga. \"Sandal gap deformity - Radiology Reference Article\
56
+ \ - Radiopaedia.org\". radiopaedia.org.\n\n## External links[edit]\n\nClassification\n\
57
+ \nD\n\n * ICD-10: M20.3, Q66.3\n * ICD-9-CM: 735.1, 755.66\n * MeSH: D050488\n\
58
+ \n \n \n * v\n * t\n * e\n\nAcquired musculoskeletal deformities \n \n\
59
+ Upper limb\n\nshoulder"
60
+ - "Touraine (1955), who first described this condition (Touraine, 1941), discovered\
61
+ \ a total of 32 cases in 17 families examined. In 9 of the families, a parent\
62
+ \ and 1 or more children were affected. In 5 families with a total of 15 cases,\
63
+ \ only 2 or more sibs were affected. He quoted an instance of affected mother\
64
+ \ and 4 children. Mental retardation was frequently associated. In a series of\
65
+ \ 40 reported cases reviewed by Dociu et al. (1976), no lentigines were found\
66
+ \ other than those on the face.\n\n \nInheritance \\- Autosomal dominant Neuro\
67
+ \ \\- Mental retardation Skin \\- Facial lentigines ▲ Close"
68
+ - 'Trisomy 18, also called Edwards syndrome, is a chromosomal condition associated
69
+ with abnormalities in many parts of the body. Individuals with trisomy 18 often
70
+ have slow growth before birth (intrauterine growth retardation) and a low birth
71
+ weight. Affected individuals may have heart defects and abnormalities of other
72
+ organs that develop before birth. Other features of trisomy 18 include a small,
73
+ abnormally shaped head; a small jaw and mouth; and clenched fists with overlapping
74
+ fingers. Due to the presence of several life-threatening medical problems, many
75
+ individuals with trisomy 18 die before birth or within their first month. Five
76
+ to 10 percent of children with this condition live past their first year, and
77
+ these children often have severe intellectual disability.
78
+
79
+
80
+ ## Frequency'
81
+ - source_sentence: hyperreflexia, infantile onset
82
+ sentences:
83
+ - 'Furuncular myiasis in humans is caused by two species: the Cayor worm (larvae
84
+ of the African tumbu fly Cordylobia anthropophaga) and the larvae of the human
85
+ botfly (Dermatobia hominis).
86
+
87
+
88
+ ## Epidemiology
89
+
90
+
91
+ The prevalence is unknown but the cases reported in Europe occur following visits
92
+ to affected regions (Latin America, Sub-Saharan Africa) or in association with
93
+ animal importation.
94
+
95
+
96
+ ## Clinical description
97
+
98
+
99
+ In the case of Cordylobia anthropophaga, the females lay their eggs on damp fabric
100
+ or on the ground. The larvae penetrate the skin following contact with the ground
101
+ or with non-ironed contaminated fabric. Infection becomes evident within 10 to
102
+ 15 days with the formation of a pseudo-furuncle or emergence of a maggot. Dermatobia
103
+ hominis is found in Latin America. Infestation is usually localised to the scalp
104
+ of infected individuals.'
105
+ - A rare ARX-related epileptic encephalopathy characterized by infantile onset of
106
+ myoclonic epilepsy with generalized spasticity, severe global developmental delay,
107
+ and moderate to profound intellectual disability. Obligate female carriers show
108
+ subtle, generalized hyperreflexia. Late onset progressive spastic ataxia has also
109
+ been reported.
110
+ - Intestinal lymphangiectasia is a rare digestive disorder characterized by abnormally
111
+ enlarged lymph vessels supplying the lining of the small intestine. Affected people
112
+ may experience intermittent diarrhea, nausea, vomiting, swelling of the limbs
113
+ and abdominal discomfort. Intestinal lymphangiectasia can be congenital (also
114
+ called primary intestinal lymphangiectasia or Waldmann disease) in which case
115
+ it affects children and young adults (mean age of onset, 11 years); it can also
116
+ be associated with a variety of other conditions and affect older adults. Treatment
117
+ generally involves control of symptoms with dietary and/or behavioral modifications
118
+ and the use of certain medications.
119
+ - source_sentence: mutations in CYLD gene, chromosome 16q12-q13
120
+ sentences:
121
+ - '## Description
122
+
123
+
124
+ Multiple familial trichoepithelioma (MFT) is an autosomal dominant disorder of
125
+ skin appendage tumors characterized by the appearance of trichoepitheliomas.
126
+
127
+
128
+ See also MFT1 (601606), which is caused by mutations in the CYLD gene (605018)
129
+ on chromosome 16q12-q13.
130
+
131
+
132
+ Mapping
133
+
134
+
135
+ In 3 families with multiple familial trichoepithelioma, 2 African American and
136
+ 1 Caucasian, Harada et al. (1996) found linkage of the disorder to a 4-cM region
137
+ between IFNA (147660) and D9S126 on chromosome 9p21; maximum combined lod = 3.31
138
+ at D9S171 at theta = 0.0.'
139
+ - This article has multiple issues. Please help improve it or discuss these issues
140
+ on the talk page. (Learn how and when to remove these template messages)
141
+ - 'Male congenital condition
142
+
143
+
144
+ Buried penis on a circumcised 30 year old male not due to obesity
145
+
146
+
147
+ Buried penis in a circumcised 40 year old male due to obesity
148
+
149
+
150
+ Buried penis (also known as hidden penis or retractile penis) is a congenital
151
+ or acquired condition, in which the penis is partially or completely hidden below
152
+ the surface of the skin. It was first described by Edward Lawrence Keyes in 1919
153
+ as the apparent absence of the penis and as being buried beneath the skin of the
154
+ abdomen, thigh, or scrotum.[1] Further research was done by Maurice Campbell in
155
+ 1951 when he reported on the penis being buried beneath subcutaneous fat of the
156
+ scrotum, perineum, hypogastrium, and thigh.[2]
157
+
158
+
159
+ A buried penis can lead to obstruction of urinary stream, poor hygiene, soft tissue
160
+ infection, phimosis, and inhibition of normal sexual function.'
