Add new SentenceTransformer model.
Browse files- .gitattributes +2 -0
- 1_Pooling/config.json +10 -0
- README.md +579 -0
- config.json +26 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +64 -0
- unigram.json +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ 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
|
37 |
+
unigram.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
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 +1,579 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
3 |
+
datasets: []
|
4 |
+
language: []
|
5 |
+
library_name: sentence-transformers
|
6 |
+
metrics:
|
7 |
+
- cosine_accuracy
|
8 |
+
- cosine_accuracy_threshold
|
9 |
+
- cosine_f1
|
10 |
+
- cosine_f1_threshold
|
11 |
+
- cosine_precision
|
12 |
+
- cosine_recall
|
13 |
+
- cosine_ap
|
14 |
+
- dot_accuracy
|
15 |
+
- dot_accuracy_threshold
|
16 |
+
- dot_f1
|
17 |
+
- dot_f1_threshold
|
18 |
+
- dot_precision
|
19 |
+
- dot_recall
|
20 |
+
- dot_ap
|
21 |
+
- manhattan_accuracy
|
22 |
+
- manhattan_accuracy_threshold
|
23 |
+
- manhattan_f1
|
24 |
+
- manhattan_f1_threshold
|
25 |
+
- manhattan_precision
|
26 |
+
- manhattan_recall
|
27 |
+
- manhattan_ap
|
28 |
+
- euclidean_accuracy
|
29 |
+
- euclidean_accuracy_threshold
|
30 |
+
- euclidean_f1
|
31 |
+
- euclidean_f1_threshold
|
32 |
+
- euclidean_precision
|
33 |
+
- euclidean_recall
|
34 |
+
- euclidean_ap
|
35 |
+
- max_accuracy
|
36 |
+
- max_accuracy_threshold
|
37 |
+
- max_f1
|
38 |
+
- max_f1_threshold
|
39 |
+
- max_precision
|
40 |
+
- max_recall
|
41 |
+
- max_ap
|
42 |
+
pipeline_tag: sentence-similarity
|
43 |
+
tags:
|
44 |
+
- sentence-transformers
|
45 |
+
- sentence-similarity
|
46 |
+
- feature-extraction
|
47 |
+
- generated_from_trainer
|
48 |
+
- dataset_size:450000
|
49 |
+
- loss:ContrastiveLoss
|
50 |
+
widget:
|
51 |
+
- source_sentence: گوشی a 21 s
|
52 |
+
sentences:
|
53 |
+
- FIFA 21 اکانت قانونی FIFA 21 Standard Edition مخصوص XBOX Series S/X
|
54 |
+
- روکش صندلی چرم طرح بی ام و مناسب پژو پارس صندلی قدیم کد BMW69
|
55 |
+
- هایلایتر پودری وت اند وایلد مدل مگا گلو شماره E319B هایلایتر پودری مگا گلو وت
|
56 |
+
اند وایلد مدل E319B Blossom Glow wet n wild megaglo highlighting powder هایلایتر
|
57 |
+
پودری مگا گلو وت اند وایلد مدل E321B Precious Petals هایلایتر وت اند وایلد پودری
|
58 |
+
مگا گلو هایلایتر پودری مگا گلو شماره 319B وت اند وایلد / هایلایتر پودری مگا گلو
|
59 |
+
وت اند وایلد هایلایتر پودری مگا گلو شماره 321B وت اند وایلد هایلایتر وت اند وایلد
|
60 |
+
| هایلایتر پودری وت اند وایلید megaglot هایلایتر پودری وت اند وایلد مگا گلو
|
61 |
+
- source_sentence: استویا
|
62 |
+
sentences:
|
63 |
+
- ساعت گارمین مدل GARMIN FORERUNNER 35 GREEN Smart Watch Garmin Watch forerunner
|
64 |
+
35 green ساعت گارمين Forerunner 35 ساعت مچی هوشمند گارمین forerunner 35 green
|
65 |
+
- برگ استویا
|
66 |
+
- تاچ و ال سی دی شیائومی ردمی مدل نوت 8 پرو تاچ و ال سی دی شیائومی REDMI NOTE 8
|
67 |
+
