Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +744 -0
- config.json +24 -0
- config_sentence_transformers.json +9 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,744 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: []
|
3 |
+
library_name: sentence-transformers
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- sentence-similarity
|
7 |
+
- feature-extraction
|
8 |
+
- generated
|
9 |
+
base_model: sentence-transformers/stsb-distilbert-base
|
10 |
+
metrics:
|
11 |
+
- cosine_accuracy
|
12 |
+
- cosine_accuracy_threshold
|
13 |
+
- cosine_f1
|
14 |
+
- cosine_f1_threshold
|
15 |
+
- cosine_precision
|
16 |
+
- cosine_recall
|
17 |
+
- cosine_ap
|
18 |
+
- manhattan_accuracy
|
19 |
+
- manhattan_accuracy_threshold
|
20 |
+
- manhattan_f1
|
21 |
+
- manhattan_f1_threshold
|
22 |
+
- manhattan_precision
|
23 |
+
- manhattan_recall
|
24 |
+
- manhattan_ap
|
25 |
+
- euclidean_accuracy
|
26 |
+
- euclidean_accuracy_threshold
|
27 |
+
- euclidean_f1
|
28 |
+
- euclidean_f1_threshold
|
29 |
+
- euclidean_precision
|
30 |
+
- euclidean_recall
|
31 |
+
- euclidean_ap
|
32 |
+
- dot_accuracy
|
33 |
+
- dot_accuracy_threshold
|
34 |
+
- dot_f1
|
35 |
+
- dot_f1_threshold
|
36 |
+
- dot_precision
|
37 |
+
- dot_recall
|
38 |
+
- dot_ap
|
39 |
+
- max_accuracy
|
40 |
+
- max_accuracy_threshold
|
41 |
+
- max_f1
|
42 |
+
- max_f1_threshold
|
43 |
+
- max_precision
|
44 |
+
- max_recall
|
45 |
+
- max_ap
|
46 |
+
- average_precision
|
47 |
+
- f1
|
48 |
+
- precision
|
49 |
+
- recall
|
50 |
+
- threshold
|
51 |
+
- cosine_accuracy@1
|
52 |
+
- cosine_accuracy@3
|
53 |
+
- cosine_accuracy@5
|
54 |
+
- cosine_accuracy@10
|
55 |
+
- cosine_precision@1
|
56 |
+
- cosine_precision@3
|
57 |
+
- cosine_precision@5
|
58 |
+
- cosine_precision@10
|
59 |
+
- cosine_recall@1
|
60 |
+
- cosine_recall@3
|
61 |
+
- cosine_recall@5
|
62 |
+
- cosine_recall@10
|
63 |
+
- cosine_ndcg@10
|
64 |
+
- cosine_mrr@10
|
65 |
+
- cosine_map@100
|
66 |
+
- dot_accuracy@1
|
67 |
+
- dot_accuracy@3
|
68 |
+
- dot_accuracy@5
|
69 |
+
- dot_accuracy@10
|
70 |
+
- dot_precision@1
|
71 |
+
- dot_precision@3
|
72 |
+
- dot_precision@5
|
73 |
+
- dot_precision@10
|
74 |
+
- dot_recall@1
|
75 |
+
- dot_recall@3
|
76 |
+
- dot_recall@5
|
77 |
+
- dot_recall@10
|
78 |
+
- dot_ndcg@10
|
79 |
+
- dot_mrr@10
|
80 |
+
- dot_map@100
|
81 |
+
widget:
|
82 |
+
- source_sentence: How porn is made?
|
83 |
+
sentences:
|
84 |
+
- How is porn made?
|
85 |
+
- How do you study before a test?
|
86 |
+
- What is the best book for afcat?
|
87 |
+
- source_sentence: Is WW3 inevitable?
|
88 |
+
sentences:
|
89 |
+
- How close to WW3 are we?
|
90 |
+
- Is it ok not to know everything?
|
91 |
+
- How can I get good marks on my exam?
|
92 |
+
- source_sentence: How do stop smoking?
|
93 |
+
sentences:
|
94 |
+
- How did you quit/stop smoking?
|
95 |
+
- How can I gain weight naturally?
|
96 |
+
- What movie is the best movie of 2016?
|
97 |
+
- source_sentence: What is astrology?
|
98 |
+
sentences:
|
99 |
+
- What really is astrology?
|
100 |
+
- How do I control blood pressure?
|
101 |
+
- How should I reduce weight easily?