161
+ - source_sentence: metastasis, lung pain, liver symptoms
162
+ sentences:
163
+ - 'Testicular seminomatous germ cell tumor is a rare testicular germ cell tumor
164
+ (see this term), most commonly presenting with a painless mass in the scrotum,
165
+ with a very high cure rate if caught in the early stages.
166
+
167
+
168
+ ## Epidemiology
169
+
170
+
171
+ Annual incidence in Europe is 1/62,000 people. It accounts for 40% of testicular
172
+ cancer cases.
173
+
174
+
175
+ ## Clinical description
176
+
177
+
178
+ Seminoma usually presents in males between the ages of 30-40. A painless mass
179
+ in the scrotum is indicative of disease. A long-standing hydrocele may be noted
180
+ causing a feeling of heaviness in the testicle. Gynecomastia and back and flank
181
+ pain are symptoms that are seen in some patients. Relapse after surgery can occur,
182
+ usually (in 97% of cases) in the high iliac or retroperitoneal lymph nodes. Metastasis,
183
+ although rare, can occur in some cases, affecting the lungs, liver, bones and
184
+ central nervous system.
185
+
186
+
187
+ ## Etiology'
188
+ - 'Proteus-like syndrome describes patients who do not meet the diagnostic criteria
189
+ for Proteus syndrome (see this term) but who share a multitude of characteristic
190
+ clinical features of the disease.
191
+
192
+
193
+ ## Epidemiology
194
+
195
+
196
+ The prevalence is unknown.
197
+
198
+
199
+ ## Clinical description
200
+
201
+
202
+ Proteus-like syndrome has the clinical features of Proteus syndrome but lacks
203
+ some of the required criteria necessary for diagnosis. The main clinical features
204
+ include skeletal overgrowth, hamartomous overgrowth of multiple tissues, cerebriform
205
+ connective tissue nevi, vascular malformations and linear epidermal nevi.
206
+
207
+
208
+ ## Etiology'
209
+ - "\"ESUS\" redirects here. For other uses, see ESUS (disambiguation).\n\nEmbolic\
210
+ \ stroke of undetermined source (ESUS) is a type of ischemic stroke with an unknown\
211
+ \ origin, defined as a non-lacunar brain infarct without proximal arterial stenosis\
212
+ \ or cardioembolic sources.[1] As such, it forms a subset of cryptogenic stroke,\
213
+ \ which is part of the TOAST-classification.[2] The following diagnostic criteria\
214
+ \ define an ESUS:[1]\n\n * Stroke detected by CT or MRI that is not lacunar\n\
215
+ \ * No major-risk cardioembolic source of embolism\n * Absence of extracranial\
216
+ \ or intracranial atherosclerosis causing 50% luminal stenosis in arteries supplying\
217
+ \ the area of ischaemia\n * No other specific cause of stroke identified (e.g.,\
218
+ \ arteritis, dissection, migraine/vasospasm, drug misuse)\n\n## Contents\n\n \
219
+ \ * 1 Causes\n * 2 Diagnosis\n * 2.1 Cryptogenic stroke vs ESUS\n * 3 Management\n\
220
+ \ * 4 Epidemiology\n * 5 References\n * 6 Further reading\n\n## Causes[edit]"
221
+ - source_sentence: nerve cell dysfunction, riboflavin deficiency
222
+ sentences:
223
+ - Riboflavin transporter deficiency neuronopathy is a disorder that affects nerve
224
+ cells (neurons). Affected individuals typically have hearing loss caused by nerve
225
+ damage in the inner ear (sensorineural hearing loss) and signs of damage to other
226
+ nerves.
227
+ - 'A number sign (#) is used with this entry because autosomal recessive deafness-23
228
+ (DFNB23) is caused by homozygous mutation in the gene encoding protocadherin-15
229
+ (PCDH15; 605514) on chromosome 10q21.
230
+
231
+
232
+ Mutation in the PCDH15 gene can also cause Usher syndrome type IF (602083).
233
+
234
+
235
+ Clinical Features
236
+
237
+
238
+ Ahmed et al. (2003) reported 3 families with isolated deafness. Two of the families
239
+ had no history of nyctalopia, and the funduscopy and electroretinograms were normal
240
+ in 2 older affected individuals from each family (age range, 13-44 years). Vestibular
241
+ responses were intact in affected individuals.'
242
+ - 'A number sign (#) is used with this entry because hyperprolinemia type I (HYRPRO1)
243
+ is caused by homozygous or compound heterozygous mutation in the proline dehydrogenase
244
+ gene (PRODH; 606810) on chromosome 22q11.
245
+
246
+
247
+ The PRODH gene falls within the region deleted in the 22q11 deletion syndrome,
248
+ including DiGeorge syndrome (188400) and velocardiofacial syndrome (192430).
249
+
250
+
251
+ Description
252
+
253
+
254
+ Phang et al. (2001) noted that prospective studies of HPI probands identified
255
+ through newborn screening as well as reports of several families have suggested
256
+ that it is a metabolic disorder not clearly associated with clinical manifestations.
257
+ Phang et al. (2001) concluded that HPI is a relatively benign condition in most
258
+ individuals under most circumstances. However, other reports have suggested that
259
+ some patients have a severe phenotype with neurologic manifestations, including
260
+ epilepsy and mental retardation (Jacquet et al., 2003).