PRO تاچ و ال سی دی گوشی شائومی ردمی نوت 8 پرو LCD XIAOMI REDMI NOTE 8 PRO
|
68 |
+
- source_sentence: سنباده برقی
|
69 |
+
sentences:
|
70 |
+
- گوشت کوب برقی سه کاره میگل مدل GHB 801 سفید گوشتکوب برقی چند کاره میگل غذاساز
|
71 |
+
دستی GHB 801 میگل Migel GHB 801 Food Processor گوشت کوب برقی GHB 801 سفيد ميگل
|
72 |
+
غذاساز دستی میگل مشکی مدل GHB 801 گوشتکوب برقی میگل GHB 801 غذاساز میگل مدل GHB
|
73 |
+
801 (سفید) غذاساز دستی میگل مدل GHB 801 گوشت کوب برقی سه کاره میگل مدل GHB 801
|
74 |
+
مشکی غذاساز میگل مدل GHB 801 غذاساز میگل مدل GHB 801 غذاساز دستی میگل مدل GHB801
|
75 |
+
W غذاساز دستی میگل سفید مدل GHB 801 گوشت کوب برقی میگل مدل GHB 801 غذاساز میگل
|
76 |
+
مدل GHB 801 ا Migel GHB 801 Food Processor گوشت کوب برقی میگل GHB801
|
77 |
+
- کلگی شارژر دو پورت تسکو با کابل میکرو TTC 57 کلگی شارژر تسکو مدل TSCO – TTC57
|
78 |
+
به همراه کابل MICRO USB شارژر دیواری تسکو مدل TTC 57 با کابل micro-USB شارژر دیواری
|
79 |
+
دو پورت تسکو مدل TTC 57 شارژر دیواری TTC 57 تسکو شارژر دیواری تسکو مدل ttc 57
|
80 |
+
گلد و نقره ای شارژر دیواری تسکو مدل TTC57 شارژر 2 پورت تسکو TTC 57 tsco ttc 57
|
81 |
+
wall charger شارژر دیواری تسکو مدل TTC 57 به همراه کابل microUSB شارژر دیواری
|
82 |
+
تسکو TSCO TTC 57 به همراه کابل MicroUSB شارژر دیواری تسکو مدل WALL CHARGER TTC-57
|
83 |
+
شارژر دیواری TTC 57 به همراه کابل تبدیل microUSB Tsco TTC 57 Wall charger With
|
84 |
+
MicroUSB Conversion Cable شارژر دیواری تسکو TTC 57 شارژر دیواری تسکو TSCO TTC
|
85 |
+
57 + کابل شارژر دیواری تسکو مدل TTC 57 با کابل MicroUSB شارژر دیواری TTC 57 TSCO
|
86 |
+
TTC 57 Wall Charger with microUSB Cable شارژر دیواری تسکو(TSCO TTC57 ) شارژر دیواری
|
87 |
+
تسکو مدل TTC 57 شارژر دیواری به همراه کابل تبدیل microUSB تسکو مدل TSCO TTC 57
|
88 |
+
+ دو پورت USB TSCO TTC 57 2.4A Wall Charger TSCO TTC 57 Wall Charger شارژر دیواری
|
89 |
+
تسکو مدلTTC57 به همراه کابل شارژ شارژر دیواری TSCO TTC57 + کابل میکرو یو اس بی
|
90 |
+
شارژر دیواری تسکو مدل TTC 57 به همراه با کابل microUSB Tsco TTC57 CHarger Fast
|
91 |
+
with Micro Cable شارژر دیواری TSCO TTC57 کابل میکرو یو اس بی گارانتی یکساله شارژر
|
92 |
+
TSCO مدل TTC 57 به همراه کابل MICRO شارژر دیواری سه پورت تسکو مدل TTC57 شارژر
|
93 |
+
دیواری تسکو مدل TTC 57 به همراه کابل شارژ microUSB شارژر دیواری تسکو مدل TSCO
|
94 |
+
TTC 57 به همراه کابل تبدیل microUSB WALL CHARGER TTC 57 شارژر دیواری تسکو مدل
|
95 |
+
TTC 57 به همراه کابل تبدیل microUSB TSCO TTC 57 شارژر دیواری تسکوttc 57
|
96 |
+
- سنباده برقی ایکس کورت XSF02-180S
|
97 |
+
- source_sentence: میز تنیس
|
98 |
+
sentences:
|
99 |
+
- کاندوم شیت کلوپلاست سایز ۳۰ میلیمتر کاندوم شیت کانوین کلوپلاست کاندوم شیت Espi
|
100 |
+
سایز ۳۰ میلیمتر کاندوم شیت کلوپلاست مدل کانوین کاندوم شیت کلوپلاست کاندوم شیت
|
101 |
+
کلوپلاست سایز 30 کاندوم شیت کولوپلاست 30 میلی متر Coloplast Freedom Clear کاندوم
|
102 |
+
شیت سایز 25 میلی متر کلوپلاست coloplast ساخت دانمارک کاندوم شیت لاتکس کلوپلاست
|
103 |
+
کاندوم شیت دانمارکی کاندوم شیت کلوپلاست - coloplast کاندوم شیت سایز 30 میلی متر
|
104 |
+
کلوپلاست coloplast ساخت دانمارک کاندوم شیت کاندوم شیت کلوپلاست در سایزبندی کاندوم
|
105 |
+
شیت 30میلی لیتر کاندوم شیت کلوپلاست coloplast دانمارکی
|
106 |
+
- کاور گوشی سامسونگ A70 - A70S سه بعدی کد5
|
107 |
+
- میز تنیس روی میز مدل Horse TT11
|
108 |
+
- source_sentence: 'هندزفری بلوتوث جبرا '
|
109 |
+
sentences:
|
110 |
+
- آرمیچر دریل رونیکس 2210
|
111 |
+
- هدست بلوتوث جبرا Mini هندزفری بلوتوث جبرا Jabra Mini Bluetooth Handsfree هدست
|
112 |
+
بلوتوث جبرا مدل Mini هندزفری بلوتوث جبرا MINI
|
113 |
+
- گاز پیک نیک 5 کیلویی شیدا گاز
|
114 |
+
model-index:
|
115 |
+
- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
116 |
+
results:
|
117 |
+
- task:
|
118 |
+
type: binary-classification
|
119 |
+
name: Binary Classification
|
120 |
+
dataset:
|
121 |
+
name: Unknown
|
122 |
+
type: unknown
|
123 |
+
metrics:
|
124 |
+
- type: cosine_accuracy
|
125 |
+
value: 0.85498
|
126 |
+
name: Cosine Accuracy
|
127 |
+
- type: cosine_accuracy_threshold
|
128 |
+
value: 0.7729779481887817
|
129 |
+
name: Cosine Accuracy Threshold
|
130 |
+
- type: cosine_f1
|
131 |
+
value: 0.8740799339616153
|
132 |
+
name: Cosine F1
|
133 |
+
- type: cosine_f1_threshold
|
134 |
+
value: 0.7386565208435059
|
135 |
+
name: Cosine F1 Threshold
|
136 |
+
- type: cosine_precision
|
137 |
+
value: 0.8376623376623377
|
138 |
+
name: Cosine Precision
|
139 |
+
- type: cosine_recall
|
140 |
+
value: 0.9138079827400216
|
141 |
+
name: Cosine Recall
|
142 |
+
- type: cosine_ap
|
143 |
+
value: 0.9043744924756869
|
144 |
+
name: Cosine Ap
|
145 |
+
- type: dot_accuracy
|
146 |
+
value: 0.81168
|
147 |
+
name: Dot Accuracy
|
148 |
+
- type: dot_accuracy_threshold
|
149 |
+
value: 18.684463500976562
|
150 |
+
name: Dot Accuracy Threshold
|
151 |
+
- type: dot_f1
|
152 |
+
value: 0.8382417731385773
|
153 |
+
name: Dot F1
|
154 |
+
- type: dot_f1_threshold
|
155 |
+
value: 18.00467300415039
|
156 |
+
name: Dot F1 Threshold
|
157 |
+
- type: dot_precision
|
158 |
+
value: 0.7926547878477118
|
159 |
+
name: Dot Precision
|
160 |
+
- type: dot_recall
|
161 |
+
value: 0.8893923049262855
|
162 |
+
name: Dot Recall
|
163 |
+
- type: dot_ap
|
164 |
+
value: 0.8808088425591442
|
165 |
+
name: Dot Ap
|
166 |
+
- type: manhattan_accuracy
|
167 |
+
value: 0.8519
|
168 |
+
name: Manhattan Accuracy
|
169 |
+
- type: manhattan_accuracy_threshold
|
170 |
+
value: 54.21998596191406
|
171 |
+
name: Manhattan Accuracy Threshold
|
172 |
+
- type: manhattan_f1
|
173 |
+
value: 0.8715498573540026
|
174 |
+
name: Manhattan F1
|
175 |
+
- type: manhattan_f1_threshold
|
176 |
+
value: 57.27758026123047
|
177 |
+
name: Manhattan F1 Threshold
|
178 |
+
- type: manhattan_precision
|
179 |
+
value: 0.8347379510139584
|
180 |
+
name: Manhattan Precision
|
181 |
+
- type: manhattan_recall
|
182 |
+
value: 0.9117583603020496
|
183 |
+
name: Manhattan Recall
|
184 |
+
- type: manhattan_ap
|
185 |
+
value: 0.8994757702061444
|
186 |
+
name: Manhattan Ap
|
187 |
+
- type: euclidean_accuracy
|
188 |
+
value: 0.85192
|
189 |
+
name: Euclidean Accuracy
|
190 |
+
- type: euclidean_accuracy_threshold
|
191 |
+
value: 3.4671199321746826
|
192 |
+
name: Euclidean Accuracy Threshold
|
193 |
+
- type: euclidean_f1
|
194 |
+
value: 0.8717798493960334
|
195 |
+
name: Euclidean F1
|
196 |
+
- type: euclidean_f1_threshold
|
197 |
+
value: 3.664275646209717
|
198 |
+
name: Euclidean F1 Threshold
|
199 |
+
- type: euclidean_precision
|
200 |
+
value: 0.8369784601131589
|
201 |
+
name: Euclidean Precision
|
202 |
+
- type: euclidean_recall
|
203 |
+
value: 0.9096008629989213
|
204 |
+
name: Euclidean Recall
|
205 |
+
- type: euclidean_ap
|
206 |
+
value: 0.8996992828192123
|
207 |
+
name: Euclidean Ap
|
208 |
+
- type: max_accuracy
|
209 |
+
value: 0.85498
|
210 |
+
name: Max Accuracy
|
211 |
+
- type: max_accuracy_threshold
|
212 |
+
value: 54.21998596191406
|
213 |
+
name: Max Accuracy Threshold
|
214 |
+
- type: max_f1
|
215 |
+
value: 0.8740799339616153
|
216 |
+
name: Max F1
|
217 |
+
- type: max_f1_threshold
|
218 |
+
value: 57.27758026123047
|
219 |
+
name: Max F1 Threshold
|
220 |
+
- type: max_precision
|
221 |
+
value: 0.8376623376623377
|
222 |
+
name: Max Precision
|
223 |
+
- type: max_recall
|
224 |
+
value: 0.9138079827400216
|
225 |
+
name: Max Recall
|
226 |
+
- type: max_ap
|
227 |
+
value: 0.9043744924756869
|
228 |
+
name: Max Ap
|
229 |
+
---
|
230 |
+
|
231 |
+
# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
|
232 |
+
|
233 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
234 |
+
|
235 |
+
## Model Details
|
236 |
+
|
237 |
+
### Model Description
|
238 |
+
- **Model Type:** Sentence Transformer
|
239 |
+
- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
|
240 |
+
- **Maximum Sequence Length:** 128 tokens
|
241 |
+
- **Output Dimensionality:** 384 tokens
|
242 |
+
- **Similarity Function:** Cosine Similarity
|
243 |
+
<!-- - **Training Dataset:** Unknown -->
|
244 |
+
<!-- - **Language:** Unknown -->
|
245 |
+
<!-- - **License:** Unknown -->
|
246 |
+
|
247 |
+
### Model Sources
|
248 |
+
|
249 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
250 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
251 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
252 |
+
|
253 |
+
### Full Model Architecture
|
254 |
+
|
255 |
+
```
|
256 |
+
SentenceTransformer(
|
257 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
258 |
+
(1): Pooling({'word_embedding_dimension': 384, '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})
|
259 |
+
)
|
260 |
+
```
|
261 |
+
|
262 |
+
## Usage
|
263 |
+
|
264 |
+
### Direct Usage (Sentence Transformers)
|
265 |
+
|
266 |
+
First install the Sentence Transformers library:
|
267 |
+
|
268 |
+
```bash
|
269 |
+
pip install -U sentence-transformers
|
270 |
+
```
|
271 |
+
|
272 |
+
Then you can load this model and run inference.
|
273 |
+
```python
|
274 |
+
from sentence_transformers import SentenceTransformer
|
275 |
+
|
276 |
+
# Download from the 🤗 Hub
|
277 |
+
model = SentenceTransformer("DashReza7/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2_FINETUNED_on_torob_data_v2_3")
|
278 |
+
# Run inference
|
279 |
+
sentences = [
|
280 |
+
'هندزفری بلوتوث جبرا ',
|
281 |
+
'هدست بلوتوث جبرا Mini هندزفری بلوتوث جبرا Jabra Mini Bluetooth Handsfree هدست بلوتوث جبرا مدل Mini هندزفری بلوتوث جبرا MINI',
|
282 |
+
'گاز پیک نیک 5 کیلویی شیدا گاز',
|
283 |
+
]
|
284 |
+
embeddings = model.encode(sentences)
|
285 |
+
print(embeddings.shape)
|
286 |
+
# [3, 384]
|
287 |
+
|
288 |
+
# Get the similarity scores for the embeddings
|
289 |
+
similarities = model.similarity(embeddings, embeddings)
|
290 |
+
print(similarities.shape)
|
291 |
+
# [3, 3]
|
292 |
+
```
|
293 |
+
|
294 |
+
<!--
|
295 |
+
### Direct Usage (Transformers)
|
296 |
+
|
297 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
298 |
+
|
299 |
+
</details>
|
300 |
+
-->
|
301 |
+
|
302 |
+
<!--
|
303 |
+
### Downstream Usage (Sentence Transformers)
|
304 |
+
|
305 |
+
You can finetune this model on your own dataset.
|
306 |
+
|
307 |
+
<details><summary>Click to expand</summary>
|
308 |
+
|
309 |
+
</details>
|
310 |
+
-->
|
311 |
+
|
312 |
+
<!--
|
313 |
+
### Out-of-Scope Use
|
314 |
+
|
315 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
316 |
+
-->
|
317 |
+
|
318 |
+
## Evaluation
|
319 |
+
|
320 |
+
### Metrics
|
321 |
+
|
322 |
+
#### Binary Classification
|
323 |
+
|
324 |
+
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
|
325 |
+
|
326 |
+
| Metric | Value |
|
327 |
+
|:-----------------------------|:-----------|
|
328 |
+
| cosine_accuracy | 0.855 |
|
329 |
+
| cosine_accuracy_threshold | 0.773 |
|
330 |
+
| cosine_f1 | 0.8741 |
|
331 |
+
| cosine_f1_threshold | 0.7387 |
|
332 |
+
| cosine_precision | 0.8377 |
|
333 |
+
| cosine_recall | 0.9138 |
|
334 |
+
| cosine_ap | 0.9044 |
|
335 |
+
| dot_accuracy | 0.8117 |
|
336 |
+
| dot_accuracy_threshold | 18.6845 |
|
337 |
+
| dot_f1 | 0.8382 |
|
338 |
+
| dot_f1_threshold | 18.0047 |
|
339 |
+
| dot_precision | 0.7927 |
|
340 |
+
| dot_recall | 0.8894 |
|
341 |
+
| dot_ap | 0.8808 |
|
342 |
+
| manhattan_accuracy | 0.8519 |
|
343 |
+
| manhattan_accuracy_threshold | 54.22 |
|
344 |
+
| manhattan_f1 | 0.8715 |
|
345 |
+
| manhattan_f1_threshold | 57.2776 |
|
346 |
+
| manhattan_precision | 0.8347 |
|
347 |
+
| manhattan_recall | 0.9118 |
|
348 |
+
| manhattan_ap | 0.8995 |
|
349 |
+
| euclidean_accuracy | 0.8519 |
|
350 |
+
| euclidean_accuracy_threshold | 3.4671 |
|
351 |
+
| euclidean_f1 | 0.8718 |
|
352 |
+
| euclidean_f1_threshold | 3.6643 |
|
353 |
+
| euclidean_precision | 0.837 |
|
354 |
+
| euclidean_recall | 0.9096 |
|
355 |
+
| euclidean_ap | 0.8997 |
|
356 |
+
| max_accuracy | 0.855 |
|
357 |
+
| max_accuracy_threshold | 54.22 |
|
358 |
+
| max_f1 | 0.8741 |
|
359 |
+
| max_f1_threshold | 57.2776 |
|
360 |
+
| max_precision | 0.8377 |
|
361 |
+
| max_recall | 0.9138 |
|
362 |
+
| **max_ap** | **0.9044** |
|
363 |
+
|
364 |
+
<!--
|
365 |
+
## Bias, Risks and Limitations
|
366 |
+
|
367 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
368 |
+
-->
|
369 |
+
|
370 |
+
<!--
|
371 |
+
### Recommendations
|
372 |
+
|
373 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
374 |
+
-->
|
375 |
+
|
376 |
+
## Training Details
|
377 |
+
|
378 |
+
### Training Hyperparameters
|
379 |
+
#### Non-Default Hyperparameters
|
380 |
+
|
381 |
+
- `eval_strategy`: steps
|
382 |
+
- `per_device_train_batch_size`: 64
|
383 |
+
- `per_device_eval_batch_size`: 64
|
384 |
+
- `learning_rate`: 2e-05
|
385 |
+
- `num_train_epochs`: 1
|
386 |
+
- `warmup_ratio`: 0.1
|
387 |
+
- `fp16`: True
|
388 |
+
|
389 |
+
#### All Hyperparameters
|
390 |
+
<details><summary>Click to expand</summary>
|
391 |
+
|
392 |
+
- `overwrite_output_dir`: False
|
393 |
+
- `do_predict`: False
|
394 |
+
- `eval_strategy`: steps
|
395 |
+
- `prediction_loss_only`: True
|
396 |
+
- `per_device_train_batch_size`: 64
|
397 |
+
- `per_device_eval_batch_size`: 64
|
398 |
+
- `per_gpu_train_batch_size`: None
|
399 |
+
- `per_gpu_eval_batch_size`: None
|
400 |
+
- `gradient_accumulation_steps`: 1
|
401 |
+
- `eval_accumulation_steps`: None
|
402 |
+
- `learning_rate`: 2e-05
|
403 |
+
- `weight_decay`: 0.0
|
404 |
+
- `adam_beta1`: 0.9
|
405 |
+
- `adam_beta2`: 0.999
|
406 |
+
- `adam_epsilon`: 1e-08
|
407 |
+
- `max_grad_norm`: 1.0
|
408 |
+
- `num_train_epochs`: 1
|
409 |
+
- `max_steps`: -1
|
410 |
+
- `lr_scheduler_type`: linear
|
411 |
+
- `lr_scheduler_kwargs`: {}
|
412 |
+
- `warmup_ratio`: 0.1
|
413 |
+
- `warmup_steps`: 0
|
414 |
+
- `log_level`: passive
|
415 |
+
- `log_level_replica`: warning
|
416 |
+
- `log_on_each_node`: True
|
417 |
+
- `logging_nan_inf_filter`: True
|
418 |
+
- `save_safetensors`: True
|
419 |
+
- `save_on_each_node`: False
|
420 |
+
- `save_only_model`: False
|
421 |
+
- `restore_callback_states_from_checkpoint`: False
|
422 |
+
- `no_cuda`: False
|
423 |
+
- `use_cpu`: False
|
424 |
+
- `use_mps_device`: False
|
425 |
+
- `seed`: 42
|
426 |
+
- `data_seed`: None
|
427 |
+
- `jit_mode_eval`: False
|
428 |
+
- `use_ipex`: False
|
429 |
+
- `bf16`: False
|
430 |
+
- `fp16`: True
|
431 |
+
- `fp16_opt_level`: O1
|
432 |
+
- `half_precision_backend`: auto
|
433 |
+
- `bf16_full_eval`: False
|
434 |
+
- `fp16_full_eval`: False
|
435 |
+
- `tf32`: None
|
436 |
+
- `local_rank`: 0
|
437 |
+
- `ddp_backend`: None
|
438 |
+
- `tpu_num_cores`: None
|
439 |
+
- `tpu_metrics_debug`: False
|
440 |
+
- `debug`: []
|
441 |
+
- `dataloader_drop_last`: False
|
442 |
+
- `dataloader_num_workers`: 0
|
443 |
+
- `dataloader_prefetch_factor`: None
