Hugging Face's logo

saraleivam
/
GURU-model2

Sentence Similarity
sentence-transformers
Safetensors
6 datasets
English
Spanish
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:58270
loss:MultipleNegativesRankingLoss
loss:CoSENTLoss
dataset_size:38270
dataset_size:18270
text-embeddings-inference
Inference Endpoints
Model card Files Community
saraleivam commited on
Commit
86e31b0
•
1 Parent(s): c7f09c0

Add new SentenceTransformer model.

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. 1_Pooling/config.json +10 -0
  3. README.md +599 -0
  4. config.json +29 -0
  5. config_sentence_transformers.json +10 -0
  6. model.safetensors +3 -0
  7. modules.json +14 -0
  8. sentence_bert_config.json +4 -0
  9. special_tokens_map.json +51 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +61 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
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 +1,599 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
3
+ datasets:
4
+ - sentence-transformers/msmarco-msmarco-distilbert-base-tas-b
5
+ - jaimevera1107/similarity-sentences-spanish
6
+ - sentence-transformers/all-nli
7
+ - sentence-transformers/stsb
8
+ - sentence-transformers/quora-duplicates
9
+ - sentence-transformers/natural-questions
10
+ language:
11
+ - en
12
+ - es
13
+ library_name: sentence-transformers
14
+ pipeline_tag: sentence-similarity
15
+ tags:
16
+ - sentence-transformers
17
+ - sentence-similarity
18
+ - feature-extraction
19
+ - generated_from_trainer
20
+ - dataset_size:58270
21
+ - loss:MultipleNegativesRankingLoss
22
+ - loss:CoSENTLoss
23
+ - dataset_size:38270
24
+ - dataset_size:18270
25
+ widget:
26
+ - source_sentence: The men are outside.
27
+ sentences:
28
+ - Two men with backpacks hiking up a trail.
29
+ - Two men are leaning out of a window and looking at something to the right of them.
30
+ - Two men are trying to plow some dirt, behind a red motorcycle.
31
+ - source_sentence: The men are outside.
32
+ sentences:
33
+ - Two men work on the sewers in the middle of the road as a BMW stops next to them.
34
+ - Two women work on a project outdoors.
35
+ - Two men work on the sewers in the middle of the road as a BMW stops next to them.
36
+ - source_sentence: Fundamentals of quantum computing.
37
+ sentences:
38
+ - Quantum computing researcher with qubit systems experience.
39
+ - Teacher with classroom management skills.
40
+ - ' Analista financiero con experiencia en predicción de series temporales y modelos
41
+ financieros.'
42
+ - source_sentence: Software architecture fundamentals course.
43
+ sentences:
44
+ - Software architect with system design skills.
45
+ - Desarrollador web con habilidades en WordPress
46
+ - Nurse with neonatal care experience.
47
+ - source_sentence: what creates a bunion
48
+ sentences:
49
+ - Mitral valve regurgitation means that one of the valves in your heart-the mitral
50
+ valve-is letting blood leak backward into the heart.Heart valves work like one-way
51
+ gates, helping blood flow in one direction between heart chambers or in and out
52
+ of the heart. The mitral valve is on the left side of your heart.It lets blood
53
+ flow from the upper to the lower heart chamber. See a picture of mitral valve
54
+ regurgitation.When the mitral valve is damaged-for example, by an infection-it
55
+ may no longer close tightly.This lets blood leak backward, or regurgitate, into
56
+ the upper chamber.t lets blood flow from the upper to the lower heart chamber.
57
+ See a picture of mitral valve regurgitation. When the mitral valve is damaged-for
58
+ example, by an infection-it may no longer close tightly. This lets blood leak
59
+ backward, or regurgitate, into the upper chamber.
60
+ - A bunion is a bony bump that forms on the joint at the base of your big toe. It
61
+ forms when your big toe pushes against your next toe, forcing the joint of your
62
+ big toe to get bigger and stick out. The skin over the bunion might be red and
63
+ sore. Wearing tight, narrow shoes might cause bunions or make them worse. Bunions
64
+ also can develop as a result of an inherited structural defect, stress on your
65
+ foot or a medical condition, such as arthritis. Smaller bunions (bunionettes)
66
+ can develop on the joint of your little toe. Nov. 08, 2016.