261
+
262
+
263
+ ### Genetic Heterogeneity of Hyperprolinemia'
264
+ pipeline_tag: sentence-similarity
265
+ model-index:
266
+ - name: SentenceTransformer based on sentence-transformers/multi-qa-mpnet-base-dot-v1
267
+ results:
268
+ - task:
269
+ type: information-retrieval
270
+ name: Information Retrieval
271
+ dataset:
272
+ name: Unknown
273
+ type: unknown
274
+ metrics:
275
+ - type: cosine_accuracy@1
276
+ value: 0.1933234251743455
277
+ name: Cosine Accuracy@1
278
+ - type: cosine_accuracy@3
279
+ value: 0.5625928889905111
280
+ name: Cosine Accuracy@3
281
+ - type: cosine_accuracy@5
282
+ value: 0.7512289927975306
283
+ name: Cosine Accuracy@5
284
+ - type: cosine_accuracy@10
285
+ value: 0.8409740482451126
286
+ name: Cosine Accuracy@10
287
+ - type: cosine_precision@1
288
+ value: 0.1933234251743455
289
+ name: Cosine Precision@1
290
+ - type: cosine_precision@3
291
+ value: 0.187530962996837
292
+ name: Cosine Precision@3
293
+ - type: cosine_precision@5
294
+ value: 0.15024579855950612
295
+ name: Cosine Precision@5
296
+ - type: cosine_precision@10
297
+ value: 0.08409740482451128
298
+ name: Cosine Precision@10
299
+ - type: cosine_recall@1
300
+ value: 0.1933234251743455
301
+ name: Cosine Recall@1
302
+ - type: cosine_recall@3
303
+ value: 0.5625928889905111
304
+ name: Cosine Recall@3
305
+ - type: cosine_recall@5
306
+ value: 0.7512289927975306
307
+ name: Cosine Recall@5
308
+ - type: cosine_recall@10
309
+ value: 0.8409740482451126
310
+ name: Cosine Recall@10
311
+ - type: cosine_ndcg@10
312
+ value: 0.5119882960837339
313
+ name: Cosine Ndcg@10
314
+ - type: cosine_mrr@10
315
+ value: 0.405861873730865
316
+ name: Cosine Mrr@10
317
+ - type: cosine_map@100
318
+ value: 0.4109594895459784
319
+ name: Cosine Map@100
320
+ - type: dot_accuracy@1
321
+ value: 0.1949239739339202
322
+ name: Dot Accuracy@1
323
+ - type: dot_accuracy@3
324
+ value: 0.5672802103578369
325
+ name: Dot Accuracy@3
326
+ - type: dot_accuracy@5
327
+ value: 0.7570595632788385
328
+ name: Dot Accuracy@5
329
+ - type: dot_accuracy@10
330
+ value: 0.8415456728021036
331
+ name: Dot Accuracy@10
332
+ - type: dot_precision@1
333
+ value: 0.1949239739339202
334
+ name: Dot Precision@1
335
+ - type: dot_precision@3
336
+ value: 0.18909340345261233
337
+ name: Dot Precision@3
338
+ - type: dot_precision@5
339
+ value: 0.1514119126557677
340
+ name: Dot Precision@5
341
+ - type: dot_precision@10
342
+ value: 0.08415456728021035
343
+ name: Dot Precision@10
344
+ - type: dot_recall@1
345
+ value: 0.1949239739339202
346
+ name: Dot Recall@1
347
+ - type: dot_recall@3
348
+ value: 0.5672802103578369
349
+ name: Dot Recall@3
350
+ - type: dot_recall@5
351
+ value: 0.7570595632788385
352
+ name: Dot Recall@5
353
+ - type: dot_recall@10
354
+ value: 0.8415456728021036
355
+ name: Dot Recall@10
356
+ - type: dot_ndcg@10
357
+ value: 0.5141471619143755
358
+ name: Dot Ndcg@10
359
+ - type: dot_mrr@10
360
+ value: 0.40838527858078216
361
+ name: Dot Mrr@10
362
+ - type: dot_map@100
363
+ value: 0.4135618156873651
364
+ name: Dot Map@100
365
+ ---
366
+
367
+ # SentenceTransformer based on sentence-transformers/multi-qa-mpnet-base-dot-v1
368
+
369
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/multi-qa-mpnet-base-dot-v1](https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-dot-v1). 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.
370
+
371
+ ## Model Details
372
+
373
+ ### Model Description
374
+ - **Model Type:** Sentence Transformer
375
+ - **Base model:** [sentence-transformers/multi-qa-mpnet-base-dot-v1](https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-dot-v1) <!-- at revision 3af7c6da5b3e1bea796ef6c97fe237538cbe6e7f -->
376
+ - **Maximum Sequence Length:** 512 tokens
377
+ - **Output Dimensionality:** 768 tokens
378
+ - **Similarity Function:** Dot Product
379
+ <!-- - **Training Dataset:** Unknown -->
380
+ <!-- - **Language:** Unknown -->
381
+ <!-- - **License:** Unknown -->
382
+
383
+ ### Model Sources
384
+
385
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
386
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
387
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
388
+
389
+ ### Full Model Architecture
390
+
391
+ ```
392
+ SentenceTransformer(
393
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
394
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
395
+ )
396
+ ```
397
+
398
+ ## Usage
399
+
400
+ ### Direct Usage (Sentence Transformers)
401
+
402
+ First install the Sentence Transformers library:
403
+
404
+ ```bash
405
+ pip install -U sentence-transformers
406
+ ```
407
+
408
+ Then you can load this model and run inference.