|
444 |
+
- `past_index`: -1
|
445 |
+
- `disable_tqdm`: False
|
446 |
+
- `remove_unused_columns`: True
|
447 |
+
- `label_names`: None
|
448 |
+
- `load_best_model_at_end`: False
|
449 |
+
- `ignore_data_skip`: False
|
450 |
+
- `fsdp`: []
|
451 |
+
- `fsdp_min_num_params`: 0
|
452 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
453 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
454 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
455 |
+
- `deepspeed`: None
|
456 |
+
- `label_smoothing_factor`: 0.0
|
457 |
+
- `optim`: adamw_torch
|
458 |
+
- `optim_args`: None
|
459 |
+
- `adafactor`: False
|
460 |
+
- `group_by_length`: False
|
461 |
+
- `length_column_name`: length
|
462 |
+
- `ddp_find_unused_parameters`: None
|
463 |
+
- `ddp_bucket_cap_mb`: None
|
464 |
+
- `ddp_broadcast_buffers`: False
|
465 |
+
- `dataloader_pin_memory`: True
|
466 |
+
- `dataloader_persistent_workers`: False
|
467 |
+
- `skip_memory_metrics`: True
|
468 |
+
- `use_legacy_prediction_loop`: False
|
469 |
+
- `push_to_hub`: False
|
470 |
+
- `resume_from_checkpoint`: None
|
471 |
+
- `hub_model_id`: None
|
472 |
+
- `hub_strategy`: every_save
|
473 |
+
- `hub_private_repo`: False
|
474 |
+
- `hub_always_push`: False
|
475 |
+
- `gradient_checkpointing`: False
|
476 |
+
- `gradient_checkpointing_kwargs`: None
|
477 |
+
- `include_inputs_for_metrics`: False
|
478 |
+
- `eval_do_concat_batches`: True
|
479 |
+
- `fp16_backend`: auto
|
480 |
+
- `push_to_hub_model_id`: None
|
481 |
+
- `push_to_hub_organization`: None
|
482 |
+
- `mp_parameters`:
|
483 |
+
- `auto_find_batch_size`: False
|
484 |
+
- `full_determinism`: False
|
485 |
+
- `torchdynamo`: None
|
486 |
+
- `ray_scope`: last
|
487 |
+
- `ddp_timeout`: 1800
|
488 |
+
- `torch_compile`: False
|
489 |
+
- `torch_compile_backend`: None
|
490 |
+
- `torch_compile_mode`: None
|
491 |
+
- `dispatch_batches`: None
|
492 |
+
- `split_batches`: None
|
493 |
+
- `include_tokens_per_second`: False
|
494 |
+
- `include_num_input_tokens_seen`: False
|
495 |
+
- `neftune_noise_alpha`: None
|
496 |
+
- `optim_target_modules`: None
|
497 |
+
- `batch_eval_metrics`: False
|
498 |
+
- `eval_on_start`: False
|
499 |
+
- `batch_sampler`: batch_sampler
|
500 |
+
- `multi_dataset_batch_sampler`: proportional
|
501 |
+
|
502 |
+
</details>
|
503 |
+
|
504 |
+
### Training Logs
|
505 |
+
| Epoch | Step | Training Loss | loss | max_ap |
|
506 |
+
|:------:|:----:|:-------------:|:------:|:------:|
|
507 |
+
| 0.0711 | 500 | 0.0318 | - | - |
|
508 |
+
| 0.1422 | 1000 | 0.0201 | - | - |
|
509 |
+
| 0.2133 | 1500 | 0.0183 | - | - |
|
510 |
+
| 0.2844 | 2000 | 0.0171 | 0.0166 | 0.8756 |
|
511 |
+
| 0.3555 | 2500 | 0.0164 | - | - |
|
512 |
+
| 0.4266 | 3000 | 0.0161 | - | - |
|
513 |
+
| 0.4977 | 3500 | 0.0155 | - | - |
|
514 |
+
| 0.5688 | 4000 | 0.0153 | 0.0147 | 0.8955 |
|
515 |
+