67
+ - 'A bunionette , or tailor''s bunion, is one that develops at the base of the little
68
+ toe. When the long bone that connects to the toe (metatarsal ) bends away from
69
+ the foot, the little toe bends inward and the joint swells or enlarges. Other
70
+ factors that can lead to a bunion include: Loose ligaments in the foot.'
71
+ ---
72
+
73
+ # SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
74
+
75
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the dataset, [distilbert](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-tas-b), [spanish](https://huggingface.co/datasets/jaimevera1107/similarity-sentences-spanish), [all-nli-triplet](https://huggingface.co/datasets/sentence-transformers/all-nli) and [stsb](https://huggingface.co/datasets/sentence-transformers/stsb) datasets. 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.
76
+
77
+ ## Model Details
78
+
79
+ ### Model Description
80
+ - **Model Type:** Sentence Transformer
81
+ - **Base model:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) <!-- at revision 79f2382ceacceacdf38563d7c5d16b9ff8d725d6 -->
82
+ - **Maximum Sequence Length:** 128 tokens
83
+ - **Output Dimensionality:** 768 tokens
84
+ - **Similarity Function:** Cosine Similarity
85
+ - **Training Datasets:**
86
+ - dataset
87
+ - [distilbert](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-tas-b)
88
+ - [spanish](https://huggingface.co/datasets/jaimevera1107/similarity-sentences-spanish)
89
+ - [all-nli-triplet](https://huggingface.co/datasets/sentence-transformers/all-nli)
90
+ - [stsb](https://huggingface.co/datasets/sentence-transformers/stsb)
91
+ - **Languages:** en, es
92
+ <!-- - **License:** Unknown -->
93
+
94
+ ### Model Sources
95
+
96
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
97
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
98
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
99
+
100
+ ### Full Model Architecture
101
+
102
+ ```
103
+ SentenceTransformer(
104
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
105
+ (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})
106
+ )
107
+ ```
108
+
109
+ ## Usage
110
+
111
+ ### Direct Usage (Sentence Transformers)
112
+
113
+ First install the Sentence Transformers library:
114
+
115
+ ```bash
116
+ pip install -U sentence-transformers
117
+ ```
118
+
119
+ Then you can load this model and run inference.
120
+ ```python
121
+ from sentence_transformers import SentenceTransformer
122
+
123
+ # Download from the 🤗 Hub
124
+ model = SentenceTransformer("saraleivam/GURU-model2")
125
+ # Run inference
126
+ sentences = [
127
+ 'what creates a bunion',
128
+ "A bunionette , or tailor's bunion, is one that develops at the base of the little toe. When the long bone that connects to the toe (metatarsal ) bends away from the foot, the little toe bends inward and the joint swells or enlarges. Other factors that can lead to a bunion include: Loose ligaments in the foot.",
129
+ 'A bunion is a bony bump that forms on the joint at the base of your big toe. It forms when your big toe pushes against your next toe, forcing the joint of your big toe to get bigger and stick out. The skin over the bunion might be red and sore. Wearing tight, narrow shoes might cause bunions or make them worse. Bunions also can develop as a result of an inherited structural defect, stress on your foot or a medical condition, such as arthritis. Smaller bunions (bunionettes) can develop on the joint of your little toe. Nov. 08, 2016.',
130
+ ]
131
+ embeddings = model.encode(sentences)
132
+ print(embeddings.shape)
133
+ # [3, 768]
134
+
135
+ # Get the similarity scores for the embeddings
136
+ similarities = model.similarity(embeddings, embeddings)
137
+ print(similarities.shape)
138
+ # [3, 3]
139
+ ```
140
+
141
+ <!--
142
+ ### Direct Usage (Transformers)
143
+
144
+ <details><summary>Click to see the direct usage in Transformers</summary>
145
+
146
+ </details>
147
+ -->
148
+
149
+ <!--
150
+ ### Downstream Usage (Sentence Transformers)
151
+
152
+ You can finetune this model on your own dataset.
