Upload 13 files
Browse files- 1_Pooling/config.json +10 -0
- 2_Dense/config.json +1 -0
- 2_Dense/model.safetensors +3 -0
- README.md +1007 -0
- config.json +24 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +20 -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 |
+
}
|
2_Dense/config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"in_features": 768, "out_features": 512, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}
|
2_Dense/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:986dd5160d6aa2e107d67874926028f49d5cf8a1f67874e2b2171d11b746384b
|
3 |
+
size 1575072
|
README.md
ADDED
@@ -0,0 +1,1007 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: sentence-transformers/distiluse-base-multilingual-cased-v1
|
3 |
+
library_name: sentence-transformers
|
4 |
+
pipeline_tag: sentence-similarity
|
5 |
+
tags:
|
6 |
+
- sentence-transformers
|
7 |
+
- sentence-similarity
|
8 |
+
- feature-extraction
|
9 |
+
- generated_from_trainer
|
10 |
+
- dataset_size:5108
|
11 |
+
- loss:CosineSimilarityLoss
|
12 |
+
widget:
|
13 |
+
- source_sentence: 'EDUCATION
|
14 |
+
|
15 |
+
University of Roseton
|
16 |
+
|
17 |
+
Bachelor of Science in Computer Science | Graduated: 2016
|
18 |
+
|
19 |
+
|
20 |
+
Graduated Cum Laude with GPA: 3.9
|
21 |
+
|
22 |
+
Class Salutatorian
|
23 |
+
|
24 |
+
Computer Club President
|
25 |
+
|
26 |
+
Student Council Member
|
27 |
+
|
28 |
+
Winslough High School
|
29 |
+
|
30 |
+
High School Diploma | 2008 - 2012
|
31 |
+
|
32 |
+
|
33 |
+
Computer Club Vice President
|
34 |
+
|
35 |
+
Winslough Warriors Basketball Team Member
|
36 |
+
|
37 |
+
AP Scholar Award
|
38 |
+
|
39 |
+
National Honor Society Member
|
40 |
+
|
41 |
+
SKILLS AND ABILITIES
|
42 |
+
|
43 |
+
Programming Languages: Proficient in multiple programming languages
|
44 |
+
|
45 |
+
Problem Solving: Strong problem-solving and critical thinking skills
|
46 |
+
|
47 |
+
Expertise: Expertise in software systems and computer operating structures
|
48 |
+
|
49 |
+
Communication: Effective communication and teamwork skills'
|
50 |
+
sentences:
|
51 |
+
- 'Eduvator
|
52 |
+
|
53 |
+
Skills and expertise:
|
54 |
+
|
55 |
+
Degree:
|
56 |
+
|
57 |
+
|
58 |
+
University graduate, major in Computer Science or Information Technology.
|
59 |
+
|
60 |
+
Priority is given to candidates who graduated from universities such as University
|
61 |
+
of Natural Sciences, University of Information Technology - VNU-HCM, University
|
62 |
+
of Technology, etc.
|
63 |
+
|
64 |
+
Experience:
|
65 |
+
|
66 |
+
|
67 |
+
At least 2 years of experience developing software for enterprise solutions, especially
|
68 |
+
using NodeJS.
|
69 |
+
|
70 |
+
Professional skills:
|
71 |
+
|
72 |
+
|
73 |
+
Experience with NodeJS and familiarity with ExpressJS (priority is given to those
|
74 |
+
with experience with Apollo Server).
|
75 |
+
|
76 |
+
Good knowledge of SQL and NoSQL databases, ability to write complex queries (priority
|
77 |
+
is given to those who know how to use MongoDB).
|
78 |
+
|
79 |
+
Proficient or experienced with Docker.
|
80 |
+
|
81 |
+
Good problem-solving skills, proficient in handling and manipulating strings/characters
|
82 |
+
and arrays.
|
83 |
+
|
84 |
+
Strong knowledge of the git source code management system.
|
85 |
+
|
86 |
+
Learning ability:
|
87 |
+
|
88 |
+
|
89 |
+
Ability to learn new technologies quickly.'
|
90 |
+
- 'Skills & Expertise:
|
91 |
+
|
92 |
+
|
93 |
+
Requirements:
|
94 |
+
|
95 |
+
|
96 |
+
Education:
|
97 |
+
|
98 |
+
|
99 |
+
Graduated from a regular university (with a degree), priority is given to majors:
|
100 |
+
Information Technology, Telecommunications, Information Systems, Computer Science,
|
101 |
+
etc.
|
102 |
+
|
103 |
+
Experience:
|
104 |
+
|
105 |
+
|
106 |
+
At least 3 years of experience as a Java programmer.
|
107 |
+
|
108 |
+
Professional knowledge:
|
109 |
+
|
110 |
+
|
111 |
+
Strong knowledge of Object Oriented Programming (OOP), Web Development, Database
|
112 |
+
Management System (DBMS), ORM, Design Pattern.
|
113 |
+
|
114 |
+
Proficient in Restful API, HTML, CSS, JavaScript (Jquery, ...), Bootstrap, JSON,
|
115 |
+
XML.
|
116 |
+
|
117 |
+
Proficient in PostgreSQL (or MySQL, MSSQL, Oracle), priority is given to candidates
|
118 |
+
with the ability to design DB and optimize system performance.
|
119 |
+
|
120 |
+
Understand and apply MVC model.
|
121 |
+
|
122 |
+
Proficient in Git.'
|
123 |
+
- 'Skills & Expertise:
|
124 |
+
|
125 |
+
|
126 |
+
Requirements:
|
127 |
+
|
128 |
+
|
129 |
+
Education:
|
130 |
+
|
131 |
+
|
132 |
+
University degree or higher in Information Technology or Electronics - Telecommunications.
|
133 |
+
|
134 |
+
Professional certificates:
|
135 |
+
|
136 |
+
|
137 |
+
CCNA or CCNP certificate.
|
138 |
+
|
139 |
+
Priority is given to candidates with certificates such as: MCSA, Azure, VMware,
|
140 |
+
CEH, OSCE, OSCP, COMPTIA Pentest+ or equivalent.
|
141 |
+
|
142 |
+
Foreign languages:
|
143 |
+
|
144 |
+
|
145 |
+
English equivalent to Toeic 400 points or higher.
|
146 |
+
|
147 |
+
Office skills:
|
148 |
+
|
149 |
+
|
150 |
+
Proficient in MS Office, Visio.'
|
151 |
+
- source_sentence: 'EDUCATION Bachelor of Technology Really Great University Really
|
152 |
+
Great Company 2016 - Present Responsible for database administration and website
|
153 |
+
design.