409
+ ```python
410
+ from sentence_transformers import SentenceTransformer
411
+
412
+ # Download from the 🤗 Hub
413
+ model = SentenceTransformer("sentence_transformers_model_id")
414
+ # Run inference
415
+ sentences = [
416
+ 'nerve cell dysfunction, riboflavin deficiency',
417
+ 'Riboflavin transporter deficiency neuronopathy is a disorder that affects nerve cells (neurons). Affected individuals typically have hearing loss caused by nerve damage in the inner ear (sensorineural hearing loss) and signs of damage to other nerves.',
418
+ 'A number sign (#) is used with this entry because hyperprolinemia type I (HYRPRO1) is caused by homozygous or compound heterozygous mutation in the proline dehydrogenase gene (PRODH; 606810) on chromosome 22q11.\n\nThe PRODH gene falls within the region deleted in the 22q11 deletion syndrome, including DiGeorge syndrome (188400) and velocardiofacial syndrome (192430).\n\nDescription\n\nPhang et al. (2001) noted that prospective studies of HPI probands identified through newborn screening as well as reports of several families have suggested that it is a metabolic disorder not clearly associated with clinical manifestations. Phang et al. (2001) concluded that HPI is a relatively benign condition in most individuals under most circumstances. However, other reports have suggested that some patients have a severe phenotype with neurologic manifestations, including epilepsy and mental retardation (Jacquet et al., 2003).\n\n### Genetic Heterogeneity of Hyperprolinemia',
419
+ ]
420
+ embeddings = model.encode(sentences)
421
+ print(embeddings.shape)
422
+ # [3, 768]
423
+
424
+ # Get the similarity scores for the embeddings
425
+ similarities = model.similarity(embeddings, embeddings)
426
+ print(similarities.shape)
427
+ # [3, 3]
428
+ ```
429
+
430
+ <!--
431
+ ### Direct Usage (Transformers)
432
+
433
+ <details><summary>Click to see the direct usage in Transformers</summary>
434
+
435
+ </details>
436
+ -->
437
+
438
+ <!--
439
+ ### Downstream Usage (Sentence Transformers)
440
+
441
+ You can finetune this model on your own dataset.
442
+
443
+ <details><summary>Click to expand</summary>
444
+
445
+ </details>
446
+ -->
447
+
448
+ <!--
449
+ ### Out-of-Scope Use
450
+
451
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
452
+ -->
453
+
454
+ ## Evaluation
455
+
456
+ ### Metrics
457
+
458
+ #### Information Retrieval
459
+
460
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
461
+
462
+ | Metric | Value |
463
+ |:--------------------|:-----------|
464
+ | cosine_accuracy@1 | 0.1933 |
465
+ | cosine_accuracy@3 | 0.5626 |
466
+ | cosine_accuracy@5 | 0.7512 |
467
+ | cosine_accuracy@10 | 0.841 |
468
+ | cosine_precision@1 | 0.1933 |
469
+ | cosine_precision@3 | 0.1875 |
470
+ | cosine_precision@5 | 0.1502 |
471
+ | cosine_precision@10 | 0.0841 |
472
+ | cosine_recall@1 | 0.1933 |
473
+ | cosine_recall@3 | 0.5626 |
474
+ | cosine_recall@5 | 0.7512 |
475
+ | cosine_recall@10 | 0.841 |
476
+ | cosine_ndcg@10 | 0.512 |
477
+ | cosine_mrr@10 | 0.4059 |
478
+ | cosine_map@100 | 0.411 |
479
+ | dot_accuracy@1 | 0.1949 |
480
+ | dot_accuracy@3 | 0.5673 |
481
+ | dot_accuracy@5 | 0.7571 |
482
+ | dot_accuracy@10 | 0.8415 |
483
+ | dot_precision@1 | 0.1949 |
484
+ | dot_precision@3 | 0.1891 |
485
+ | dot_precision@5 | 0.1514 |
486
+ | dot_precision@10 | 0.0842 |
487
+ | dot_recall@1 | 0.1949 |
488
+ | dot_recall@3 | 0.5673 |
489
+ | dot_recall@5 | 0.7571 |
490
+ | dot_recall@10 | 0.8415 |
491
+ | dot_ndcg@10 | 0.5141 |
492
+ | dot_mrr@10 | 0.4084 |
493
+ | **dot_map@100** | **0.4136** |
494
+
495
+ <!--
496
+ ## Bias, Risks and Limitations
497
+
498
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
499
+ -->
500
+
501
+ <!--
502
+ ### Recommendations
503
+
504
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
505
+ -->
506
+
507
+ ## Training Details
508
+
509
+ ### Training Dataset
510
+
511
+ #### Unnamed Dataset
512
+
513
+
514
+ * Size: 95,159 training samples
515
+ * Columns: <code>queries</code> and <code>chunks</code>
516
+ * Approximate statistics based on the first 1000 samples:
517
+ | | queries | chunks |
518
+ |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
519
+ | type | string | string |
520
+ | details | <ul><li>min: 5 tokens</li><li>mean: 15.01 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 158.91 tokens</li><li>max: 319 tokens</li></ul> |
521
+ * Samples:
522
+ | queries | chunks |
523
+ |:-------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
524