153
+
154
+ <details><summary>Click to expand</summary>
155
+
156
+ </details>
157
+ -->
158
+
159
+ <!--
160
+ ### Out-of-Scope Use
161
+
162
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
163
+ -->
164
+
165
+ <!--
166
+ ## Bias, Risks and Limitations
167
+
168
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
169
+ -->
170
+
171
+ <!--
172
+ ### Recommendations
173
+
174
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
175
+ -->
176
+
177
+ ## Training Details
178
+
179
+ ### Training Datasets
180
+
181
+ #### dataset
182
+
183
+ * Dataset: dataset
184
+ * Size: 521 training samples
185
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
186
+ * Approximate statistics based on the first 1000 samples:
187
+ | | anchor | positive | negative |
188
+ |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
189
+ | type | string | string | string |
190
+ | details | <ul><li>min: 5 tokens</li><li>mean: 18.41 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 19.98 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 15.84 tokens</li><li>max: 128 tokens</li></ul> |
191
+ * Samples:
192
+ | anchor | positive | negative |
193
+ |:-------------------------------------------------------------------|:------------------------------------------------------------------------|:-------------------------------------------------------------|
194
+ | <code>Advanced data analysis with R.</code> | <code>Data analyst with R and statistical modeling experience.</code> | <code>Interior designer with space decoration skills.</code> |
195
+ | <code>Introduction to quantum machine learning.</code> | <code>AI researcher with quantum machine learning skills.</code> | <code>Pharmacist with pharmaceutical care skills.</code> |
196
+ | <code>Fundamentos de diseño de experiencia de usuario (UX).</code> | <code>Diseñador UX con habilidades en investigación de usuarios.</code> | <code>Abogado con habilidades en derecho civil.</code> |
197
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
198
+ ```json
199
+ {
200
+ "scale": 20.0,
201
+ "similarity_fct": "cos_sim"
202
+ }
203
+ ```
204
+
205
+ #### distilbert
206
+
207
+ * Dataset: [distilbert](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-tas-b) at [e63dd83](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-tas-b/tree/e63dd8397db956cdde78e5e18c0d734585874db2)
208
+ * Size: 1,000 training samples
209
+ * Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
210
+ * Approximate statistics based on the first 1000 samples:
211
+ | | query | positive | negative |
212
+ |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
213
+ | type | string | string | string |
214
+ | details | <ul><li>min: 4 tokens</li><li>mean: 9.95 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 84.21 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 79.55 tokens</li><li>max: 128 tokens</li></ul> |
215
+ * Samples:
216
+ | query | positive | negative |
217
+ |:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
218
+ | <code>what are the liberal arts?</code> | <code>liberal arts. 1. the academic course of instruction at a college intended to provide general knowledge and comprising the arts, humanities, natural sciences, and social sciences, as opposed to professional or technical subjects.</code> | <code>liberal arts definition The areas of learning that cultivate general intellectual ability rather than technical or professional skills. Liberal arts is often used as a synonym for humanities, because literature, languages, history, and philosophy are often considered the primary subjects of the liberal arts.</code> |
219
+ | <code>what is the mechanism of action of fibrinolytic or thrombolytic drugs?</code> | <code>Baillière's Clinical Haematology. 6 Mechanism of action of the thrombolytic agents. 6 Mechanism of action of the thrombolytic agents JEFFREY I. WEITZ Fibrin formed during the haemostatic, inflammatory or tissue repair process serves a temporary role, and must be degraded to restore normal tissue function and structure.</code> | <code>Thrombolytic drugs such as tPA are often the first line of defense in treating some forms of ischemic stroke. The stroke occurs when fibrin strands in the blood trap blood cells and platelets, forming a clot in an artery to the brain (A).</code> |