|
154 |
+
|
155 |
+
Developed the logic for a streamlined ad-serving platform that scales effectively
|
156 |
+
for educational institutions and online classroom management.
|
157 |
+
|
158 |
+
|
159 |
+
SKILLS Web Design Design Thinking Wireframe Creation Front-End Coding Back-End
|
160 |
+
Technology Problem Solving Computer Literacy Project Management Tools Strong Communication
|
161 |
+
Skills'
|
162 |
+
sentences:
|
163 |
+
- 'ABBANK
|
164 |
+
|
165 |
+
|
166 |
+
Skill requirements:
|
167 |
+
|
168 |
+
|
169 |
+
University or master''s degree in: Information Security, Information Technology,
|
170 |
+
Software Engineering, Computer Science.
|
171 |
+
|
172 |
+
At least 5 years of experience in the field of information security.
|
173 |
+
|
174 |
+
At least 2 years of experience in the field of DevOps / DevSecOps.
|
175 |
+
|
176 |
+
At least 2 years of experience working with Cloud platforms (AWS, Azure, GCP).
|
177 |
+
|
178 |
+
Deep knowledge of IT in the field of DevSecOps, solutions in On-premise, Cloud
|
179 |
+
native and Hybrid environments (Container, Kubernetes, Docker, Git, CI/CD Jenkins,
|
180 |
+
GitLab CI, GitHub...).
|
181 |
+
|
182 |
+
Skills related to exploiting vulnerabilities, security weaknesses.
|
183 |
+
|
184 |
+
Understanding of OWASP, MITRE Attack.
|
185 |
+
|
186 |
+
Deep knowledge of CI/CD pipeline model, deploying integrated security automation
|
187 |
+
solutions in the development process.
|
188 |
+
|
189 |
+
Develop documentation and standard processes to deploy and operate security solutions
|
190 |
+
on Cloud/DevSecOps in a stable and secure manner.
|
191 |
+
|
192 |
+
Have certificates such as CEH, OSCP, CCSP... or equivalent; having a certificate
|
193 |
+
in GCP Cloud Security is an advantage.
|
194 |
+
|
195 |
+
Education requirements:
|
196 |
+
|
197 |
+
|
198 |
+
Graduate from university or master''s degree in related field.
|
199 |
+
|
200 |
+
Language requirements:
|
201 |
+
|
202 |
+
|
203 |
+
Being able to communicate in English is an advantage.'
|
204 |
+
- 'FPT
|
205 |
+
|
206 |
+
Skills and qualifications required:
|
207 |
+
|
208 |
+
|
209 |
+
General standards:
|
210 |
+
|
211 |
+
|
212 |
+
Be a Vietnamese citizen, have a permanent residence in Vietnam.
|
213 |
+
|
214 |
+
Be under 35 years old.
|
215 |
+
|
216 |
+
Be in good health to perform the job.
|
217 |
+
|
218 |
+
Have good moral qualities, no criminal record, no detention, no prison sentence,
|
219 |
+
suspended sentence, non-custodial reform, no local education status, medical treatment,
|
220 |
+
drug rehabilitation, etc.
|
221 |
+
|
222 |
+
Specific standards:
|
223 |
+
|
224 |
+
|
225 |
+
Professional qualifications:
|
226 |
+
|
227 |
+
|
228 |
+
Graduate from university or higher, regular system (including second university,
|
229 |
+
not including university transfer) at domestic universities or graduate from university
|
230 |
+
or higher at foreign universities, affiliated universities.
|
231 |
+
|
232 |
+
Major: Graduated from majors such as Information Technology, Information Security,
|
233 |
+
Telecommunications Electronics, Information Electronics, Mathematics - Informatics
|
234 |
+
or equivalent majors.
|
235 |
+
|
236 |
+
Foreign Language:
|
237 |
+
|
238 |
+
|
239 |
+
Having one of the following certificates: TOEIC 600/990, TOEFL PBT/IPT 500/677,
|
240 |
+
TOEFL CBT 173/300, TOEFL iBT 61/120, IELTS 5.5/9.0, Cambridge Exam First (FCE),
|
241 |
+
B2 European Framework, 4/6 6-level Foreign Language Proficiency Framework for
|
242 |
+
Vietnam. Accepting additional English certificates within 24 months from the date
|
243 |
+
of recruitment.
|
244 |
+
|
245 |
+
Knowledge, skills and experience:
|
246 |
+
|
247 |
+
|
248 |
+
Experience in managing server systems and storage systems is an advantage.
|
249 |
+
|
250 |
+
Having one of the following certificates: MCITP-SA/Oracle Certified Associate/Oracle
|
251 |
+
Solaris 11 System Administrator Certification/Linux Professional Institute LPIC-1
|
252 |
+
is an advantage.
|
253 |
+
|
254 |
+
Withstand high work pressure, accept to monitor, track systems and handle incidents
|
255 |
+
according to job requirements. Have a serious, careful and enthusiastic working
|
256 |
+
attitude.
|
257 |
+
|
258 |
+
Ability to research and learn technology quickly.
|
259 |
+
|
260 |
+
Good communication and problem-solving skills.
|
261 |
+
|
262 |
+
Ability to work in a team or independently.'
|
263 |
+
- 'Professional qualifications:
|
264 |
+
|
265 |
+
Experience: At least 1 year of participating in projects related to Machine Learning
|
266 |
+
and image processing.
|
267 |
+
|
268 |
+
Programming languages: Proficiency in Python and using frameworks such as TensorFlow,
|
269 |
+
PyTorch, Keras.
|
270 |
+
|
271 |
+
Programming skills: C/C++ skills are an advantage.
|
272 |
+
|
273 |
+
CAD experience: Experience in AI for CAD (AutoCAD, SolidWorks,...) and reading
|
274 |
+
CAD drawings in Python/C++ is an advantage.
|
275 |
+
|
276 |
+
CAD knowledge: Knowledge of 2D to 3D, 3D CAD and Gaussian Splatting is an advantage.
|
277 |
+
|
278 |
+
Awards: Priority is given to those who have IT/mathematical awards or scientific
|
279 |
+
papers in conferences on Image Processing, Image Recognition.
|
280 |
+
|
281 |
+
Language: Good English if the candidate is capable and can work full-time.'
|
282 |
+
- source_sentence: 'PROFESSIONAL EXPERIENCE
|
283 |
+
|
284 |
+
Giggling Platypus Co.
|
285 |
+
|
286 |
+
Software Engineer
|
287 |
+
|
288 |
+
01 Jun 2052 - Present
|
289 |
+
|
290 |
+
|
291 |
+
Designed and implemented a new microservice architecture using Borcelle, improving
|
292 |
+
application performance by 20%.