+ | <code>hypotrichosis, wiry hair, onycholysis</code> | <code>Green et al. (2003) reported an Australian family in which 22 members over 4 generations had progressive patterned scalp hypotrichosis and wiry hair similar to that seen in Marie Unna hereditary hypotrichosis (MUHH; 146550). Features differing from those of MUHH included absence of signs of abnormality at birth, relative sparing of body hair, distal onycholysis, and intermittent cosegregation with autosomal dominant cleft lip and palate. Five individuals had associated cleft lip and palate. Green et al. (2003) excluded linkage of the disorder in the Australian family to the MUHH locus on chromosome 8p21.</code> |
525
+ | <code>cleft lip, cleft palate, hair loss</code> | <code>Green et al. (2003) reported an Australian family in which 22 members over 4 generations had progressive patterned scalp hypotrichosis and wiry hair similar to that seen in Marie Unna hereditary hypotrichosis (MUHH; 146550). Features differing from those of MUHH included absence of signs of abnormality at birth, relative sparing of body hair, distal onycholysis, and intermittent cosegregation with autosomal dominant cleft lip and palate. Five individuals had associated cleft lip and palate. Green et al. (2003) excluded linkage of the disorder in the Australian family to the MUHH locus on chromosome 8p21.</code> |
526
+ | <code>progressive patterned scalp, autosomal dominant inheritance</code> | <code>Green et al. (2003) reported an Australian family in which 22 members over 4 generations had progressive patterned scalp hypotrichosis and wiry hair similar to that seen in Marie Unna hereditary hypotrichosis (MUHH; 146550). Features differing from those of MUHH included absence of signs of abnormality at birth, relative sparing of body hair, distal onycholysis, and intermittent cosegregation with autosomal dominant cleft lip and palate. Five individuals had associated cleft lip and palate. Green et al. (2003) excluded linkage of the disorder in the Australian family to the MUHH locus on chromosome 8p21.</code> |
527
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
528
+ ```json
529
+ {
530
+ "scale": 1,
531
+ "similarity_fct": "dot_score"
532
+ }
533
+ ```
534
+
535
+ ### Evaluation Dataset
536
+
537
+ #### Unnamed Dataset
538
+
539
+
540
+ * Size: 8,747 evaluation samples
541
+ * Columns: <code>queries</code> and <code>chunks</code>
542
+ * Approximate statistics based on the first 1000 samples:
543
+ | | queries | chunks |
544
+ |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
545
+ | type | string | string |
546
+ | details | <ul><li>min: 6 tokens</li><li>mean: 14.71 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 155.81 tokens</li><li>max: 305 tokens</li></ul> |
547
+ * Samples:
548
+ | queries | chunks |
549
+ |:-----------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
550
+ | <code>white patches, corrugated tongue, immunocompromised, Epstein-Barr virus</code> | <code>Not to be confused with Hairy tongue.<br><br>Hairy leukoplakia <br>Other namesOral hairy leukoplakia,[1]:385 OHL, or HIV-associated hairy leukoplakia[2] <br>SpecialtyGastroenterology <br> <br>Hairy leukoplakia is a white patch on the side of the tongue with a corrugated or hairy appearance. It is caused by Epstein-Barr virus (EBV) and occurs usually in persons who are immunocompromised, especially those with human immunodeficiency virus infection/acquired immunodeficiency syndrome (HIV/AIDS). The white lesion, which cannot be scraped off, is benign and does not require any treatment, although its appearance may have diagnostic and prognostic implications for the underlying condition.<br><br>Depending upon what definition of leukoplakia is used, hairy leukoplakia is sometimes considered a subtype of leukoplakia, or a distinct diagnosis.<br><br>## Contents</code> |
551
+ | <code>HIV-associated lesions, oral hairy leukoplakia, benign white lesions, tongue appearance</code> | <code>Not to be confused with Hairy tongue.<br><br>Hairy leukoplakia <br>Other namesOral hairy leukoplakia,[1]:385 OHL, or HIV-associated hairy leukoplakia[2] <br>SpecialtyGastroenterology <br> <br>Hairy leukoplakia is a white patch on the side of the tongue with a corrugated or hairy appearance. It is caused by Epstein-Barr virus (EBV) and occurs usually in persons who are immunocompromised, especially those with human immunodeficiency virus infection/acquired immunodeficiency syndrome (HIV/AIDS). The white lesion, which cannot be scraped off, is benign and does not require any treatment, although its appearance may have diagnostic and prognostic implications for the underlying condition.<br><br>Depending upon what definition of leukoplakia is used, hairy leukoplakia is sometimes considered a subtype of leukoplakia, or a distinct diagnosis.<br><br>## Contents</code> |