220
+ | <code>what is normal plat count</code> | <code>78 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).The average platelet count is 237,000 per mcL in men and 266,000 per mcL in women.8 Followers. A. Platelets are the tiny blood cells that help stop bleeding by binding together to form a clump or plug at sites of injury inside blood vessels. A normal platelet count is between 150,000 and 450,000 platelets per microliter (one-millionth of a liter, abbreviated mcL).</code> | <code>The normal number of platelets is between 150 and 400 million per millilitre (ml) of blood. Most pregnant women have normal numbers of platelets, but about eight per cent of pregnant women have a slight drop in their platelet count.Your count is below normal if you have between 100 and 150 million platelets per ml of blood.our platelet count will look something like Plat. 160x10.9/L, which means you have a platelet count of 160, which is in the normal range. If your platelet count is low, the blood test should be done again. This will keep track of whether or not your count is dropping.</code> |
221
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
222
+ ```json
223
+ {
224
+ "scale": 20.0,
225
+ "similarity_fct": "cos_sim"
226
+ }
227
+ ```
228
+
229
+ #### spanish
230
+
231
+ * Dataset: [spanish](https://huggingface.co/datasets/jaimevera1107/similarity-sentences-spanish) at [de18671](https://huggingface.co/datasets/jaimevera1107/similarity-sentences-spanish/tree/de18671fdc278718fab8a505e209e69264079c7a)
232
+ * Size: 1,000 training samples
233
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, <code>score</code>, and <code>source</code>
234
+ * Approximate statistics based on the first 1000 samples:
235
+ | | sentence1 | sentence2 | score | source |
236
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|:-------------------------------------------------------------------------------|
237
+ | type | string | string | float | string |
238
+ | details | <ul><li>min: 9 tokens</li><li>mean: 27.57 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 27.6 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.51</li><li>max: 1.0</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 4.0 tokens</li><li>max: 4 tokens</li></ul> |
239
+ * Samples:
240
+ | sentence1 | sentence2 | score | source |
241
+ |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|:-----------------|
242
+ | <code>La comida china tradicional se basa en la filosofía de equilibrio entre el yin y el yang, y el uso de ingredientes frescos.</code> | <code>Los principios de la cocina china se centran en el equilibrio entre los sabores dulce y salado, así como en el uso de productos naturales.</code> | <code>0.4</code> | <code>GPT</code> |
243
+ | <code>El neokantismo es una corriente filosófica que busca revitalizar los principios del pensamiento de Immanuel Kant en el contexto moderno.</code> | <code>Los neokantianos buscan actualizar los conceptos de Immanuel Kant para aplicarlos a la filosofía contemporánea.</code> | <code>0.4</code> | <code>GPT</code> |
244
+ | <code>La teoría de la paridad del poder adquisitivo sostiene que en el largo plazo, los tipos de cambio entre dos monedas deben ajustarse para reflejar las diferencias en los niveles de precios de los países.</code> | <code>La teoría de la paridad del poder adquisitivo se refiere a la relación entre los niveles de precios de los países y los tipos de cambio entre dos monedas, con el objetivo de mantener el equilibrio a largo plazo.</code> | <code>0.3</code> | <code>GPT</code> |
245
+ * Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
246
+ ```json
247
+ {
248
+ "scale": 20.0,
249
+ "similarity_fct": "pairwise_cos_sim"
250
+ }
251
+ ```
252
+
253
+ #### all-nli-triplet
254
+
255
+ * Dataset: [all-nli-triplet](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
256
+ * Size: 10,000 training samples
257
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
258
+ * Approximate statistics based on the first 1000 samples:
259
+ | | anchor | positive | negative |
260
+ |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
261
+ | type | string | string | string |