|
102 |
+
- source_sentence: What is SMS API?
|
103 |
+
sentences:
|
104 |
+
- What is an SMS API?
|
105 |
+
- How will Sound travel in SPACE?
|
106 |
+
- Do we live inside a black hole?
|
107 |
+
pipeline_tag: sentence-similarity
|
108 |
+
model-index:
|
109 |
+
- name: SentenceTransformer based on sentence-transformers/stsb-distilbert-base
|
110 |
+
results:
|
111 |
+
- task:
|
112 |
+
type: binary-classification
|
113 |
+
name: Binary Classification
|
114 |
+
dataset:
|
115 |
+
name: Unknown
|
116 |
+
type: unknown
|
117 |
+
metrics:
|
118 |
+
- type: cosine_accuracy
|
119 |
+
value: 0.770712179816613
|
120 |
+
name: Cosine Accuracy
|
121 |
+
- type: cosine_accuracy_threshold
|
122 |
+
value: 0.8169694542884827
|
123 |
+
name: Cosine Accuracy Threshold
|
124 |
+
- type: cosine_f1
|
125 |
+
value: 0.7086398522340053
|
126 |
+
name: Cosine F1
|
127 |
+
- type: cosine_f1_threshold
|
128 |
+
value: 0.7420324087142944
|
129 |
+
name: Cosine F1 Threshold
|
130 |
+
- type: cosine_precision
|
131 |
+
value: 0.6032968224704479
|
132 |
+
name: Cosine Precision
|
133 |
+
- type: cosine_recall
|
134 |
+
value: 0.8585539007639479
|
135 |
+
name: Cosine Recall
|
136 |
+
- type: cosine_ap
|
137 |
+
value: 0.7191176594498068
|
138 |
+
name: Cosine Ap
|
139 |
+
- type: manhattan_accuracy
|
140 |
+
value: 0.7729301344296882
|
141 |
+
name: Manhattan Accuracy
|
142 |
+
- type: manhattan_accuracy_threshold
|
143 |
+
value: 181.4663848876953
|
144 |
+
name: Manhattan Accuracy Threshold
|
145 |
+
- type: manhattan_f1
|
146 |
+
value: 0.7082838527457715
|
147 |
+
name: Manhattan F1
|
148 |
+
- type: manhattan_f1_threshold
|
149 |
+
value: 222.911865234375
|
150 |
+
name: Manhattan F1 Threshold
|
151 |
+
- type: manhattan_precision
|
152 |
+
value: 0.6063303659742829
|
153 |
+
name: Manhattan Precision
|
154 |
+
- type: manhattan_recall
|
155 |
+
value: 0.8514545875453353
|
156 |
+
name: Manhattan Recall
|
157 |
+
- type: manhattan_ap
|
158 |
+
value: 0.7188011305084623
|
159 |
+
name: Manhattan Ap
|
160 |
+
- type: euclidean_accuracy
|
161 |
+
value: 0.7736333883313948
|
162 |
+
name: Euclidean Accuracy
|
163 |
+
- type: euclidean_accuracy_threshold
|
164 |
+
value: 8.356552124023438
|
165 |
+
name: Euclidean Accuracy Threshold
|
166 |
+
- type: euclidean_f1
|
167 |
+
value: 0.7088200276731988
|
168 |
+
name: Euclidean F1
|
169 |
+
- type: euclidean_f1_threshold
|
170 |
+
value: 10.092880249023438
|
171 |
+
name: Euclidean F1 Threshold
|
172 |
+
- type: euclidean_precision
|
173 |
+
value: 0.6079037421348935
|
174 |
+
name: Euclidean Precision
|
175 |
+
- type: euclidean_recall
|
176 |
+
value: 0.8499112585847673
|
177 |
+
name: Euclidean Recall
|
178 |
+
- type: euclidean_ap
|
179 |
+
value: 0.719131590718056
|
180 |
+
name: Euclidean Ap
|
181 |
+
- type: dot_accuracy
|
182 |
+
value: 0.7441508209136891
|
183 |
+
name: Dot Accuracy
|
184 |
+
- type: dot_accuracy_threshold
|
185 |
+
value: 168.56625366210938
|
186 |
+
name: Dot Accuracy Threshold
|
187 |
+
- type: dot_f1
|
188 |
+
value: 0.6831510249103777
|
189 |
+
name: Dot F1
|
190 |
+
- type: dot_f1_threshold