552
+ | <code>hairy leukoplakia symptoms, non-scrapable lesions, HIV/AIDS, oral lesions</code> | <code>Not to be confused with Hairy tongue.<br><br>Hairy leukoplakia <br>Other namesOral hairy leukoplakia,[1]:385 OHL, or HIV-associated hairy leukoplakia[2] <br>SpecialtyGastroenterology <br> <br>Hairy leukoplakia is a white patch on the side of the tongue with a corrugated or hairy appearance. It is caused by Epstein-Barr virus (EBV) and occurs usually in persons who are immunocompromised, especially those with human immunodeficiency virus infection/acquired immunodeficiency syndrome (HIV/AIDS). The white lesion, which cannot be scraped off, is benign and does not require any treatment, although its appearance may have diagnostic and prognostic implications for the underlying condition.<br><br>Depending upon what definition of leukoplakia is used, hairy leukoplakia is sometimes considered a subtype of leukoplakia, or a distinct diagnosis.<br><br>## Contents</code> |
553
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
554
+ ```json
555
+ {
556
+ "scale": 1,
557
+ "similarity_fct": "dot_score"
558
+ }
559
+ ```
560
+
561
+ ### Training Hyperparameters
562
+ #### Non-Default Hyperparameters
563
+
564
+ - `eval_strategy`: steps
565
+ - `per_device_train_batch_size`: 32
566
+ - `per_device_eval_batch_size`: 32
567
+ - `learning_rate`: 2e-05
568
+ - `num_train_epochs`: 15
569
+ - `warmup_ratio`: 0.1
570
+ - `fp16`: True
571
+ - `load_best_model_at_end`: True
572
+ - `eval_on_start`: True
573
+ - `batch_sampler`: no_duplicates
574
+
575
+ #### All Hyperparameters
576
+ <details><summary>Click to expand</summary>
577
+
578
+ - `overwrite_output_dir`: False
579
+ - `do_predict`: False
580
+ - `eval_strategy`: steps
581
+ - `prediction_loss_only`: True
582
+ - `per_device_train_batch_size`: 32
583
+ - `per_device_eval_batch_size`: 32
584
+ - `per_gpu_train_batch_size`: None
585
+ - `per_gpu_eval_batch_size`: None
586
+ - `gradient_accumulation_steps`: 1
587
+ - `eval_accumulation_steps`: None
588
+ - `torch_empty_cache_steps`: None
589
+ - `learning_rate`: 2e-05
590
+ - `weight_decay`: 0.0
591
+ - `adam_beta1`: 0.9
592
+ - `adam_beta2`: 0.999
593
+ - `adam_epsilon`: 1e-08
594
+ - `max_grad_norm`: 1.0
595
+ - `num_train_epochs`: 15
596
+ - `max_steps`: -1
597
+ - `lr_scheduler_type`: linear
598
+ - `lr_scheduler_kwargs`: {}
599
+ - `warmup_ratio`: 0.1
600
+ - `warmup_steps`: 0
601
+ - `log_level`: passive
602
+ - `log_level_replica`: warning
603
+ - `log_on_each_node`: True
604
+ - `logging_nan_inf_filter`: True
605
+ - `save_safetensors`: True
606
+ - `save_on_each_node`: False
607
+ - `save_only_model`: False
608
+ - `restore_callback_states_from_checkpoint`: False
609
+ - `no_cuda`: False
610
+ - `use_cpu`: False
611
+ - `use_mps_device`: False
612
+ - `seed`: 42
613
+ - `data_seed`: None
614
+ - `jit_mode_eval`: False
615
+ - `use_ipex`: False
616
+ - `bf16`: False
617
+ - `fp16`: True
618
+ - `fp16_opt_level`: O1
619
+ - `half_precision_backend`: auto
620
+ - `bf16_full_eval`: False
621
+ - `fp16_full_eval`: False
622
+ - `tf32`: None
623
+ - `local_rank`: 0
624
+ - `ddp_backend`: None
625
+ - `tpu_num_cores`: None
626
+ - `tpu_metrics_debug`: False
627
+ - `debug`: []
628
+ - `dataloader_drop_last`: True
629
+ - `dataloader_num_workers`: 0
630
+ - `dataloader_prefetch_factor`: None
631
+ - `past_index`: -1
632
+ - `disable_tqdm`: False
633
+ - `remove_unused_columns`: True
634
+ - `label_names`: None
635
+ - `load_best_model_at_end`: True
636
+ - `ignore_data_skip`: False
637
+ - `fsdp`: []
638
+ - `fsdp_min_num_params`: 0
639
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
640
+ - `fsdp_transformer_layer_cls_to_wrap`: None
641
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
642
+ - `deepspeed`: None
643
+ - `label_smoothing_factor`: 0.0
644
+ - `optim`: adamw_torch
645
+ - `optim_args`: None
646
+ - `adafactor`: False
647
+ - `group_by_length`: False
648
+ - `length_column_name`: length
649
+ - `ddp_find_unused_parameters`: None
650
+ - `ddp_bucket_cap_mb`: None
651
+ - `ddp_broadcast_buffers`: False
652
+ - `dataloader_pin_memory`: True
653
+ - `dataloader_persistent_workers`: False
654
+ - `skip_memory_metrics`: True
655
+ - `use_legacy_prediction_loop`: False
656
+ - `push_to_hub`: False
657
+ - `resume_from_checkpoint`: None
658
+ - `hub_model_id`: None
659
+ - `hub_strategy`: every_save
660
+ - `hub_private_repo`: False
661
+ - `hub_always_push`: False
662
+ - `gradient_checkpointing`: False
663
+ - `gradient_checkpointing_kwargs`: None
664
+ - `include_inputs_for_metrics`: False
665
+ - `eval_do_concat_batches`: True
666
+ - `fp16_backend`: auto
667
+ - `push_to_hub_model_id`: None
668
+ - `push_to_hub_organization`: None
669
+ - `mp_parameters`:
670
+ - `auto_find_batch_size`: False
671
+ - `full_determinism`: False
672
+ - `torchdynamo`: None
673
+ - `ray_scope`: last
674
+ - `ddp_timeout`: 1800
675
+ - `torch_compile`: False
676
+ - `torch_compile_backend`: None
677
+ - `torch_compile_mode`: None
678
+ - `dispatch_batches`: None
679
+ - `split_batches`: None
680
+ - `include_tokens_per_second`: False
681
+ - `include_num_input_tokens_seen`: False
682
+ - `neftune_noise_alpha`: None
683
+ - `optim_target_modules`: None
684
+ - `batch_eval_metrics`: False
685
+ - `eval_on_start`: True
686
+ - `eval_use_gather_object`: False
687
+ - `batch_sampler`: no_duplicates
688
+ - `multi_dataset_batch_sampler`: proportional
689
+
690
+ </details>
691
+
692
+ ### Training Logs
693
+ <details><summary>Click to expand</summary>
694
+
695
+ | Epoch | Step | Training Loss | loss | dot_map@100 |
696
+ |:-----------:|:--------:|:-------------:|:----------:|:-----------:|
697
+ | 0 | 0 | - | 1.4355 | 0.2271 |
698
+ | 0.1346 | 100 | 1.2599 | - | - |
699
+ | 0.2692 | 200 | 0.7627 | - | - |
700
+ | 0.4038 | 300 | 0.6061 | - | - |
701
+ | 0.5384 | 400 | 0.5632 | - | - |
702
+ | 0.6729 | 500 | 0.3965 | 0.4589 | 0.3852 |
703
+ | 0.8075 | 600 | 0.3104 | - | - |
704
+ | 0.9421 | 700 | 0.446 | - | - |
705
+ | 1.0767 | 800 | 0.4426 | - | - |
706
+ | 1.2113 | 900 | 0.4518 | - | - |
707
+ | 1.3459 | 1000 | 0.4145 | 0.3726 | 0.3964 |
708
+ | 1.4805 | 1100 | 0.4296 | - | - |
709
+ | 1.6151 | 1200 | 0.4144 | - | - |
710
+ | 1.7497 | 1300 | 0.1536 | - | - |
711
+ | 1.8843 | 1400 | 0.3425 | - | - |
712
+ | 2.0188 | 1500 | 0.3225 | 0.3433 | 0.3930 |
713
+ | 2.1534 | 1600 | 0.3529 | - | - |
714
+ | 2.2880 | 1700 | 0.3382 | - | - |
715
+ | 2.4226 | 1800 | 0.3092 | - | - |
716
+ | 2.5572 | 1900 | 0.339 | - | - |
717
+ | 2.6918 | 2000 | 0.1681 | 0.3633 | 0.4032 |
718
+ | 2.8264 | 2100 | 0.1753 | - | - |
719
+ | 2.9610 | 2200 | 0.2552 | - | - |
720
+ | 3.0956 | 2300 | 0.2549 | - | - |
721
+ | 3.2301 | 2400 | 0.2759 | - | - |
722
+ | 3.3647 | 2500 | 0.2513 | 0.3338 | 0.4066 |
723
+ | 3.4993 | 2600 | 0.258 | - | - |
724
+ | 3.6339 | 2700 | 0.2222 | - | - |
725
+ | 3.7685 | 2800 | 0.0541 | - | - |
726
+ | 3.9031 | 2900 | 0.2275 | - | - |
727
+ | 4.0377 | 3000 | 0.1919 | 0.3529 | 0.4026 |
728
+ | 4.1723 | 3100 | 0.215 | - | - |
729
+ | 4.3069 | 3200 | 0.2114 | - | - |
730
+ | 4.4415 | 3300 | 0.2153 | - | - |
731
+ | 4.5760 | 3400 | 0.2164 | - | - |
732
+ | 4.7106 | 3500 | 0.0773 | 0.3509 | 0.4090 |
733
+ | 4.8452 | 3600 | 0.1211 | - | - |
734
+ | 4.9798 | 3700 | 0.1553 | - | - |
735
+ | 5.1144 | 3800 | 0.1764 | - | - |
736
+ | 5.2490 | 3900 | 0.1953 | - | - |
737
+ | 5.3836 | 4000 | 0.1559 | 0.3474 | 0.4089 |
738
+ | 5.5182 | 4100 | 0.1686 | - | - |
739
+ | 5.6528 | 4200 | 0.1327 | - | - |
740
+ | 5.7873 | 4300 | 0.0514 | - | - |
741
+ | 5.9219 | 4400 | 0.1381 | - | - |
742
+ | 6.0565 | 4500 | 0.1445 | 0.3521 | 0.4056 |
743
+ | 6.1911 | 4600 | 0.1621 | - | - |
744
+ | 6.3257 | 4700 | 0.1365 | - | - |
745
+ | 6.4603 | 4800 | 0.1579 | - | - |
746
+ | 6.5949 | 4900 | 0.1547 | - | - |
747
+ | 6.7295 | 5000 | 0.0316 | 0.3895 | 0.4094 |
748
+ | 6.8641 | 5100 | 0.0958 | - | - |
749
+ | 6.9987 | 5200 | 0.1082 | - | - |
750
+ | 7.1332 | 5300 | 0.1379 | - | - |
751
+ | 7.2678 | 5400 | 0.1348 | - | - |
752
+ | 7.4024 | 5500 | 0.1322 | 0.3552 | 0.4100 |
753
+ | 7.5370 | 5600 | 0.1321 | - | - |
754
+ | 7.6716 | 5700 | 0.0763 | - | - |
755
+ | 7.8062 | 5800 | 0.0472 | - | - |
756
+ | 7.9408 | 5900 | 0.0989 | - | - |
757
+ | 8.0754 | 6000 | 0.1045 | 0.3631 | 0.3967 |
758
+ | 8.2100 | 6100 | 0.122 | - | - |
759
+ | 8.3445 | 6200 | 0.1057 | - | - |
760
+ | 8.4791 | 6300 | 0.1194 | - | - |
761
+ | 8.6137 | 6400 | 0.113 | - | - |
762
+ | 8.7483 | 6500 | 0.0126 | 0.3944 | 0.4116 |
763
+ | 8.8829 | 6600 | 0.089 | - | - |
764
+ | 9.0175 | 6700 | 0.0849 | - | - |
765
+ | 9.1521 | 6800 | 0.1052 | - | - |
766
+ | 9.2867 | 6900 | 0.111 | - | - |
767
+ | 9.4213 | 7000 | 0.1026 | 0.3665 | 0.4133 |
768
+ | 9.5559 | 7100 | 0.1165 | - | - |
769
+ | 9.6904 | 7200 | 0.0394 | - | - |