262
+ | details | <ul><li>min: 7 tokens</li><li>mean: 10.9 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.62 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 14.76 tokens</li><li>max: 55 tokens</li></ul> |
263
+ * Samples:
264
+ | anchor | positive | negative |
265
+ |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------|
266
+ | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>A person is at a diner, ordering an omelette.</code> |
267
+ | <code>Children smiling and waving at camera</code> | <code>There are children present</code> | <code>The kids are frowning</code> |
268
+ | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code> |
269
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
270
+ ```json
271
+ {
272
+ "scale": 20.0,
273
+ "similarity_fct": "cos_sim"
274
+ }
275
+ ```
276
+
277
+ #### stsb
278
+
279
+ * Dataset: [stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
280
+ * Size: 5,749 training samples
281
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
282
+ * Approximate statistics based on the first 1000 samples:
283
+ | | sentence1 | sentence2 | score |
284
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
285
+ | type | string | string | float |
286
+ | details | <ul><li>min: 6 tokens</li><li>mean: 11.08 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 11.05 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
287
+ * Samples:
288
+ | sentence1 | sentence2 | score |
289
+ |:-----------------------------------------------------------|:----------------------------------------------------------------------|:------------------|
290
+ | <code>A plane is taking off.</code> | <code>An air plane is taking off.</code> | <code>1.0</code> |
291
+ | <code>A man is playing a large flute.</code> | <code>A man is playing a flute.</code> | <code>0.76</code> |
292
+ | <code>A man is spreading shreded cheese on a pizza.</code> | <code>A man is spreading shredded cheese on an uncooked pizza.</code> | <code>0.76</code> |
293
+ * Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
294
+ ```json
295
+ {
296
+ "scale": 20.0,
297
+ "similarity_fct": "pairwise_cos_sim"
298
+ }
299
+ ```
300
+
301
+ ### Evaluation Datasets
302
+
303
+ #### dataset
304
+
305
+ * Dataset: dataset
306
+ * Size: 131 evaluation samples
307
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
308
+ * Approximate statistics based on the first 1000 samples:
309
+ | | anchor | positive | negative |
310
+ |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
311
+ | type | string | string | string |
312
+ | details | <ul><li>min: 7 tokens</li><li>mean: 19.38 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 20.61 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.47 tokens</li><li>max: 122 tokens</li></ul> |
313
+ * Samples:
314
+ | anchor | positive | negative |
315
+ |:---------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------|
316
+ | <code>Curso de matemáticas avanzadas para ingeniería</code> | <code>Ingeniero con habilidades en cálculo y álgebra avanzada</code> | <code>Chef con experiencia en repostería</code> |
317
+ | <code>Fundamentos de análisis financiero y gestión de riesgos</code> | <code>Analista financiero con habilidades en gestión de riesgos y análisis de inversiones</code> | <code>Chef con experiencia en cocina tradicion</code> |
318
+ | <code>Project Management with Agile Methodologies and Scrum.</code> | <code>Project manager with skills in Scrum and agile methodologies.</code> | <code>Mechanical engineer with structural design experience.</code> |
319
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
320
+ ```json
321
+ {
322
+ "scale": 20.0,
323
+ "similarity_fct": "cos_sim"
324
+ }
325
+ ```
326
+
327
+ #### distilbert
328
+
329
+ * Dataset: [distilbert](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-tas-b) at [e63dd83](https://huggingface.co/datasets/sentence-transformers/msmarco-msmarco-distilbert-base-tas-b/tree/e63dd8397db956cdde78e5e18c0d734585874db2)
330
+ * Size: 100 evaluation samples
331
+ * Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
332
+ * Approximate statistics based on the first 1000 samples:
333
+ | | query | positive | negative |
334