|
191 |
+
value: 142.45849609375
|
192 |
+
name: Dot F1 Threshold
|
193 |
+
- type: dot_precision
|
194 |
+
value: 0.5665209879052749
|
195 |
+
name: Dot Precision
|
196 |
+
- type: dot_recall
|
197 |
+
value: 0.8602515626205726
|
198 |
+
name: Dot Recall
|
199 |
+
- type: dot_ap
|
200 |
+
value: 0.6693622133717865
|
201 |
+
name: Dot Ap
|
202 |
+
- type: max_accuracy
|
203 |
+
value: 0.7736333883313948
|
204 |
+
name: Max Accuracy
|
205 |
+
- type: max_accuracy_threshold
|
206 |
+
value: 181.4663848876953
|
207 |
+
name: Max Accuracy Threshold
|
208 |
+
- type: max_f1
|
209 |
+
value: 0.7088200276731988
|
210 |
+
name: Max F1
|
211 |
+
- type: max_f1_threshold
|
212 |
+
value: 222.911865234375
|
213 |
+
name: Max F1 Threshold
|
214 |
+
- type: max_precision
|
215 |
+
value: 0.6079037421348935
|
216 |
+
name: Max Precision
|
217 |
+
- type: max_recall
|
218 |
+
value: 0.8602515626205726
|
219 |
+
name: Max Recall
|
220 |
+
- type: max_ap
|
221 |
+
value: 0.719131590718056
|
222 |
+
name: Max Ap
|
223 |
+
- task:
|
224 |
+
type: paraphrase-mining
|
225 |
+
name: Paraphrase Mining
|
226 |
+
dataset:
|
227 |
+
name: dev
|
228 |
+
type: dev
|
229 |
+
metrics:
|
230 |
+
- type: average_precision
|
231 |
+
value: 0.47803306271270435
|
232 |
+
name: Average Precision
|
233 |
+
- type: f1
|
234 |
+
value: 0.5119182746878547
|
235 |
+
name: F1
|
236 |
+
- type: precision
|
237 |
+
value: 0.4683281412253375
|
238 |
+
name: Precision
|
239 |
+
- type: recall
|
240 |
+
value: 0.5644555694618273
|
241 |
+
name: Recall
|
242 |
+
- type: threshold
|
243 |
+
value: 0.8193174600601196
|
244 |
+
name: Threshold
|
245 |
+
- task:
|
246 |
+
type: information-retrieval
|
247 |
+
name: Information Retrieval
|
248 |
+
dataset:
|
249 |
+
name: Unknown
|
250 |
+
type: unknown
|
251 |
+
metrics:
|
252 |
+
- type: cosine_accuracy@1
|
253 |
+
value: 0.9654
|
254 |
+
name: Cosine Accuracy@1
|
255 |
+
- type: cosine_accuracy@3
|
256 |
+
value: 0.9904
|
257 |
+
name: Cosine Accuracy@3
|
258 |
+
- type: cosine_accuracy@5
|
259 |
+
value: 0.9948
|
260 |
+
name: Cosine Accuracy@5
|
261 |
+
- type: cosine_accuracy@10
|
262 |
+
value: 0.9974
|
263 |
+
name: Cosine Accuracy@10
|
264 |
+
- type: cosine_precision@1
|
265 |
+
value: 0.9654
|
266 |
+
name: Cosine Precision@1
|
267 |
+
- type: cosine_precision@3
|
268 |
+
value: 0.43553333333333333
|
269 |
+
name: Cosine Precision@3
|
270 |
+
- type: cosine_precision@5
|
271 |
+
value: 0.28064
|
272 |
+
name: Cosine Precision@5
|
273 |
+
- type: cosine_precision@10
|
274 |
+
value: 0.14934
|
275 |
+
name: Cosine Precision@10
|
276 |
+
- type: cosine_recall@1
|
277 |
+
value: 0.8251379240296788
|
278 |
+
name: Cosine Recall@1
|
279 |
+
- type: cosine_recall@3
|
280 |
+
value: 0.9549051140803786
|
281 |
+
name: Cosine Recall@3
|
282 |
+
- type: cosine_recall@5
|
283 |
+
value: 0.9757885342898082
|
284 |
+
name: Cosine Recall@5
|
285 |
+
- type: cosine_recall@10
|
286 |
+
value: 0.9898260744103871
|
287 |
+
name: Cosine Recall@10
|
288 |
+
- type: cosine_ndcg@10
|
289 |
+
value: 0.9786162291363164
|
290 |
+