| 0.6399 | 4500 | 0.015 | - | - |
|
516 |
+
| 0.7110 | 5000 | 0.0145 | - | - |
|
517 |
+
| 0.7821 | 5500 | 0.0144 | - | - |
|
518 |
+
| 0.8532 | 6000 | 0.0143 | 0.0138 | 0.9044 |
|
519 |
+
| 0.9243 | 6500 | 0.0141 | - | - |
|
520 |
+
| 0.9954 | 7000 | 0.0139 | - | - |
|
521 |
+
|
522 |
+
|
523 |
+
### Framework Versions
|
524 |
+
- Python: 3.10.12
|
525 |
+
- Sentence Transformers: 3.0.1
|
526 |
+
- Transformers: 4.42.4
|
527 |
+
- PyTorch: 2.4.0+cu121
|
528 |
+
- Accelerate: 0.32.1
|
529 |
+
- Datasets: 2.21.0
|
530 |
+
- Tokenizers: 0.19.1
|
531 |
+
|
532 |
+
## Citation
|
533 |
+
|
534 |
+
### BibTeX
|
535 |
+
|
536 |
+
#### Sentence Transformers
|
537 |
+
```bibtex
|
538 |
+
@inproceedings{reimers-2019-sentence-bert,
|
539 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
540 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
541 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
542 |
+
month = "11",
|
543 |
+
year = "2019",
|
544 |
+
publisher = "Association for Computational Linguistics",
|
545 |
+
url = "https://arxiv.org/abs/1908.10084",
|
546 |
+
}
|
547 |
+
```
|
548 |
+
|
549 |
+
#### ContrastiveLoss
|
550 |
+
```bibtex
|
551 |
+
@inproceedings{hadsell2006dimensionality,
|
552 |
+
author={Hadsell, R. and Chopra, S. and LeCun, Y.},
|
553 |
+
booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
|
554 |
+
title={Dimensionality Reduction by Learning an Invariant Mapping},
|
555 |
+
year={2006},
|
556 |
+
volume={2},
|
557 |
+
number={},
|
558 |
+
pages={1735-1742},
|
559 |
+
doi={10.1109/CVPR.2006.100}
|
560 |
+
}
|
561 |
+
```
|
562 |
+
|
563 |
+
<!--
|
564 |
+
## Glossary
|
565 |
+
|
566 |
+
*Clearly define terms in order to be accessible across audiences.*
|
567 |
+
-->
|
568 |
+
|
569 |
+
<!--
|
570 |
+
## Model Card Authors
|
571 |
+
|
572 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
573 |
+
-->
|
574 |
+
|
575 |
+
<!--
|
576 |
+
## Model Card Contact
|
577 |
+
|
578 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
579 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.42.4",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 250037
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.42.4",
|
5 |
+
"pytorch": "2.4.0+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": "cosine"
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2021d264c74eceed25900033dc29ea092efc945caa658a190a4880a33915fdfd
|
3 |
+
size 470637416
|
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 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"do_lower_case": true,
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
50 |
+
"max_length": 128,
|
51 |
+
"model_max_length": 128,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "</s>",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "<unk>"
|
64 |
+
}
|
unigram.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
|
3 |
+
size 14763260
|