+ |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
335
+ | type | string | string | string |
336
+ | details | <ul><li>min: 5 tokens</li><li>mean: 9.87 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 28 tokens</li><li>mean: 86.98 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 23 tokens</li><li>mean: 80.97 tokens</li><li>max: 128 tokens</li></ul> |
337
+ * Samples:
338
+ | query | positive | negative |
339
+ |:-----------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
340
+ | <code>when was the town of farragut tn incorporated</code> | <code>In January of 1980, residents decided to incorporate by an overwhelming margin. The Town of Farragut was incorporated on January 16, 1980, with the first board of Mayor and Alderman elected on April 1, 1980.</code> | <code>Farragut is a town which straddles both Knox and Loudon counties in Tennessee. It is a suburb of Knoxville. The town's population was 20,676 at the 2010 census. It is included in the Knoxville Metropolitan Area. The town is named in honor of American Civil War Admiral David Farragut, who was born just east of Farragut at Campbell's Station in 1801.</code> |
341
+ | <code>how long to roast a chicken</code> | <code>There are two methods for roasting a whole chicken: Regular method: 1 Preheat oven to 350 degrees F (175 degrees C). 2 Roast whole (thawed) chickens for 20 minutes per pound, plus an additional 15 minutes.</code> | <code>1 Roast the chicken at 450 degrees for 20 minutes, then reduce the heat to 400 degrees and continue roasting for about 40 minutes (or until the internal temperature reaches about 175 to 180 degrees F. about 1 hour or a little less).</code> |
342
+ | <code>what is a hormone?</code> | <code>What Are Hormones, And What Do They Do? Hormones are special chemical messengers in the body that are created in the endocrine glands. These messengers control most major bodily functions, from simple basic needs like hunger to complex systems like reproduction, and even the emotions and mood. Understanding the major hormones and what they do will help patients take control of their health. Prostaglandins.</code> | <code>Hormone is a chemical substance that is produced in one part of the body (by an endocrine gland) and is carried in the blood to other distant organs or tissues where it acts to modify their structure or function.</code> |
343
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
344
+ ```json
345
+ {
346
+ "scale": 20.0,
347
+ "similarity_fct": "cos_sim"
348
+ }
349
+ ```
350
+
351
+ #### all-nli-triplet
352
+
353
+ * Dataset: [all-nli-triplet](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab)
354
+ * Size: 100 evaluation samples
355
+ * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
356
+ * Approximate statistics based on the first 1000 samples:
357
+ | | anchor | positive | negative |
358
+ |:--------|:-------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
359
+ | type | string | string | string |
360
+ | details | <ul><li>min: 7 tokens</li><li>mean: 7.0 tokens</li><li>max: 7 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 20.62 tokens</li><li>max: 78 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 16.0 tokens</li><li>max: 21 tokens</li></ul> |
361
+ * Samples:
362
+ | anchor | positive | negative |
363
+ |:----------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|
364
+ | <code>The men are outside.</code> | <code>A man in a green and white "Irish" baseball uniform is lunging forward as though to throw the ball underhand as an older man in umpire's uniform looks on.</code> | <code>Two men are leaning out of a window and looking at something to the right of them.</code> |
365
+ | <code>The men are outside.</code> | <code>Three men getting some kind of grass together on a windy day.</code> | <code>Two women work on a project outdoors.</code> |
366
+ | <code>The men are outside.</code> | <code>Three men getting some kind of grass together on a windy day.</code> | <code>Two men are leaning out of a window and looking at something to the right of them.</code> |
367
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
368
+ ```json
369
+ {
370
+ "scale": 20.0,
371
+ "similarity_fct": "cos_sim"
372
+ }
373
+ ```
374
+