|
293 |
+
|
294 |
+
Developed and maintained critical features for the company''s core product, resulting
|
295 |
+
in a 15% increase in user engagement.
|
296 |
+
|
297 |
+
Lead the development of a new automated testing framework using Rimberio, reducing
|
298 |
+
manual testing time by 30%.
|
299 |
+
|
300 |
+
Developed and implemented a real-time data processing pipeline using Rimberio
|
301 |
+
to handle a 10x increase in data volume.
|
302 |
+
|
303 |
+
Data Thynk Unlimited
|
304 |
+
|
305 |
+
Software Engineer
|
306 |
+
|
307 |
+
01 Aug 2050 - 30 Apr 2052
|
308 |
+
|
309 |
+
|
310 |
+
Developed custom software solutions to improve application performance.
|
311 |
+
|
312 |
+
Worked closely with cross-functional teams to ensure requirements and quality
|
313 |
+
standards were met.
|
314 |
+
|
315 |
+
EDUCATION
|
316 |
+
|
317 |
+
Fauget University
|
318 |
+
|
319 |
+
Bachelor of Science in Information Technology
|
320 |
+
|
321 |
+
June 2050
|
322 |
+
|
323 |
+
|
324 |
+
SKILLS & COMPETENCIES
|
325 |
+
|
326 |
+
Programming Languages: Rimberio, Borcelle, Java, Python
|
327 |
+
|
328 |
+
Software Development: System Design, Automated Testing, CI/CD
|
329 |
+
|
330 |
+
Analytical and Problem Solving Skills: Requirements Analysis, Performance Optimization
|
331 |
+
|
332 |
+
Communication and Collaboration: Teamwork, Agile Project Management
|
333 |
+
|
334 |
+
Adaptability and Continuous Learning: Quickly Assimilate New Technologies
|
335 |
+
|
336 |
+
CERTIFICATIONS
|
337 |
+
|
338 |
+
Cloud Certified Rimberio | 2050
|
339 |
+
|
340 |
+
Software Lifecycle Professional Borcelle | 2050
|
341 |
+
|
342 |
+
Scrum Developer Borcelle | 2050'
|
343 |
+
sentences:
|
344 |
+
- 'Skills and expertise:
|
345 |
+
|
346 |
+
|
347 |
+
Education:
|
348 |
+
|
349 |
+
|
350 |
+
University graduate majoring in Information Technology or related field.
|
351 |
+
|
352 |
+
Experience:
|
353 |
+
|
354 |
+
|
355 |
+
Minimum 2 years of front-end development experience using the following technologies:
|
356 |
+
|
357 |
+
Proficient in front-end development with JavaScript.
|
358 |
+
|
359 |
+
Experience developing applications for Windows operating systems.
|
360 |
+
|
361 |
+
Passionate about developing applications for Windows platforms.'
|
362 |
+
- 'Required Skills:
|
363 |
+
|
364 |
+
|
365 |
+
Experience:
|
366 |
+
|
367 |
+
|
368 |
+
Minimum 3 years of experience working with .NET or .NET Core.
|
369 |
+
|
370 |
+
Proficient in back-end technologies: ASP.NET Core, EF6 Code First, Identity Server
|
371 |
+
4, RESTful API, SQL Server 2016, C#, Unit Test.
|
372 |
+
|
373 |
+
Good knowledge of ASP.NET MVC frameworks (3,4,5,6), JavaScript, jQuery, JSON,
|
374 |
+
Web API and web application security.
|
375 |
+
|
376 |
+
Additional Skills:
|
377 |
+
|
378 |
+
|
379 |
+
Experience with NodeJS or WPF, WinForms is an advantage.
|
380 |
+
|
381 |
+
Preferably with Microsoft MCP/MCSD certification in web applications or Azure
|
382 |
+
solutions.
|
383 |
+
|
384 |
+
Understanding of Agile/Scrum development methodology.
|
385 |
+
|
386 |
+
Personal Skills:
|
387 |
+
|
388 |
+
|
389 |
+
Honest and confident when working directly with customers.
|
390 |
+
|
391 |
+
Passionate about developing innovative products and willing to learn new technologies
|
392 |
+
from Microsoft Tech Stack and Azure cloud services.
|
393 |
+
|
394 |
+
Ability to analyze and translate business needs into system design and technical
|
395 |
+
solutions.'
|
396 |
+
- 'Qualifications:
|
397 |
+
|
398 |
+
Experience:
|
399 |
+
|
400 |
+
Minimum 2-3 years of experience working with Fullstack technologies, including:
|
401 |
+
|
402 |
+
Frontend: Vue.js (TypeScript), React Native or Flutter.
|
403 |
+
|
404 |
+
Backend: Node.js, C# .NET Core.
|
405 |
+
|
406 |
+
Database: MySQL, SQL Server.
|
407 |
+
|
408 |
+
Architecture: Microservices.
|
409 |
+
|
410 |
+
Advantages:
|
411 |
+
|
412 |
+
Knowledge of Kubernetes (K8s) and ArgoCD.
|
413 |
+
|
414 |
+
Experience working with CI/CD and DevOps systems is a big plus.
|
415 |
+
|
416 |
+
Good problem-solving skills, ability to work independently and collaborate effectively
|
417 |
+
in a team.
|
418 |
+
|
419 |
+
Logical thinking and willingness to learn new technologies.'
|
420 |
+
- source_sentence: 'EDUCATION Bachelor of Technology Really Great University Really
|
421 |
+
Great Company 2016 - Present Responsible for database administration and website
|
422 |
+
design.
|
423 |
+
|
424 |
+
Developed the logic for a streamlined ad-serving platform that scales effectively
|
425 |
+
for educational institutions and online classroom management.
|
426 |
+
|
427 |
+
|
428 |
+
SKILLS Web Design Design Thinking Wireframe Creation Front-End Coding Back-End
|
429 |
+
Technology Problem Solving Computer Literacy Project Management Tools Strong Communication
|
430 |
+
Skills'
|
431 |
+
sentences:
|
432 |
+
- 'LG CNS Vietnam
|
433 |
+
|
434 |
+
|
435 |
+
Skill Requirements
|
436 |
+
|
437 |
+
University graduate majoring in IT.
|
438 |
+
|
439 |
+
Good English communication skills.
|
440 |
+
|
441 |
+
At least 1 year of experience with C#, .NET framework.
|
442 |
+
|
443 |
+
Experience with SQL and DB Function/Procedure.
|
444 |
+
|
445 |
+
Experience with complex SQL optimization (PL/SQL preferred).
|
446 |
+
|
447 |
+
Experience developing Zebra print (will be trained if joining the company).
|
448 |
+
|
449 |
+
Experience with C++, Unix/Linux (will be trained if joining the company).
|
450 |
+
|
451 |
+
Ability to read/write Korean is an advantage.
|
452 |
+
|
453 |
+
Education Requirements
|
454 |
+
|
455 |
+
University graduate majoring in related field.
|
456 |
+
|
457 |
+
Language Requirements
|
458 |
+
|
459 |
+
Good English communication skills.
|
460 |
+
|
461 |
+
Ability to read/write Korean is an advantage.'
|
462 |
+
- 'CA Advance
|
463 |
+
|
464 |
+
Skills & Expertise:
|
465 |
+
|
466 |
+
General Requirements:
|
467 |
+
|
468 |
+
Education:
|
469 |
+
|
470 |
+
|
471 |
+
College degree or higher.
|
472 |
+
|
473 |
+
Development Experience:
|
474 |
+
|
475 |
+
|
476 |
+
2+ years of experience developing Web systems.
|
477 |
+
|
478 |
+
Source Code Management:
|
479 |
+
|
480 |
+
|
481 |
+
2+ years of experience using Git, GitHub or GitLab.
|
482 |
+
|
483 |
+
Learning Ability:
|
484 |
+
|
485 |
+
|
486 |
+
Willing to learn and develop new languages.
|
487 |
+
|
488 |
+
Specific Experience:
|
489 |
+
|
490 |
+
2 years of experience in:
|
491 |
+
|
492 |
+
|
493 |
+
Using HTML, CSS and Bootstrap.
|
494 |
+
|
495 |
+
Using JavaScript.
|
496 |
+
|
497 |
+
Using Next.js, React.js and Redux.
|
498 |
+
|
499 |
+
Using Restful API.
|
500 |
+
|
501 |
+
1 year of experience in:
|
502 |
+
|
503 |
+
|
504 |
+
Developing on public cloud (AWS, Azure, GCP).
|
505 |
+
|
506 |
+
Developing using Agile methodology.
|
507 |
+
|
508 |
+
Experience developing team projects.'
|
509 |
+
- 'Professional Qualifications:
|
510 |
+
|
511 |
+
Education:
|
512 |
+
|
513 |
+
University degree in Information Technology, Software Engineering or related fields.
|
514 |
+
|
515 |
+
Experience:
|
516 |
+
|
517 |
+
More than 4 years of experience as a software developer.
|
518 |
+
|
519 |
+
Skills:
|
520 |
+
|
521 |
+
Experience managing configuration management platforms such as Git, GitHub.
|
522 |
+
|
523 |
+
Familiar with both WinForm and WebForm applications.
|
524 |
+
|
525 |
+
Understanding SQL (MSSQL).
|
526 |
+
|
527 |
+
Using tools: Confluence, Jira, GitHub, CI/CD.
|
528 |
+
|
529 |
+
Understanding of software development processes: Agile, Waterfall.
|
530 |
+
|
531 |
+
Good communication skills (preferred).
|
532 |
+
|
533 |
+
Experience with .NET both WinForm and WebForm, Node.js, Angular.
|
534 |
+
|
535 |
+
Good skills to have:
|
536 |
+
|
537 |
+
Self-management mindset.
|
538 |
+
|
539 |
+
Experience with Information Management Systems.'
|
540 |
+
- source_sentence: 'EDUCATION
|
541 |
+
|
542 |
+
BA in Management Information Systems
|
543 |
+
|
544 |
+
Duy Tan University (2021 - Expected completion 05/2025)
|
545 |
+
|
546 |
+
GPA: 3.6/4.0
|
547 |
+
|
548 |
+
TECHNICAL SKILLS
|
549 |
+
|
550 |
+
Frontend:
|
551 |
+
|
552 |
+
|
553 |
+
Languages ??& Frameworks: HTML, CSS, JavaScript, TypeScript
|
554 |
+
|
555 |
+
Libraries & Tools: TailwindCSS, React.js, Next.js
|
556 |
+
|
557 |
+
Backend:
|
558 |
+
|
559 |
+
|
560 |
+
Main Framework: NestJS, ExpressJS
|
561 |
+
|
562 |
+
Database & ORM: PostgreSQL, MongoDB, TypeOrm, Mongoose
|
563 |
+
|
564 |
+
Cloud Services: AWS, Elasticsearch
|
565 |
+
|
566 |
+
|
567 |
+
Messaging & Streaming: KafkaJS, WebSocket
|
568 |
+
|
569 |
+
|
570 |
+
Container & Deployment: Docker
|
571 |
+
|
572 |
+
|
573 |
+
Other Tools:
|
574 |
+
|
575 |
+
|
576 |
+
Version Control: Git, GitHub
|
577 |
+
|
578 |
+
CI/CD: Vercel
|
579 |
+
|
580 |
+
PERSONAL PROJECTS
|
581 |
+
|
582 |
+
Nestgres
|
583 |
+
|
584 |
+
GitHub Repository: Learning Project with NestJS and PostgreSQL. Integrate AWS
|
585 |
+
S3 for file storage, Docker for containerization, and Elasticsearch for advanced
|
586 |
+
search. This project helped me gain a deep understanding of building a scalable
|
587 |
+
backend system and handling big data.
|
588 |
+
|
589 |
+
|
590 |
+
Simple Todo
|
591 |
+
|
592 |
+
Live Demo: A simple to-do list application to reinforce my knowledge of React,
|
593 |
+
including component architecture, state management, and efficient rendering.
|
594 |
+
|
595 |
+
|
596 |
+
Nestactube
|
597 |
+
|
598 |
+
GitHub Repository: A full-stack video platform combining NestJS and React, serving
|
599 |
+
video streaming from backend to frontend. Focusing on handling large media files
|
600 |
+
and ensuring smooth video playback.
|
601 |
+
|
602 |
+
|
603 |
+
MindForge
|
604 |
+
|
605 |
+
GitHub Repository - Live Demo: Clone of Notion with note creation and editing
|
606 |
+
features. Using Convex for secure data storage and Clerk for user authentication.
|
607 |
+
The project helped me develop a friendly interface and handle complex data structures.