770
+ | 9.8250 | 7300 | 0.0443 | - | - |
771
+ | 9.9596 | 7400 | 0.0756 | - | - |
772
+ | 10.0942 | 7500 | 0.0806 | 0.3785 | 0.4090 |
773
+ | 10.2288 | 7600 | 0.103 | - | - |
774
+ | 10.3634 | 7700 | 0.0875 | - | - |
775
+ | 10.4980 | 7800 | 0.0959 | - | - |
776
+ | 10.6326 | 7900 | 0.0851 | - | - |
777
+ | **10.7672** | **8000** | **0.0073** | **0.3902** | **0.4136** |
778
+ | 10.9017 | 8100 | 0.079 | - | - |
779
+ | 11.0363 | 8200 | 0.0664 | - | - |
780
+ | 11.1709 | 8300 | 0.0766 | - | - |
781
+ | 11.3055 | 8400 | 0.084 | - | - |
782
+ | 11.4401 | 8500 | 0.0947 | 0.3733 | 0.4099 |
783
+ | 11.5747 | 8600 | 0.0906 | - | - |
784
+ | 11.7093 | 8700 | 0.0224 | - | - |
785
+ | 11.8439 | 8800 | 0.0424 | - | - |
786
+ | 11.9785 | 8900 | 0.0569 | - | - |
787
+ | 12.1131 | 9000 | 0.0697 | 0.3824 | 0.4071 |
788
+ | 12.2476 | 9100 | 0.095 | - | - |
789
+ | 12.3822 | 9200 | 0.0651 | - | - |
790
+ | 12.5168 | 9300 | 0.0756 | - | - |
791
+ | 12.6514 | 9400 | 0.065 | - | - |
792
+ | 12.7860 | 9500 | 0.0194 | 0.3876 | 0.4110 |
793
+ | 12.9206 | 9600 | 0.0595 | - | - |
794
+ | 13.0552 | 9700 | 0.0629 | - | - |
795
+ | 13.1898 | 9800 | 0.0808 | - | - |
796
+ | 13.3244 | 9900 | 0.0652 | - | - |
797
+ | 13.4590 | 10000 | 0.0802 | 0.3783 | 0.4091 |
798
+ | 13.5935 | 10100 | 0.0809 | - | - |
799
+ | 13.7281 | 10200 | 0.0111 | - | - |
800
+ | 13.8627 | 10300 | 0.0465 | - | - |
801
+ | 13.9973 | 10400 | 0.0504 | - | - |
802
+ | 14.1319 | 10500 | 0.068 | 0.3831 | 0.4071 |
803
+ | 14.2665 | 10600 | 0.0739 | - | - |
804
+ | 14.4011 | 10700 | 0.0734 | - | - |
805
+ | 14.5357 | 10800 | 0.0737 | - | - |
806
+ | 14.6703 | 10900 | 0.0379 | - | - |
807
+ | 14.8048 | 11000 | 0.0231 | 0.3841 | 0.4112 |
808
+ | 14.9394 | 11100 | 0.0493 | - | - |
809
+ | 15.0 | 11145 | - | 0.3902 | 0.4136 |
810
+
811
+ * The bold row denotes the saved checkpoint.
812
+ </details>
813
+
814
+ ### Framework Versions
815
+ - Python: 3.11.9
816
+ - Sentence Transformers: 3.0.1
817
+ - Transformers: 4.43.3
818
+ - PyTorch: 2.3.1+cu121
819
+ - Accelerate: 0.30.1
820
+ - Datasets: 2.19.2
821
+ - Tokenizers: 0.19.1
822
+
823
+ ## Citation
824
+
825
+ ### BibTeX
826
+
827
+ #### Sentence Transformers
828
+ ```bibtex
829
+ @inproceedings{reimers-2019-sentence-bert,
830
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
831
+ author = "Reimers, Nils and Gurevych, Iryna",
832
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
833
+ month = "11",
834
+ year = "2019",
835
+ publisher = "Association for Computational Linguistics",
836
+ url = "https://arxiv.org/abs/1908.10084",
837
+ }
838
+ ```
839
+
840
+ #### MultipleNegativesRankingLoss
841
+ ```bibtex
842
+ @misc{henderson2017efficient,
843
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
844
+ 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},
845
+ year={2017},
846
+ eprint={1705.00652},
847
+ archivePrefix={arXiv},
848
+ primaryClass={cs.CL}
849
+ }
850
+ ```
851
+
852
+ <!--
853
+ ## Glossary
854
+
855
+ *Clearly define terms in order to be accessible across audiences.*
856
+ -->
857
+
858
+ <!--
859
+ ## Model Card Authors
860
+
861
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
862
+ -->
863
+
864
+ <!--
865
+ ## Model Card Contact
866
+
867
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
868
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/multi-qa-mpnet-base-dot-v1",
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": "4.43.3",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.43.3",
5
+ "pytorch": "2.3.1+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "dot"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2390c6ed604106f286814c21e7495d06a1dc2ade74a3b334f84080e3cd61de09
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": false,
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": false,
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 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 250,
59
+ "model_max_length": 512,
60
+ "pad_to_multiple_of": null,
61
+ "pad_token": "<pad>",
62
+ "pad_token_type_id": 0,
63
+ "padding_side": "right",
64
+ "sep_token": "</s>",
65
+ "stride": 0,
66
+ "strip_accents": null,
67
+ "tokenize_chinese_chars": true,
68
+ "tokenizer_class": "MPNetTokenizer",
69
+ "truncation_side": "right",
70
+ "truncation_strategy": "longest_first",
71
+ "unk_token": "[UNK]"
72
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6244a513f44ab0bb2e8e9a88f3573d4d7ad54bd7937de9befef24913b91202
3
+ size 5624
vocab.txt ADDED
The diff for this file is too large to render. See raw diff