375
+ #### stsb
376
+
377
+ * Dataset: [stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
378
+ * Size: 1,500 evaluation samples
379
+ * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
380
+ * Approximate statistics based on the first 1000 samples:
381
+ | | sentence1 | sentence2 | score |
382
+ |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
383
+ | type | string | string | float |
384
+ | details | <ul><li>min: 5 tokens</li><li>mean: 16.55 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 16.5 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> |
385
+ * Samples:
386
+ | sentence1 | sentence2 | score |
387
+ |:--------------------------------------------------|:------------------------------------------------------|:------------------|
388
+ | <code>A man with a hard hat is dancing.</code> | <code>A man wearing a hard hat is dancing.</code> | <code>1.0</code> |
389
+ | <code>A young child is riding a horse.</code> | <code>A child is riding a horse.</code> | <code>0.95</code> |
390
+ | <code>A man is feeding a mouse to a snake.</code> | <code>The man is feeding a mouse to the snake.</code> | <code>1.0</code> |
391
+ * Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
392
+ ```json
393
+ {
394
+ "scale": 20.0,
395
+ "similarity_fct": "pairwise_cos_sim"
396
+ }
397
+ ```
398
+
399
+ ### Training Hyperparameters
400
+
401
+ #### All Hyperparameters
402
+ <details><summary>Click to expand</summary>
403
+
404
+ - `overwrite_output_dir`: False
405
+ - `do_predict`: False
406
+ - `eval_strategy`: no
407
+ - `prediction_loss_only`: True
408
+ - `per_device_train_batch_size`: 8
409
+ - `per_device_eval_batch_size`: 8
410
+ - `per_gpu_train_batch_size`: None
411
+ - `per_gpu_eval_batch_size`: None
412
+ - `gradient_accumulation_steps`: 1
413
+ - `eval_accumulation_steps`: None
414
+ - `learning_rate`: 5e-05
415
+ - `weight_decay`: 0.0
416
+ - `adam_beta1`: 0.9
417
+ - `adam_beta2`: 0.999
418
+ - `adam_epsilon`: 1e-08
419
+ - `max_grad_norm`: 1.0
420
+ - `num_train_epochs`: 3.0
421
+ - `max_steps`: -1
422
+ - `lr_scheduler_type`: linear
423
+ - `lr_scheduler_kwargs`: {}
424
+ - `warmup_ratio`: 0.0
425
+ - `warmup_steps`: 0
426
+ - `log_level`: passive
427
+ - `log_level_replica`: warning
428
+ - `log_on_each_node`: True
429
+ - `logging_nan_inf_filter`: True
430
+ - `save_safetensors`: True
431
+ - `save_on_each_node`: False
432
+ - `save_only_model`: False
433
+ - `restore_callback_states_from_checkpoint`: False
434
+ - `no_cuda`: False
435
+ - `use_cpu`: False
436
+ - `use_mps_device`: False
437
+ - `seed`: 42
438
+ - `data_seed`: None
439
+ - `jit_mode_eval`: False
440
+ - `use_ipex`: False
441
+ - `bf16`: False
442
+ - `fp16`: False
443
+ - `fp16_opt_level`: O1
444
+ - `half_precision_backend`: auto
445
+ - `bf16_full_eval`: False
446
+ - `fp16_full_eval`: False
447
+ - `tf32`: None
448
+ - `local_rank`: 0
449
+ - `ddp_backend`: None
450
+ - `tpu_num_cores`: None
451
+ - `tpu_metrics_debug`: False
452
+ - `debug`: []
453
+ - `dataloader_drop_last`: False
454
+ - `dataloader_num_workers`: 0
455
+ - `dataloader_prefetch_factor`: None
456
+ - `past_index`: -1
457
+ - `disable_tqdm`: False
458
+ - `remove_unused_columns`: True
459
+ - `label_names`: None
460
+ - `load_best_model_at_end`: False
461
+ - `ignore_data_skip`: False
462
+ - `fsdp`: []
463
+ - `fsdp_min_num_params`: 0
464
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
465
+ - `fsdp_transformer_layer_cls_to_wrap`: None
466
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
467
+ - `deepspeed`: None
468
+ - `label_smoothing_factor`: 0.0
469
+ - `optim`: adamw_torch
470
+ - `optim_args`: None
471
+ - `adafactor`: False
472
+ - `group_by_length`: False
473
+ - `length_column_name`: length
474
+ - `ddp_find_unused_parameters`: None
475
+ - `ddp_bucket_cap_mb`: None
476
+ - `ddp_broadcast_buffers`: False
477
+ - `dataloader_pin_memory`: True
478
+ - `dataloader_persistent_workers`: False
479
+ - `skip_memory_metrics`: True
480
+ - `use_legacy_prediction_loop`: False
481
+ - `push_to_hub`: False
482
+ - `resume_from_checkpoint`: None
483
+ - `hub_model_id`: None
484
+ - `hub_strategy`: every_save
485
+ - `hub_private_repo`: False
486
+ - `hub_always_push`: False
487