|
608 |
+
|
609 |
+
|
610 |
+
AWARDS & ACHIEVEMENTS
|
611 |
+
|
612 |
+
Excellent Academic Performance - 2022, 2023
|
613 |
+
|
614 |
+
Boeing Scholarship - 2022, 2023
|
615 |
+
|
616 |
+
Third Prize - Duy Tan Informatics Competition, 2023
|
617 |
+
|
618 |
+
Third Prize - Informatics Olympiad (non-specialist group), 2023
|
619 |
+
|
620 |
+
CERTIFICATIONS
|
621 |
+
|
622 |
+
Foundations of User Experience (UX) Design'
|
623 |
+
sentences:
|
624 |
+
- 'Skills and Qualifications Required:
|
625 |
+
|
626 |
+
|
627 |
+
Qualifications:
|
628 |
+
|
629 |
+
|
630 |
+
Bachelor''s degree in Computer Science, Computer Networking or related fields
|
631 |
+
from Universities such as University of Science, University of Natural Sciences,
|
632 |
+
University of Information Technology, Vietnam National University, Ho Chi Minh
|
633 |
+
City, or Vietnam National University, Hanoi.
|
634 |
+
|
635 |
+
Only candidates with academic background and practical experience directly related
|
636 |
+
to Information Technology will be considered (candidates from short-term or non-major
|
637 |
+
programs will not be accepted).
|
638 |
+
|
639 |
+
Grade Point Average (GPA):
|
640 |
+
|
641 |
+
|
642 |
+
Minimum GPA: 7.0 (on a scale of 10) or 2.8 (on a scale of 4)
|
643 |
+
|
644 |
+
|
645 |
+
Technical Skills:
|
646 |
+
|
647 |
+
|
648 |
+
Strong programming skills with C/C++, along with knowledge of object-oriented
|
649 |
+
programming.
|
650 |
+
|
651 |
+
Have practical experience (1 year or more) working with C/C++.
|
652 |
+
|
653 |
+
Basic knowledge of operating systems such as Windows, Linux, and MacOS.
|
654 |
+
|
655 |
+
Understanding of network protocols and security principles. Strong team working
|
656 |
+
skills and problem solving ability.'
|
657 |
+
- 'Qualifications:
|
658 |
+
|
659 |
+
|
660 |
+
Expected Skills:
|
661 |
+
|
662 |
+
|
663 |
+
Programming Languages: Proficiency in C# and experience working with Unity3D.
|
664 |
+
|
665 |
+
Game Development: Solid understanding of game mechanics, UI/UX, and physics.
|
666 |
+
|
667 |
+
Cybersecurity Tools: Experience with cyber security tools with a defensive/offensive
|
668 |
+
mindset.
|
669 |
+
|
670 |
+
Performance Optimization: Solid skills in game optimization and memory management.
|
671 |
+
|
672 |
+
Version Management Knowledge: Familiarity with Git or similar version control
|
673 |
+
systems.
|
674 |
+
|
675 |
+
Preferred Skills:
|
676 |
+
|
677 |
+
|
678 |
+
AR/VR development experience is a plus.
|
679 |
+
|
680 |
+
Knowledge of multi-player and networking concepts, along with creativity.
|
681 |
+
|
682 |
+
Education:
|
683 |
+
|
684 |
+
|
685 |
+
Bachelor''s degree in Computer Science, Game Development, or related field, or
|
686 |
+
equivalent hands-on experience.'
|
687 |
+
- 'Professional qualifications:
|
688 |
+
|
689 |
+
Experience: At least 1 year of participating in projects related to Machine Learning
|
690 |
+
and image processing.
|
691 |
+
|
692 |
+
Programming languages: Proficiency in Python and using frameworks such as TensorFlow,
|
693 |
+
PyTorch, Keras.
|
694 |
+
|
695 |
+
Programming skills: C/C++ skills are an advantage.
|
696 |
+
|
697 |
+
CAD experience: Experience in AI for CAD (AutoCAD, SolidWorks,...) and reading
|
698 |
+
CAD drawings in Python/C++ is an advantage.
|
699 |
+
|
700 |
+
CAD knowledge: Knowledge of 2D to 3D, 3D CAD and Gaussian Splatting is an advantage.
|
701 |
+
|
702 |
+
Awards: Priority is given to those who have IT/mathematical awards or scientific
|
703 |
+
papers in conferences on Image Processing, Image Recognition.
|
704 |
+
|
705 |
+
Language: Good English if the candidate is capable and can work full-time.'
|
706 |
+
---
|
707 |
+
|
708 |
+
# SentenceTransformer based on sentence-transformers/distiluse-base-multilingual-cased-v1
|
709 |
+
|
710 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/distiluse-base-multilingual-cased-v1](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v1). It maps sentences & paragraphs to a 512-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
711 |
+
|
712 |
+
## Model Details
|
713 |
+
|
714 |
+
### Model Description
|
715 |
+
- **Model Type:** Sentence Transformer
|
716 |
+
- **Base model:** [sentence-transformers/distiluse-base-multilingual-cased-v1](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v1) <!-- at revision 30487a83b196a60bdf70abff0505ec70f112213c -->
|
717 |
+
- **Maximum Sequence Length:** 128 tokens
|
718 |
+
- **Output Dimensionality:** 512 tokens
|
719 |
+
- **Similarity Function:** Cosine Similarity
|
720 |
+
<!-- - **Training Dataset:** Unknown -->
|
721 |
+
<!-- - **Language:** Unknown -->
|
722 |
+
<!-- - **License:** Unknown -->
|
723 |
+
|
724 |
+
### Model Sources
|
725 |
+
|
726 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
727 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
728 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
729 |
+
|
730 |
+
### Full Model Architecture
|
731 |
+
|
732 |
+
```
|
733 |
+
SentenceTransformer(
|
734 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
|
735 |
+
(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})
|
736 |
+
(2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
|
737 |
+
)
|
738 |
+
```
|
739 |
+
|
740 |
+
## Usage
|
741 |
+
|
742 |
+
### Direct Usage (Sentence Transformers)
|
743 |
+
|
744 |
+
First install the Sentence Transformers library:
|
745 |
+
|
746 |
+
```bash
|
747 |
+
pip install -U sentence-transformers
|
748 |
+
```
|
749 |
+
|
750 |
+
Then you can load this model and run inference.
|
751 |
+
```python
|
752 |
+
from sentence_transformers import SentenceTransformer
|
753 |
+
|
754 |
+
# Download from the 🤗 Hub
|
755 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
756 |
+
# Run inference
|
757 |
+
sentences = [
|
758 |
+
'EDUCATION\nBA in Management Information Systems\nDuy Tan University (2021 - Expected completion 05/2025)\nGPA: 3.6/4.0\nTECHNICAL SKILLS\nFrontend:\n\nLanguages ??& Frameworks: HTML, CSS, JavaScript, TypeScript\nLibraries & Tools: TailwindCSS, React.js, Next.js\nBackend:\n\nMain Framework: NestJS, ExpressJS\nDatabase & ORM: PostgreSQL, MongoDB, TypeOrm, Mongoose\nCloud Services: AWS, Elasticsearch\n\nMessaging & Streaming: KafkaJS, WebSocket\n\nContainer & Deployment: Docker\n\nOther Tools:\n\nVersion Control: Git, GitHub\nCI/CD: Vercel\nPERSONAL PROJECTS\nNestgres\nGitHub Repository: Learning Project with NestJS and PostgreSQL. Integrate AWS S3 for file storage, Docker for containerization, and Elasticsearch for advanced search. This project helped me gain a deep understanding of building a scalable backend system and handling big data.\n\nSimple Todo\nLive Demo: A simple to-do list application to reinforce my knowledge of React, including component architecture, state management, and efficient rendering.\n\nNestactube\nGitHub Repository: A full-stack video platform combining NestJS and React, serving video streaming from backend to frontend. Focusing on handling large media files and ensuring smooth video playback.\n\nMindForge\nGitHub Repository - Live Demo: Clone of Notion with note creation and editing features. Using Convex for secure data storage and Clerk for user authentication. The project helped me develop a friendly interface and handle complex data structures.\n\nAWARDS & ACHIEVEMENTS\nExcellent Academic Performance - 2022, 2023\nBoeing Scholarship - 2022, 2023\nThird Prize - Duy Tan Informatics Competition, 2023\nThird Prize - Informatics Olympiad (non-specialist group), 2023\nCERTIFICATIONS\nFoundations of User Experience (UX) Design',
|
759 |
+
"Skills and Qualifications Required:\n\nQualifications:\n\nBachelor's degree in Computer Science, Computer Networking or related fields from Universities such as University of Science, University of Natural Sciences, University of Information Technology, Vietnam National University, Ho Chi Minh City, or Vietnam National University, Hanoi.\nOnly candidates with academic background and practical experience directly related to Information Technology will be considered (candidates from short-term or non-major programs will not be accepted).\nGrade Point Average (GPA):\n\nMinimum GPA: 7.0 (on a scale of 10) or 2.8 (on a scale of 4)\n\nTechnical Skills:\n\nStrong programming skills with C/C++, along with knowledge of object-oriented programming.\nHave practical experience (1 year or more) working with C/C++.\nBasic knowledge of operating systems such as Windows, Linux, and MacOS.\nUnderstanding of network protocols and security principles. Strong team working skills and problem solving ability.",
|
760 |
+
"Qualifications:\n\nExpected Skills:\n\nProgramming Languages: Proficiency in C# and experience working with Unity3D.\nGame Development: Solid understanding of game mechanics, UI/UX, and physics.\nCybersecurity Tools: Experience with cyber security tools with a defensive/offensive mindset.\nPerformance Optimization: Solid skills in game optimization and memory management.\nVersion Management Knowledge: Familiarity with Git or similar version control systems.\nPreferred Skills:\n\nAR/VR development experience is a plus.\nKnowledge of multi-player and networking concepts, along with creativity.\nEducation:\n\nBachelor's degree in Computer Science, Game Development, or related field, or equivalent hands-on experience.",
|
761 |
+
]
|
762 |
+
embeddings = model.encode(sentences)
|
763 |
+
print(embeddings.shape)
|
764 |
+
# [3, 512]
|
765 |
+
|
766 |
+
# Get the similarity scores for the embeddings
|
767 |
+
similarities = model.similarity(embeddings, embeddings)
|
768 |
+
print(similarities.shape)
|
769 |
+
# [3, 3]
|
770 |
+
```
|
771 |
+
|
772 |
+
<!--
|
773 |
+
### Direct Usage (Transformers)
|
774 |
+
|
775 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
776 |
+
|
777 |
+
</details>
|
778 |
+
-->
|
779 |
+
|
780 |
+
<!--
|
781 |
+
### Downstream Usage (Sentence Transformers)
|
782 |
+
|
783 |
+
You can finetune this model on your own dataset.
|
784 |
+
|
785 |
+
<details><summary>Click to expand</summary>
|
786 |
+
|
787 |
+
</details>
|
788 |
+
-->
|
789 |
+
|
790 |
+
<!--
|
791 |
+
### Out-of-Scope Use
|
792 |
+
|
793 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
794 |
+
-->
|
795 |
+
|
796 |
+
<!--
|
797 |
+
## Bias, Risks and Limitations
|
798 |
+
|
799 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
800 |
+
-->
|
801 |
+
|
802 |
+
<!--
|
803 |
+
### Recommendations
|
804 |
+
|
805 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
806 |
+
-->
|
807 |
+
|
808 |
+
## Training Details
|
809 |
+
|
810 |
+
### Training Dataset
|
811 |
+
|
812 |
+
#### Unnamed Dataset
|
813 |
+
|
814 |
+
|
815 |
+
* Size: 5,108 training samples
|
816 |
+
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
|
817 |
+
* Approximate statistics based on the first 1000 samples:
|
818 |
+
| | sentence_0 | sentence_1 | label |
|
819 |
+
|:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:----------------------------------------------------------------|
|
820 |
+
| type | string | string | float |
|
821 |
+
| details | <ul><li>min: 44 tokens</li><li>mean: 106.09 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 46 tokens</li><li>mean: 117.55 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 0.5</li><li>mean: 0.66</li><li>max: 0.74</li></ul> |
|
822 |
+
* Samples:
|
823 |
+
| sentence_0 | sentence_1 | label |
|
824 |
+
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------|
|
825 |
+
| <code>EDUCATION<br>Software Engineer (CMU)<br>Duy Tan University, 09/2021 - Present<br>GPA: 3.6/4.0<br>OUTSTANDING PROJECTS<br>Fashion Store Website<br>Time: 17/01 - 25/02<br>Role: Backend Developer<br><br>Features:<br><br>Register, log in, log out (customer rights)<br>Log in and manage with admin rights<br>Add, edit, delete products and vouchers (admin)<br>Display product and voucher list<br>Technology:<br><br>Frontend: Customer page & admin dashboard (edit from available template)<br>Backend: Typescript (NestJS)<br>Database: MongoDB (Mongoose)<br>GitHub Link: Fashion Store Project<br><br>SKILLS<br>Front-end: HTML, CSS, JavaScript, Bootstrap 5, ReactJS<br>Back-end: ExpressJS, NestJS (TypeScript)<br>Database: MySQL, MongoDB<br>OTHER TOOLS & TECHNOLOGIES<br>Tools: Git (GitHub), Docker, Postman<br>Other languages: C# (ASP.NET), Java (Spring Boot)<br>LANGUAGES<br>English: Good communication and reading skills</code> | <code>Professional Qualifications:<br>Experience: Minimum 2 years of experience working with Java, proficient in Spring Boot.<br>Frontend Framework: Proficient in using one of the Frontend frameworks (such as Vue, React,...) to develop interactive user interfaces.<br>Database: Experience working with relational databases such as MS SQL Server, Oracle, PostgreSQL, MongoDB.<br>Microservice Architecture: Experience with microservice architecture and containerization technologies such as Kubernetes/Docker.<br>Multitasking: Ability to handle multitasking, multithreading, multiprocessing, and mechanisms such as hash tables, file processing mechanisms.<br>API Integration: Experience in integrating/developing RESTful, SOAP, TCP/IP APIs.<br>Operating System: Experience working with Enterprise Linux and Windows Server operating systems.</code> | <code>0.65</code> |
|
826 |
+
| <code>EDUCATION HISTORY University of Roseton Master of Science in Software Engineering | Graduated: 2020 Best Thesis Awardee Berou Solutions Scholarship Recipient De Loureigh University Bachelor of Science in Computer Science | Graduated: 2016 (Cum Laude) Founder of DLU Programming Club Hackathon Champion Beechtown 2015 RELEVANT SKILLS Programming Languages: JavaScript, C/C++, Java, Python, Kotlin, Go Core Skills: Problem Solving, Team Communication</code> | <code>FPT<br><br>Skill and qualification requirements:<br><br>General standards:<br><br>Be a Vietnamese citizen, have a permanent residence in Vietnam.<br>Be under 35 years old.<br>Be in good health to perform the job.<br>Have good moral qualities, no criminal record, no detention, no prison sentence, suspended sentence, non-custodial reform, no local education status, medical treatment, drug rehabilitation, etc.<br>Specific standards:<br><br>Professional qualifications:<br><br>Graduate from university or higher, regular system (including second university, not including university transfer) at domestic universities or graduate from university or higher at foreign universities, affiliated universities.<br>Major: Graduated from majors such as Information Technology, Information Security, Telecommunications Electronics, Information Electronics, Mathematics - Informatics or equivalent majors.<br>Foreign Language:<br><br>Having one of the following certificates: TOEIC 600/990, TOEFL PBT/IPT 500/677, TOEFL CBT 173/300, TOEFL iBT 61/120, IELTS 5.5/9.0, Cambridge Exam First (FCE), B2 European Framework, 4/6 6-level Foreign Language Proficiency Framework for Vietnam. Accepting additional English certificates within 24 months from the date of recruitment.<br>Knowledge, skills and experience:<br><br>Experience in managing server systems and storage systems is an advantage.<br>Having one of the following certificates: MCITP-SA/Oracle Certified Associate/Oracle Solaris 11 System Administrator Certification/Linux Professional Institute LPIC-1 is an advantage.<br>Withstand high work pressure, accept to monitor, track systems and handle incidents according to job requirements. Have a serious, careful and enthusiastic working attitude.<br>Ability to research and learn technology quickly.<br>Good communication and problem-solving skills.<br>Ability to work in a team or independently.</code> | <code>0.66</code> |
|
827 |
+
| <code>EDUCATION Bachelor of Science in Computer Science Rutgers University ? New Brunswick, NJ 2008 - 2012 SKILLS HTML CSS JavaScript React jQuery Angular.js Vue.js Enzyme Jest Git</code> | <code>ABBANK<br><br>Skill requirements:<br><br>Minimum 5 years of experience as a BA in CLIMS system.<br>Experience in lending activities.<br>Experience in developing test scenarios and test plans for software projects.<br>Understanding of software development processes.<br>Ensure compliance with application development standards and quality processes.<br>Ability to analyze and resolve complex technical issues, provide feasible and timely solutions.<br>Effective communication and teamwork skills when collaborating with different functional groups.<br>Focus on Agile implementation and willingness to learn and grow from experience.<br>Education requirements:<br><br>University degree in IT, banking, finance or related fields.<br>Language requirements:<br><br>Being able to communicate in English is an advantage.</code> | <code>0.62</code> |
|
828 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
829 |
+
```json
|
830 |
+
{
|
831 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
832 |
+
}
|
833 |
+
```
|
834 |
+
|
835 |
+
### Training Hyperparameters
|
836 |
+
#### Non-Default Hyperparameters
|
837 |
+
|
838 |
+
- `per_device_train_batch_size`: 16
|
839 |
+
- `per_device_eval_batch_size`: 16
|
840 |
+
- `multi_dataset_batch_sampler`: round_robin
|
841 |
+
|
842 |
+
#### All Hyperparameters
|
843 |
+
<details><summary>Click to expand</summary>
|
844 |
+
|
845 |
+
- `overwrite_output_dir`: False
|
846 |
+
- `do_predict`: False
|
847 |
+
- `eval_strategy`: no
|
848 |
+
- `prediction_loss_only`: True
|
849 |
+
- `per_device_train_batch_size`: 16
|
850 |
+
- `per_device_eval_batch_size`: 16
|
851 |
+
- `per_gpu_train_batch_size`: None
|
852 |
+
- `per_gpu_eval_batch_size`: None
|
853 |
+
- `gradient_accumulation_steps`: 1
|
854 |
+
- `eval_accumulation_steps`: None
|
855 |
+
- `torch_empty_cache_steps`: None
|
856 |
+
- `learning_rate`: 5e-05
|
857 |
+
- `weight_decay`: 0.0
|
858 |
+
- `adam_beta1`: 0.9
|
859 |
+
- `adam_beta2`: 0.999
|
860 |
+
- `adam_epsilon`: 1e-08
|
861 |
+
- `max_grad_norm`: 1
|
862 |
+
- `num_train_epochs`: 3
|
863 |
+
- `max_steps`: -1
|
864 |
+
- `lr_scheduler_type`: linear
|
865 |
+
- `lr_scheduler_kwargs`: {}
|
866 |
+
- `warmup_ratio`: 0.0
|
867 |
+
- `warmup_steps`: 0
|
868 |
+
- `log_level`: passive
|
869 |
+
- `log_level_replica`: warning
|
870 |
+
- `log_on_each_node`: True
|
871 |
+
- `logging_nan_inf_filter`: True
|
872 |
+
- `save_safetensors`: True
|
873 |
+
- `save_on_each_node`: False
|
874 |
+
- `save_only_model`: False
|
875 |
+
- `restore_callback_states_from_checkpoint`: False
|
876 |
+
- `no_cuda`: False
|
877 |
+
- `use_cpu`: False
|
878 |
+
- `use_mps_device`: False
|
879 |
+
- `seed`: 42
|
880 |
+
- `data_seed`: None
|
881 |
+
- `jit_mode_eval`: False
|
882 |
+
- `use_ipex`: False
|
883 |
+
- `bf16`: False
|
884 |
+
- `fp16`: False
|
885 |
+
- `fp16_opt_level`: O1
|
886 |
+
- `half_precision_backend`: auto
|
887 |
+
- `bf16_full_eval`: False
|
888 |
+
- `fp16_full_eval`: False
|
889 |
+
- `tf32`: None
|
890 |
+
- `local_rank`: 0
|
891 |
+
- `ddp_backend`: None
|
892 |
+
- `tpu_num_cores`: None
|
893 |
+
- `tpu_metrics_debug`: False
|
894 |
+
- `debug`: []
|
895 |
+
- `dataloader_drop_last`: False
|
896 |
+
- `dataloader_num_workers`: 0
|
897 |
+
- `dataloader_prefetch_factor`: None
|
898 |
+
- `past_index`: -1
|
899 |
+
- `disable_tqdm`: False
|
900 |
+
- `remove_unused_columns`: True
|
901 |
+
- `label_names`: None
|
902 |
+
- `load_best_model_at_end`: False
|
903 |
+
- `ignore_data_skip`: False
|
904 |
+
- `fsdp`: []
|
905 |
+
- `fsdp_min_num_params`: 0
|
906 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
907 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
908 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
909 |
+
- `deepspeed`: None
|
910 |
+
- `label_smoothing_factor`: 0.0
|
911 |
+
- `optim`: adamw_torch
|
912 |
+
- `optim_args`: None
|
913 |
+
- `adafactor`: False
|
914 |
+
- `group_by_length`: False
|
915 |
+
- `length_column_name`: length
|
916 |
+
- `ddp_find_unused_parameters`: None
|
917 |
+
- `ddp_bucket_cap_mb`: None
|
918 |
+
- `ddp_broadcast_buffers`: False
|
919 |
+
- `dataloader_pin_memory`: True
|
920 |
+
- `dataloader_persistent_workers`: False
|
921 |
+
- `skip_memory_metrics`: True
|
922 |
+
- `use_legacy_prediction_loop`: False
|
923 |
+
- `push_to_hub`: False
|
924 |
+
- `resume_from_checkpoint`: None
|
925 |
+
- `hub_model_id`: None
|
926 |
+
- `hub_strategy`: every_save
|
927 |
+
- `hub_private_repo`: False
|
928 |
+
- `hub_always_push`: False
|
929 |
+
- `gradient_checkpointing`: False
|
930 |
+
- `gradient_checkpointing_kwargs`: None
|
931 |
+
- `include_inputs_for_metrics`: False
|
932 |
+
- `eval_do_concat_batches`: True
|
933 |
+
- `fp16_backend`: auto
|
934 |
+
- `push_to_hub_model_id`: None
|
935 |
+
- `push_to_hub_organization`: None
|
936 |
+
- `mp_parameters`:
|
937 |
+
- `auto_find_batch_size`: False
|
938 |
+
- `full_determinism`: False
|
939 |
+
- `torchdynamo`: None
|
940 |
+
- `ray_scope`: last
|
941 |
+
- `ddp_timeout`: 1800
|
942 |
+
- `torch_compile`: False
|
943 |
+
- `torch_compile_backend`: None
|
944 |
+
- `torch_compile_mode`: None
|
945 |
+
- `dispatch_batches`: None
|
946 |
+
- `split_batches`: None
|
947 |
+
- `include_tokens_per_second`: False
|
948 |
+
- `include_num_input_tokens_seen`: False
|
949 |
+
- `neftune_noise_alpha`: None
|
950 |
+
- `optim_target_modules`: None
|
951 |
+
- `batch_eval_metrics`: False
|
952 |
+
- `eval_on_start`: False
|
953 |
+
- `eval_use_gather_object`: False
|
954 |
+
- `batch_sampler`: batch_sampler
|
955 |
+
- `multi_dataset_batch_sampler`: round_robin
|
956 |
+
|
957 |
+
</details>
|
958 |
+
|
959 |
+
### Training Logs
|
960 |
+
| Epoch | Step | Training Loss |
|
961 |
+
|:------:|:----:|:-------------:|
|
962 |
+
| 1.5625 | 500 | 0.0023 |
|
963 |
+
|
964 |
+
|
965 |
+
### Framework Versions
|
966 |
+
- Python: 3.10.12
|
967 |
+
- Sentence Transformers: 3.2.1
|
968 |
+
- Transformers: 4.44.2
|
969 |
+
- PyTorch: 2.5.0+cu121
|
970 |
+
- Accelerate: 0.34.2
|
971 |
+
- Datasets: 3.1.0
|
972 |
+
- Tokenizers: 0.19.1
|
973 |
+
|
974 |
+
## Citation
|
975 |
+
|
976 |
+
### BibTeX
|
977 |
+
|
978 |
+
#### Sentence Transformers
|
979 |
+
```bibtex
|
980 |
+
@inproceedings{reimers-2019-sentence-bert,
|
981 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
982 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
983 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
984 |
+
month = "11",
|
985 |
+
year = "2019",
|
986 |
+
publisher = "Association for Computational Linguistics",
|
987 |
+
url = "https://arxiv.org/abs/1908.10084",
|
988 |
+
}
|
989 |
+
```
|
990 |
+
|
991 |
+
<!--
|
992 |
+
## Glossary
|
993 |
+
|
994 |
+
*Clearly define terms in order to be accessible across audiences.*
|
995 |
+
-->
|
996 |
+
|
997 |
+
<!--
|
998 |
+
## Model Card Authors
|
999 |
+
|
1000 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
1001 |
+
-->
|
1002 |
+
|
1003 |
+
<!--
|
1004 |
+
## Model Card Contact
|
1005 |
+
|
1006 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
1007 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/distiluse-base-multilingual-cased-v1",
|
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": "4.44.2",
|
23 |
+
"vocab_size": 119547
|
24 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.2.1",
|
4 |
+
"transformers": "4.44.2",
|
5 |
+
"pytorch": "2.5.0+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": null
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:698b2fe793ff27e94ca8b6eb4470fd4f00592dff8530dd5d22b3466459d93a6e
|
3 |
+
size 538947416
|
modules.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Dense",
|
18 |
+
"type": "sentence_transformers.models.Dense"
|
19 |
+
}
|
20 |
+
]
|
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": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_len": 512,
|
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
|
|