name: Cosine Ndcg@10
|
291 |
+
- type: cosine_mrr@10
|
292 |
+
value: 0.9785615873015873
|
293 |
+
name: Cosine Mrr@10
|
294 |
+
- type: cosine_map@100
|
295 |
+
value: 0.9713888565523412
|
296 |
+
name: Cosine Map@100
|
297 |
+
- type: dot_accuracy@1
|
298 |
+
value: 0.9512
|
299 |
+
name: Dot Accuracy@1
|
300 |
+
- type: dot_accuracy@3
|
301 |
+
value: 0.985
|
302 |
+
name: Dot Accuracy@3
|
303 |
+
- type: dot_accuracy@5
|
304 |
+
value: 0.9914
|
305 |
+
name: Dot Accuracy@5
|
306 |
+
- type: dot_accuracy@10
|
307 |
+
value: 0.9964
|
308 |
+
name: Dot Accuracy@10
|
309 |
+
- type: dot_precision@1
|
310 |
+
value: 0.9512
|
311 |
+
name: Dot Precision@1
|
312 |
+
- type: dot_precision@3
|
313 |
+
value: 0.4303333333333333
|
314 |
+
name: Dot Precision@3
|
315 |
+
- type: dot_precision@5
|
316 |
+
value: 0.2788
|
317 |
+
name: Dot Precision@5
|
318 |
+
- type: dot_precision@10
|
319 |
+
value: 0.14896
|
320 |
+
name: Dot Precision@10
|
321 |
+
- type: dot_recall@1
|
322 |
+
value: 0.8119095906963455
|
323 |
+
name: Dot Recall@1
|
324 |
+
- type: dot_recall@3
|
325 |
+
value: 0.9459636855089498
|
326 |
+
name: Dot Recall@3
|
327 |
+
- type: dot_recall@5
|
328 |
+
value: 0.9708092557905298
|
329 |
+
name: Dot Recall@5
|
330 |
+
- type: dot_recall@10
|
331 |
+
value: 0.9883617291912786
|
332 |
+
name: Dot Recall@10
|
333 |
+
- type: dot_ndcg@10
|
334 |
+
value: 0.9702609044345125
|
335 |
+
name: Dot Ndcg@10
|
336 |
+
- type: dot_mrr@10
|
337 |
+
value: 0.9693138888888887
|
338 |
+
name: Dot Mrr@10
|
339 |
+
- type: dot_map@100
|
340 |
+
value: 0.9599586870108953
|
341 |
+
name: Dot Map@100
|
342 |
+
---
|
343 |
+
|
344 |
+
# SentenceTransformer based on sentence-transformers/stsb-distilbert-base
|
345 |
+
|
346 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base). 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.
|
347 |
+
|
348 |
+
## Model Details
|
349 |
+
|
350 |
+
### Model Description
|
351 |
+
- **Model Type:** Sentence Transformer
|
352 |
+
- **Base model:** [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base)
|
353 |
+
- **Maximum Sequence Length:** 128 tokens
|
354 |
+
- **Output Dimensionality:** 768 tokens
|
355 |
+
<!-- - **Training Dataset:** Unknown -->
|
356 |
+
<!-- - **Language:** Unknown -->
|
357 |
+
<!-- - **License:** Unknown -->
|
358 |
+
|
359 |
+
### Model Sources
|
360 |
+
|
361 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
362 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
363 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
364 |
+
|
365 |
+
### Full Model Architecture
|
366 |
+
|
367 |
+
```
|
368 |
+
SentenceTransformer(
|
369 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
|
370 |
+
(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})
|
371 |
+
)
|
372 |
+
```
|
373 |
+
|
374 |
+
## Usage
|
375 |
+
|
376 |
+
### Direct Usage (Sentence Transformers)
|
377 |
+
|
378 |
+
First install the Sentence Transformers library:
|
379 |
+
|
380 |
+
```bash
|
381 |
+
pip install -U sentence-transformers
|
382 |
+
```
|
383 |
+
|
384 |
+
Then you can load this model and run inference.
|
385 |
+
```python
|
386 |
+
from sentence_transformers import SentenceTransformer
|
387 |
+
|
388 |
+
# Download from the 🤗 Hub
|
389 |
+
model = SentenceTransformer("tomaarsen/stsb-distilbert-base-quora-duplicate-questions")
|
390 |
+
# Run inference
|
391 |
+
sentences = [
|
392 |
+
"What is a fetish?",
|
393 |
+
"What's a fetish?",
|
394 |
+
"Is it good to read sex stories?",
|
395 |
+
]
|
396 |
+
embeddings = model.encode(sentences)
|
397 |
+
print(embeddings.shape)
|
398 |
+
# [3, 768]
|
399 |
+
```
|
400 |
+
|
401 |
+
<!--
|
402 |
+
### Direct Usage (Transformers)
|
403 |
+
|
404 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
405 |
+
|
406 |
+
</details>
|
407 |
+
-->
|
408 |
+
|
409 |
+
<!--
|
410 |
+
### Downstream Usage (Sentence Transformers)
|
411 |
+
|
412 |
+
You can finetune this model on your own dataset.
|
413 |
+
|
414 |
+
<details><summary>Click to expand</summary>
|
415 |
+
|
416 |
+
</details>
|
417 |
+
-->
|
418 |
+
|
419 |
+
<!--
|
420 |
+
### Out-of-Scope Use
|
421 |
+
|
422 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
423 |
+
-->
|
424 |
+
|
425 |
+
## Evaluation
|
426 |
+
|
427 |
+
### Metrics
|
428 |
+
|
429 |
+
#### Binary Classification
|
430 |
+
|
431 |
+
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
|
432 |
+
|
433 |
+
| Metric | Value |
|
434 |
+
|:-----------------------------|:-----------|
|
435 |
+
| **cosine_accuracy** | **0.7707** |
|
436 |
+
| cosine_accuracy_threshold | 0.817 |
|
437 |
+
| cosine_f1 | 0.7086 |
|
438 |
+
| cosine_f1_threshold | 0.742 |
|
439 |
+
| cosine_precision | 0.6033 |
|
440 |
+
| cosine_recall | 0.8586 |
|
441 |
+
| cosine_ap | 0.7191 |
|
442 |
+
| manhattan_accuracy | 0.7729 |
|
443 |
+
| manhattan_accuracy_threshold | 181.4664 |
|
444 |
+
| manhattan_f1 | 0.7083 |
|
445 |
+
| manhattan_f1_threshold | 222.9119 |
|
446 |
+
| manhattan_precision | 0.6063 |
|
447 |
+
| manhattan_recall | 0.8515 |
|
448 |
+
| manhattan_ap | 0.7188 |
|
449 |
+
| euclidean_accuracy | 0.7736 |
|
450 |
+
| euclidean_accuracy_threshold | 8.3566 |
|
451 |
+
| euclidean_f1 | 0.7088 |
|
452 |
+
| euclidean_f1_threshold | 10.0929 |
|
453 |
+
| euclidean_precision | 0.6079 |
|
454 |
+
| euclidean_recall | 0.8499 |
|
455 |
+
| euclidean_ap | 0.7191 |
|
456 |
+
| dot_accuracy | 0.7442 |
|
457 |
+
| dot_accuracy_threshold | 168.5663 |
|
458 |
+
| dot_f1 | 0.6832 |
|
459 |
+
| dot_f1_threshold | 142.4585 |
|
460 |
+
| dot_precision | 0.5665 |
|
461 |
+
| dot_recall | 0.8603 |
|
462 |
+
| dot_ap | 0.6694 |
|
463 |
+
| max_accuracy | 0.7736 |
|
464 |
+
| max_accuracy_threshold | 181.4664 |
|
465 |
+
| max_f1 | 0.7088 |
|
466 |
+
| max_f1_threshold | 222.9119 |
|
467 |
+
| max_precision | 0.6079 |
|
468 |
+
| max_recall | 0.8603 |
|
469 |
+
| max_ap | 0.7191 |
|
470 |
+
|
471 |
+
#### Paraphrase Mining
|
472 |
+
* Dataset: `dev`
|
473 |
+
* Evaluated with [<code>ParaphraseMiningEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.ParaphraseMiningEvaluator)
|
474 |
+
|
475 |
+
| Metric | Value |
|
476 |
+
|:----------------------|:----------|
|
477 |
+
| **average_precision** | **0.478** |
|
478 |
+
| f1 | 0.5119 |
|
479 |
+
| precision | 0.4683 |
|
480 |
+
| recall | 0.5645 |
|
481 |
+
| threshold | 0.8193 |
|
482 |
+
|
483 |
+
#### Information Retrieval
|
484 |
+
|
485 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
486 |
+
|
487 |
+
| Metric | Value |
|
488 |
+
|:--------------------|:-----------|
|
489 |
+
| cosine_accuracy@1 | 0.9654 |
|
490 |
+
| cosine_accuracy@3 | 0.9904 |
|
491 |
+
| cosine_accuracy@5 | 0.9948 |
|
492 |
+
| cosine_accuracy@10 | 0.9974 |
|
493 |
+
| cosine_precision@1 | 0.9654 |
|
494 |
+
| cosine_precision@3 | 0.4355 |
|
495 |
+
| cosine_precision@5 | 0.2806 |
|
496 |
+
| cosine_precision@10 | 0.1493 |
|
497 |
+
| cosine_recall@1 | 0.8251 |
|
498 |
+
| cosine_recall@3 | 0.9549 |
|
499 |
+
| cosine_recall@5 | 0.9758 |
|
500 |
+
| cosine_recall@10 | 0.9898 |
|
501 |
+
| cosine_ndcg@10 | 0.9786 |
|
502 |
+
| cosine_mrr@10 | 0.9786 |
|
503 |
+
| **cosine_map@100** | **0.9714** |
|
504 |
+
| dot_accuracy@1 | 0.9512 |
|
505 |
+
| dot_accuracy@3 | 0.985 |
|
506 |
+
| dot_accuracy@5 | 0.9914 |
|
507 |
+
| dot_accuracy@10 | 0.9964 |
|
508 |
+
| dot_precision@1 | 0.9512 |
|
509 |
+
| dot_precision@3 | 0.4303 |
|
510 |
+
| dot_precision@5 | 0.2788 |
|
511 |
+
| dot_precision@10 | 0.149 |
|
512 |
+
| dot_recall@1 | 0.8119 |
|
513 |
+
| dot_recall@3 | 0.946 |
|
514 |
+
| dot_recall@5 | 0.9708 |
|
515 |
+
| dot_recall@10 | 0.9884 |
|
516 |
+
| dot_ndcg@10 | 0.9703 |
|
517 |
+
| dot_mrr@10 | 0.9693 |
|
518 |
+
| dot_map@100 | 0.96 |
|
519 |
+
|
520 |
+
<!--
|
521 |
+
## Bias, Risks and Limitations
|
522 |
+
|
523 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
524 |
+
-->
|
525 |
+
|
526 |
+
<!--
|
527 |
+
### Recommendations
|
528 |
+
|
529 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
530 |
+
-->
|
531 |
+
|
532 |
+
## Training Details
|
533 |
+
|
534 |
+
### Training Dataset
|
535 |
+
|
536 |
+
#### Unnamed Dataset
|
537 |
+
|
538 |
+
|
539 |
+
* Size: 207,326 training samples
|
540 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
541 |
+
* Approximate statistics based on the first 1000 samples:
|
542 |
+
| | sentence_0 | sentence_1 | label |
|
543 |
+
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------|
|
544 |
+
| type | string | string | int |
|
545 |
+
| details | <ul><li>min: 6 tokens</li><li>mean: 13.75 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.74 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>1: ~100.00%</li></ul> |
|
546 |
+
* Samples:
|
547 |
+
| sentence_0 | sentence_1 | label |
|
548 |
+
|:------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------|:---------------|
|
549 |
+
| <code>How do I improve writing skill by myself?</code> | <code>How can I improve writing skills?</code> | <code>1</code> |
|
550 |
+
| <code>Is it best to switch to Node.js from PHP?</code> | <code>Should I switch to Node.js or continue using PHP?</code> | <code>1</code> |
|
551 |
+
| <code>What do Hillary Clinton's supporters say when confronted with all her lies and scandals?</code> | <code>What do Clinton supporters say when confronted with her scandals such as the emails and 'Clinton Cash'?</code> | <code>1</code> |
|
552 |
+
* Loss: [<code>sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters:
|
553 |
+
```json
|
554 |
+
{
|
555 |
+
"scale": 20.0,
|
556 |
+
"similarity_fct": "cos_sim"
|
557 |
+
}
|
558 |
+
```
|
559 |
+
|
560 |
+
### Training Hyperparameters
|
561 |
+
#### Non-Default Hyperparameters
|
562 |
+
|
563 |
+
- per_device_train_batch_size: 64
|
564 |
+
- per_device_eval_batch_size: 64
|
565 |
+
- num_train_epochs: 1
|
566 |
+
- round_robin_sampler: True
|
567 |
+
|
568 |
+
#### All Hyperparameters
|
569 |
+
<details><summary>Click to expand</summary>
|
570 |
+
|
571 |
+
- overwrite_output_dir: False
|
572 |
+
- do_predict: False
|
573 |
+
- prediction_loss_only: False
|
574 |
+
- per_device_train_batch_size: 64
|
575 |
+
- per_device_eval_batch_size: 64
|
576 |
+
- per_gpu_train_batch_size: None
|
577 |
+
- per_gpu_eval_batch_size: None
|
578 |
+
- gradient_accumulation_steps: 1
|
579 |
+
- eval_accumulation_steps: None
|
580 |
+
- learning_rate: 5e-05
|
581 |
+
- weight_decay: 0.0
|
582 |
+
- adam_beta1: 0.9
|
583 |
+
- adam_beta2: 0.999
|
584 |
+
- adam_epsilon: 1e-08
|
585 |
+
- max_grad_norm: 1
|
586 |
+
- num_train_epochs: 1
|
587 |
+
- max_steps: -1
|
588 |
+
- lr_scheduler_type: linear
|
589 |
+
- lr_scheduler_kwargs: {}
|
590 |
+
- warmup_ratio: 0.0
|
591 |
+
- warmup_steps: 0
|
592 |
+
- log_level: passive
|
593 |
+
- log_level_replica: warning
|
594 |
+
- log_on_each_node: True
|
595 |
+
- logging_nan_inf_filter: True
|
596 |
+
- save_safetensors: True
|
597 |
+
- save_on_each_node: False
|
598 |
+
- save_only_model: False
|
599 |
+
- no_cuda: False
|
600 |
+
- use_cpu: False
|
601 |
+
- use_mps_device: False
|
602 |
+
- seed: 42
|
603 |
+
- data_seed: None
|
604 |
+
- jit_mode_eval: False
|
605 |
+
- use_ipex: False
|
606 |
+
- bf16: False
|
607 |
+
- fp16: False
|
608 |
+
- fp16_opt_level: O1
|
609 |
+
- half_precision_backend: auto
|
610 |
+
- bf16_full_eval: False
|
611 |
+
- fp16_full_eval: False
|
612 |
+
- tf32: None
|
613 |
+
- local_rank: 0
|
614 |
+
- ddp_backend: None
|
615 |
+
- tpu_num_cores: None
|
616 |
+
- tpu_metrics_debug: False
|
617 |
+
- debug: []
|
618 |
+
- dataloader_drop_last: False
|
619 |
+
- dataloader_num_workers: 0
|
620 |
+
- dataloader_prefetch_factor: None
|
621 |
+
- past_index: -1
|
622 |
+
- disable_tqdm: False
|
623 |
+
- remove_unused_columns: True
|
624 |
+
- label_names: None
|
625 |
+
- load_best_model_at_end: False
|
626 |
+
- ignore_data_skip: False
|
627 |
+
- fsdp: []
|
628 |
+
- fsdp_min_num_params: 0
|
629 |
+
- fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
630 |
+
- fsdp_transformer_layer_cls_to_wrap: None
|
631 |
+
- accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}
|
632 |
+
- deepspeed: None
|
633 |
+
- label_smoothing_factor: 0.0
|
634 |
+
- optim: adamw_torch
|
635 |
+
- optim_args: None
|
636 |
+
- adafactor: False
|
637 |
+
- group_by_length: False
|
638 |
+
- length_column_name: length
|
639 |
+
- ddp_find_unused_parameters: None
|
640 |
+
- ddp_bucket_cap_mb: None
|
641 |
+
- ddp_broadcast_buffers: None
|
642 |
+
- dataloader_pin_memory: True
|
643 |
+
- dataloader_persistent_workers: False
|
644 |
+
- skip_memory_metrics: True
|
645 |
+
- use_legacy_prediction_loop: False
|
646 |
+
- push_to_hub: False
|
647 |
+
- resume_from_checkpoint: None
|
648 |
+
- hub_model_id: None
|
649 |
+
- hub_strategy: every_save
|
650 |
+
- hub_private_repo: False
|
651 |
+
- hub_always_push: False
|
652 |
+
- gradient_checkpointing: False
|
653 |
+
- gradient_checkpointing_kwargs: None
|
654 |
+
- include_inputs_for_metrics: False
|
655 |
+
- fp16_backend: auto
|
656 |
+
- push_to_hub_model_id: None
|
657 |
+
- push_to_hub_organization: None
|
658 |
+
- mp_parameters:
|
659 |
+
- auto_find_batch_size: False
|
660 |
+
- full_determinism: False
|
661 |
+
- torchdynamo: None
|
662 |
+
- ray_scope: last
|
663 |
+
- ddp_timeout: 1800
|
664 |
+
- torch_compile: False
|
665 |
+
- torch_compile_backend: None
|
666 |
+
- torch_compile_mode: None
|
667 |
+
- dispatch_batches: None
|
668 |
+
- split_batches: None
|
669 |
+
- include_tokens_per_second: False
|
670 |
+
- include_num_input_tokens_seen: False
|
671 |
+
- neftune_noise_alpha: None
|
672 |
+
- optim_target_modules: None
|
673 |
+
- round_robin_sampler: True
|
674 |
+
|
675 |
+
</details>
|
676 |
+
|
677 |
+
### Training Logs
|
678 |
+
| Epoch | Step | Training Loss | cosine_accuracy | cosine_map@100 | dev_average_precision |
|
679 |
+
|:------:|:----:|:-------------:|:---------------:|:--------------:|:---------------------:|
|
680 |
+
| 0 | 0 | - | 0.7661 | 0.9371 | 0.4137 |
|
681 |
+
| 0.1543 | 500 | 0.1055 | 0.7632 | 0.9620 | 0.4731 |
|
682 |
+
| 0.3086 | 1000 | 0.0677 | 0.7608 | 0.9675 | 0.4732 |
|
683 |
+
| 0.4630 | 1500 | 0.0612 | 0.7663 | 0.9710 | 0.4856 |
|
684 |
+
| 0.6173 | 2000 | 0.0584 | 0.7719 | 0.9693 | 0.4925 |
|
685 |
+
| 0.7716 | 2500 | 0.0506 | 0.7714 | 0.9709 | 0.4808 |
|
686 |
+
| 0.9259 | 3000 | 0.0488 | 0.7708 | 0.9713 | 0.4784 |
|
687 |
+
| 1.0 | 3240 | - | 0.7707 | 0.9714 | 0.4780 |
|
688 |
+
|
689 |
+
|
690 |
+
### Framework Versions
|
691 |
+
- Python: 3.11.6
|
692 |
+
- Sentence Transformers: 2.7.0.dev0
|
693 |
+
- Transformers: 4.39.3
|
694 |
+
- PyTorch: 2.1.0+cu121
|
695 |
+
- Accelerate: 0.26.1
|
696 |
+
- Datasets: 2.18.0
|
697 |
+
- Tokenizers: 0.15.2
|
698 |
+
|
699 |
+
## Citation
|
700 |
+
|
701 |
+
### BibTeX
|
702 |
+
|
703 |
+
#### Sentence Transformers
|
704 |
+
```bibtex
|
705 |
+
@inproceedings{reimers-2019-sentence-bert,
|
706 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
707 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
708 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
709 |
+
month = "11",
|
710 |
+
year = "2019",
|
711 |
+
publisher = "Association for Computational Linguistics",
|
712 |
+
url = "https://arxiv.org/abs/1908.10084",
|
713 |
+
}
|
714 |
+
```
|
715 |
+
|
716 |
+
#### MultipleNegativesRankingLoss
|
717 |
+
```bibtex
|
718 |
+
@misc{henderson2017efficient,
|
719 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
720 |
+
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},
|
721 |
+
year={2017},
|
722 |
+
eprint={1705.00652},
|
723 |
+
archivePrefix={arXiv},
|
724 |
+
primaryClass={cs.CL}
|
725 |
+
}
|
726 |
+
```
|
727 |
+
|
728 |
+
<!--
|
729 |
+
## Glossary
|
730 |
+
|
731 |
+
*Clearly define terms in order to be accessible across audiences.*
|
732 |
+
-->
|
733 |
+
|
734 |
+
<!--
|
735 |
+
## Model Card Authors
|
736 |
+
|
737 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
738 |
+
-->
|
739 |
+
|
740 |
+
<!--
|
741 |
+
## Model Card Contact
|
742 |
+
|
743 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
744 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/stsb-distilbert-base",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.39.3",
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.0.0",
|
4 |
+
"transformers": "4.7.0",
|
5 |
+
"pytorch": "1.9.0+cu102"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null
|
9 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:475763bf8eb15d61532a98f946ae6b2933a661a4bf0a2bf84299ec760659ab05
|
3 |
+
size 265462608
|
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 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"full_tokenizer_file": null,
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 128,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "DistilBertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|