+ - `gradient_checkpointing`: False
488
+ - `gradient_checkpointing_kwargs`: None
489
+ - `include_inputs_for_metrics`: False
490
+ - `eval_do_concat_batches`: True
491
+ - `fp16_backend`: auto
492
+ - `push_to_hub_model_id`: None
493
+ - `push_to_hub_organization`: None
494
+ - `mp_parameters`:
495
+ - `auto_find_batch_size`: False
496
+ - `full_determinism`: False
497
+ - `torchdynamo`: None
498
+ - `ray_scope`: last
499
+ - `ddp_timeout`: 1800
500
+ - `torch_compile`: False
501
+ - `torch_compile_backend`: None
502
+ - `torch_compile_mode`: None
503
+ - `dispatch_batches`: None
504
+ - `split_batches`: None
505
+ - `include_tokens_per_second`: False
506
+ - `include_num_input_tokens_seen`: False
507
+ - `neftune_noise_alpha`: None
508
+ - `optim_target_modules`: None
509
+ - `batch_eval_metrics`: False
510
+ - `batch_sampler`: batch_sampler
511
+ - `multi_dataset_batch_sampler`: proportional
512
+
513
+ </details>
514
+
515
+ ### Training Logs
516
+ | Epoch | Step | Training Loss | distilbert loss | all-nli-triplet loss | stsb loss | dataset loss |
517
+ |:------:|:----:|:-------------:|:---------------:|:--------------------:|:---------:|:------------:|
518
+ | 0.2188 | 500 | 1.9313 | - | - | - | - |
519
+ | 0.4376 | 1000 | 1.766 | - | - | - | - |
520
+ | 0.6565 | 1500 | 1.6605 | - | - | - | - |
521
+ | 0.8753 | 2000 | 1.6541 | - | - | - | - |
522
+ | 1.0941 | 2500 | 1.6496 | - | - | - | - |
523
+ | 1.3129 | 3000 | 1.4151 | - | - | - | - |
524
+ | 1.5317 | 3500 | 1.3921 | - | - | - | - |
525
+ | 1.7505 | 4000 | 1.301 | - | - | - | - |
526
+ | 1.9694 | 4500 | 1.3356 | - | - | - | - |
527
+ | 2.1882 | 5000 | 1.212 | - | - | - | - |
528
+ | 2.4070 | 5500 | 1.1476 | - | - | - | - |
529
+ | 2.6258 | 6000 | 1.1854 | - | - | - | - |
530
+ | 2.8446 | 6500 | 1.0177 | - | - | - | - |
531
+ | 3.0 | 6855 | - | 1.3369 | 2.6425 | 4.8295 | 0.0736 |
532
+
533
+
534
+ ### Framework Versions
535
+ - Python: 3.9.13
536
+ - Sentence Transformers: 3.0.1
537
+ - Transformers: 4.41.2
538
+ - PyTorch: 2.3.1+cpu
539
+ - Accelerate: 0.31.0
540
+ - Datasets: 2.20.0
541
+ - Tokenizers: 0.19.1
542
+
543
+ ## Citation
544
+
545
+ ### BibTeX
546
+
547
+ #### Sentence Transformers
548
+ ```bibtex
549
+ @inproceedings{reimers-2019-sentence-bert,
550
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
551
+ author = "Reimers, Nils and Gurevych, Iryna",
552
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
553
+ month = "11",
554
+ year = "2019",
555
+ publisher = "Association for Computational Linguistics",
556
+ url = "https://arxiv.org/abs/1908.10084",
557
+ }
558
+ ```
559
+
560
+ #### MultipleNegativesRankingLoss
561
+ ```bibtex
562
+ @misc{henderson2017efficient,
563
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
564
+ 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},
565
+ year={2017},
566
+ eprint={1705.00652},
567
+ archivePrefix={arXiv},
568
+ primaryClass={cs.CL}
569
+ }
570
+ ```
571
+
572
+ #### CoSENTLoss
573
+ ```bibtex
574
+ @online{kexuefm-8847,
575
+ title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
576
+ author={Su Jianlin},
577
+ year={2022},
578
+ month={Jan},
579
+ url={https://kexue.fm/archives/8847},
580
+ }
581
+ ```
582
+
583
+ <!--
584
+ ## Glossary
585
+
586
+ *Clearly define terms in order to be accessible across audiences.*
587
+ -->
588
+
589
+ <!--
590
+ ## Model Card Authors
591
+
592
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
593
+ -->
594
+
595
+ <!--
596
+ ## Model Card Contact
597
+
598
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
599
+ -->
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "xlm-roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.41.2",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.3.1+cpu"
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:dd4c946531a609d1618db20e90eea97a3324c5458c103c1a87f6f8bab6b94d9a
3
+ size 1112197096
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": 128,
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
3
+ size 17082987
tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 128,
50
+ "model_max_length": 128,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "XLMRobertaTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }