Add new SentenceTransformer model
Browse files- 1_Pooling/config.json +10 -0
- README.md +855 -0
- config.json +25 -0
- config_sentence_transformers.json +12 -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 +63 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 1024,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,855 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:210
|
8 |
+
- loss:MatryoshkaLoss
|
9 |
+
- loss:MultipleNegativesRankingLoss
|
10 |
+
base_model: Snowflake/snowflake-arctic-embed-l
|
11 |
+
widget:
|
12 |
+
- source_sentence: 'What does maintenance refer to in the context of providing for
|
13 |
+
another person? '
|
14 |
+
sentences:
|
15 |
+
- '-M-
|
16 |
+
|
17 |
+
Maintenance: The f urnishing by one person to another the means of living, or
|
18 |
+
fo od, clothing,'
|
19 |
+
- 'income and expenses to determine if the debtor may proceed under Chapter 7.
|
20 |
+
|
21 |
+
Chapter 7 trustee
|
22 |
+
|
23 |
+
A person appointed in a Chapter 7 case to represent the interests of the bankruptcy
|
24 |
+
estate
|
25 |
+
|
26 |
+
and the creditors. The trustee''s responsibilities include reviewing the debtor''s
|
27 |
+
petition and
|
28 |
+
|
29 |
+
schedules, liquidating the property of the estate, and making distributions to
|
30 |
+
creditors. The
|
31 |
+
|
32 |
+
trustee may also bring actions against creditors or the debtor to recover property
|
33 |
+
of the
|
34 |
+
|
35 |
+
bankruptcy estate.
|
36 |
+
|
37 |
+
Chapter 9'
|
38 |
+
- '-19-
|
39 |
+
|
40 |
+
Trial De Novo: A new trial (See 22NYCRR 28.12).
|
41 |
+
|
42 |
+
-U-
|
43 |
+
|
44 |
+
Undertaking: Deposit of a sum of money or filing of a bond in court, to secure
|
45 |
+
some actual or
|
46 |
+
|
47 |
+
potential obligation.
|
48 |
+
|
49 |
+
-V-
|
50 |
+
|
51 |
+
Vacate: To set aside or undo a previous action or order.
|
52 |
+
|
53 |
+
Venire: Technically, a writ summoning persons to court to act as jurors; popularly
|
54 |
+
used as meaning
|
55 |
+
|
56 |
+
the body of names thus summoned.
|
57 |
+
|
58 |
+
Venue: (a) Geographical place where some legal matter occurs or may be determined.
|
59 |
+
(b) The
|
60 |
+
|
61 |
+
geographical area within which a court has jurisdiction. It relates only to a
|
62 |
+
place or territory within
|
63 |
+
|
64 |
+
which either party may require a case to be tried. A defect in venue may be waived
|
65 |
+
by the parties.'
|
66 |
+
- source_sentence: 'What does the term "Pro Se" refer to in a legal context? '
|
67 |
+
sentences:
|
68 |
+
- 'Process: A l egal means, such as a s ummons, used to s ubject a de fendant i
|
69 |
+
n a l awsuit to the
|
70 |
+
|
71 |
+
personal jur isdiction o f the c ourt; broa dly, r efers to all writs iss ued
|
72 |
+
i n the c ourse of a le gal
|
73 |
+
|
74 |
+
proceeding - what is served to obtain jurisdiction.
|
75 |
+
|
76 |
+
Pro Se (aka Self-Represented): Appearing on one’s own behalf without an attorney.
|
77 |
+
|
78 |
+
Purge: To atone for or correct an offense, to submit to a court''s mandate (i.e.,
|
79 |
+
to purge oneself
|
80 |
+
|
81 |
+
of contempt of court).
|
82 |
+
|
83 |
+
-Q-
|
84 |
+
|
85 |
+
None.
|
86 |
+
|
87 |
+
-R-
|
88 |
+
|
89 |
+
Recuse: To disqualify oneself as a judge.
|
90 |
+
|
91 |
+
Redact: To edit, revise or block out written text.
|
92 |
+
|
93 |
+
Referee: A person to whom a claim pending in a court is referred by the court
|
94 |
+
to take testimony,'
|
95 |
+
- '-10-
|
96 |
+
|
97 |
+
Hearing: A pr eliminary examination where testimony is given and e vidence presented
|
98 |
+
for the
|
99 |
+
|
100 |
+
purpose of determining an issue of fact and reaching a decision on the basis of
|
101 |
+
that evidence.
|
102 |
+
|
103 |
+
Hearsay: Testimony of a witness who relates not what he/she knows personally,
|
104 |
+
but what others
|
105 |
+
|
106 |
+
have told the witness, or what the witness has heard said by others; may be admissible
|
107 |
+
or
|
108 |
+
|
109 |
+
inadmissible in court depending upon rules of evidence.
|
110 |
+
|
111 |
+
Hung Jury: A jury whose members cannot reconcile their differences of opinion
|
112 |
+
and thus cannot
|
113 |
+
|
114 |
+
reach a verdict.
|
115 |
+
|
116 |
+
-I-
|
117 |
+
|
118 |
+
Impaneling: The process by which jurors are selected and sworn to their task.
|
119 |
+
|
120 |
+
Impleader: An addition of another party to an action by the defendant, a “third
|
121 |
+
party” claim.'
|
122 |
+
- '-12-
|
123 |
+
|
124 |
+
Jurisdiction, Subject Matter: Whether the court has authority over the thing
|
125 |
+
or right claimed by
|
126 |
+
|
127 |
+
one party against another.
|
128 |
+
|
129 |
+
Jury: A prescribed number of persons selected according to law and sworn to make
|
130 |
+
findings of
|
131 |
+
|
132 |
+
fact.
|
133 |
+
|
134 |
+
Jury (Advisory): A body of jurors impaneled to hear a case in which the parties
|
135 |
+
have no right to
|
136 |
+
|
137 |
+
a jury trial - the judge remains solely responsible for the findings and may accept
|
138 |
+
or reject the
|
139 |
+
|
140 |
+
jury''s verdict.
|
141 |
+
|
142 |
+
Jury Instructions: Directions given by the judge to the jury, at the beginning
|
143 |
+
and end of trial.
|
144 |
+
|
145 |
+
-K-
|
146 |
+
|
147 |
+
None.
|
148 |
+
|
149 |
+
-L-
|
150 |
+
|
151 |
+
Laches: The failure to diligently assert a right, which results in a refusal
|
152 |
+
to allow the right to be
|
153 |
+
|
154 |
+
asserted later.
|
155 |
+
|
156 |
+
Legal Age: Eighteen (18) years of age. See CPLR Section 1206.'
|
157 |
+
- source_sentence: What is the purpose of a Chapter 11 bankruptcy filing?
|
158 |
+
sentences:
|
159 |
+
- 'condemnation, i.e., the legal process by which real estate of a private owner
|
160 |
+
is taken for public use
|
161 |
+
|
162 |
+
without the owner''s consent, but upon the award and payment of just compensation.
|
163 |
+
|
164 |
+
Enjoin: To require a person, by writ of injunction from a court of equity, to
|
165 |
+
perform or to refrain
|
166 |
+
|
167 |
+
from or cease doing some act.
|
168 |
+
|
169 |
+
Entry: The formal filing of an order of judgment with the County Clerk.
|
170 |
+
|
171 |
+
Equitable Action (Equity Matter): An action which may be brought for the purpose
|
172 |
+
of restraining'
|
173 |
+
- 'A legal claim.
|
174 |
+
|
175 |
+
Chambers
|
176 |
+
|
177 |
+
The offices of a judge and his or her staff.
|
178 |
+
|
179 |
+
Chapter 11
|
180 |
+
|
181 |
+
A reorganization bankruptcy, usually involving a corporation or partnership. A
|
182 |
+
Chapter 11
|
183 |
+
|
184 |
+
debtor usually proposes a plan of reorganization to keep its business alive and
|
185 |
+
pay creditors
|
186 |
+
|
187 |
+
over time. Individuals or people in business can also seek relief in Chapter 11.
|
188 |
+
|
189 |
+
Chapter 12
|
190 |
+
|
191 |
+
The chapter of the Bankruptcy Code providing for adjustment of debts of a "family
|
192 |
+
farmer"
|
193 |
+
|
194 |
+
or "family fisherman," as the terms are defined in the Bankruptcy Code.
|
195 |
+
|
196 |
+
Chapter 13
|
197 |
+
|
198 |
+
The chapter of the Bankruptcy Code providing for the adjustment of debts of an
|
199 |
+
individual
|
200 |
+
|
201 |
+
with regular income, often referred to as a "wage-earner" plan. Chapter 13 allows
|
202 |
+
a debtor'
|
203 |
+
- 'Conviction
|
204 |
+
|
205 |
+
A judgment of guilt against a criminal defendant.
|
206 |
+
|
207 |
+
Counsel
|
208 |
+
|
209 |
+
Legal advice; a term also used to refer to the lawyers in a case.
|
210 |
+
|
211 |
+
Count
|
212 |
+
|
213 |
+
An allegation in an indictment or information, charging a defendant with a crime.
|
214 |
+
An
|
215 |
+
|
216 |
+
indictment or information may contain allegations that the defendant committed
|
217 |
+
more
|
218 |
+
|
219 |
+
than one crime. Each allegation is referred to as a count.
|
220 |
+
|
221 |
+
Court
|
222 |
+
|
223 |
+
Government entity authorized to resolve legal disputes. Judges sometimes use "court"
|
224 |
+
to
|
225 |
+
|
226 |
+
refer to themselves in the third person, as in "the court has read the briefs."
|
227 |
+
|
228 |
+
Court reporter
|
229 |
+
|
230 |
+
A person who makes a word-for-word record of what is said in court, generally
|
231 |
+
by using a
|
232 |
+
|
233 |
+
stenographic machine, shorthand or audio recording, and then produces a transcript
|
234 |
+
of the'
|
235 |
+
- source_sentence: 'What types of property may a debtor be able to exempt under the
|
236 |
+
homestead exemption? '
|
237 |
+
sentences:
|
238 |
+
- '-2-
|
239 |
+
|
240 |
+
Affidavit of Service: An affidavit intended to certify or prove that service
|
241 |
+
of a writ, notice, or other
|
242 |
+
|
243 |
+
document has been made.
|
244 |
+
|
245 |
+
Affirm: An act of declaring something to be true under the penalty of perjury
|
246 |
+
by a person who
|
247 |
+
|
248 |
+
conscientiously declines to take an oath for religious or other pertinent reasons;
|
249 |
+
also attorneys are
|
250 |
+
|
251 |
+
permitted to affirm rather than swear under oath.
|
252 |
+
|
253 |
+
Affirmation: A solemn and formal declaration under penalties of perjury that
|
254 |
+
a statement is true,
|
255 |
+
|
256 |
+
without an oath.
|
257 |
+
|
258 |
+
Affirmed: Upheld, agreed with (e.g.,The Appellate Court affirmed the judgment
|
259 |
+
of the City Court);
|
260 |
+
|
261 |
+
also means a challenge to a court decision or order was rejected.'
|
262 |
+
- 'A formal request for the protection of the federal bankruptcy laws. (There is
|
263 |
+
an official form
|
264 |
+
|
265 |
+
for bankruptcy petitions.)
|
266 |
+
|
267 |
+
Bankruptcy trustee
|
268 |
+
|
269 |
+
A private individual or corporation appointed in all Chapter 7 and Chapter 13
|
270 |
+
cases to
|
271 |
+
|
272 |
+
represent the interests of the bankruptcy estate and the debtor''s creditors.
|
273 |
+
|
274 |
+
Bench trial
|
275 |
+
|
276 |
+
A trial without a jury, in which the judge serves as the fact-finder.
|
277 |
+
|
278 |
+
Brief
|
279 |
+
|
280 |
+
A written statement submitted in a trial or appellate proceeding that explains
|
281 |
+
one side''s
|
282 |
+
|
283 |
+
legal and factual arguments.
|
284 |
+
|
285 |
+
Burden of proof
|
286 |
+
|
287 |
+
The duty to prove disputed facts. In civil cases, a plaintiff generally has the
|
288 |
+
burden of
|
289 |
+
|
290 |
+
proving his or her case. In criminal cases, the government has the burden of proving
|
291 |
+
the
|
292 |
+
|
293 |
+
defendant''s guilt. (See standard of proof.)'
|
294 |
+
- 'residence (homestead exemption), or some or all "tools of the trade" used by
|
295 |
+
the debtor to
|
296 |
+
|
297 |
+
make a living (i.e., auto tools for an auto mechanic or dental tools for a dentist).
|
298 |
+
The
|
299 |
+
|
300 |
+
availability and amount of property the debtor may exempt depends on the state
|
301 |
+
the debtor
|
302 |
+
|
303 |
+
lives in.
|
304 |
+
|
305 |
+
F
|
306 |
+
|
307 |
+
Face sheet filing
|
308 |
+
|
309 |
+
A bankruptcy case filed either without schedules or with incomplete schedules
|
310 |
+
listing few
|
311 |
+
|
312 |
+
creditors and debts. (Face sheet filings are often made for the purpose of delaying
|
313 |
+
an'
|
314 |
+
- source_sentence: How does a fraudulent transfer relate to a debtor's intent in bankruptcy
|
315 |
+
cases?
|
316 |
+
sentences:
|
317 |
+
- 'Glossary of Legal Terms
|
318 |
+
|
319 |
+
Find definitions of legal terms to help understand the federal
|
320 |
+
|
321 |
+
court system.
|
322 |
+
|
323 |
+
A
|
324 |
+
|
325 |
+
Acquittal
|
326 |
+
|
327 |
+
A jury verdict that a criminal defendant is not guilty, or the finding of a judge
|
328 |
+
that the
|
329 |
+
|
330 |
+
evidence is insufficient to support a conviction.
|
331 |
+
|
332 |
+
Active judge
|
333 |
+
|
334 |
+
A judge in the full-time service of the court. Compare to senior judge.
|
335 |
+
|
336 |
+
Administrative Office of the United States Courts (AO)
|
337 |
+
|
338 |
+
Enter legal term to search for definition
|
339 |
+
|
340 |
+
Search'
|
341 |
+
- 'A serious crime, usually punishable by at least one year in prison.
|
342 |
+
|
343 |
+
File
|
344 |
+
|
345 |
+
To place a paper in the official custody of the clerk of court to enter into the
|
346 |
+
files or records
|
347 |
+
|
348 |
+
of a case.
|
349 |
+
|
350 |
+
Fraudulent transfer
|
351 |
+
|
352 |
+
A transfer of a debtor''s property made with intent to defraud or for which the
|
353 |
+
debtor
|
354 |
+
|
355 |
+
receives less than the transferred property''s value.
|
356 |
+
|
357 |
+
Fresh start
|
358 |
+
|
359 |
+
The characterization of a debtor''s status after bankruptcy, i.e., free of most
|
360 |
+
debts. (Giving
|
361 |
+
|
362 |
+
debtors a fresh start is one purpose of the Bankruptcy Code.)
|
363 |
+
|
364 |
+
G
|
365 |
+
|
366 |
+
Grand jury
|
367 |
+
|
368 |
+
A body of 16-23 citizens who listen to evidence of criminal allegations, which
|
369 |
+
is presented by
|
370 |
+
|
371 |
+
the prosecutors, and determine whether there is probable cause to believe an individual'
|
372 |
+
- '-3-
|
373 |
+
|
374 |
+
Argument: A reason given in proof or rebuttal to persuade a judge or jury.
|
375 |
+
|
376 |
+
At Issue: Whenever the parties to an action come to a point in the pleadings
|
377 |
+
or argument which
|
378 |
+
|
379 |
+
is affirmed on one side and denied on the other, the points are said to be "at
|
380 |
+
issue".
|
381 |
+
|
382 |
+
Attachment: The taking of property into legal custody by an enforcement officer
|
383 |
+
(See specialty
|
384 |
+
|
385 |
+
section: Recovery of Chattel).
|
386 |
+
|
387 |
+
Attestation: The act of witnessing an instrument in writing at the request of
|
388 |
+
the party making the
|
389 |
+
|
390 |
+
instrument and signing it as a witness.
|
391 |
+
|
392 |
+
Attorney of Record: Attorney whose name appears in the court’s records or files
|
393 |
+
of a case.
|
394 |
+
|
395 |
+
Award: A decision of an Arbitrator, judge or jury.
|
396 |
+
|
397 |
+
-B-'
|
398 |
+
pipeline_tag: sentence-similarity
|
399 |
+
library_name: sentence-transformers
|
400 |
+
metrics:
|
401 |
+
- cosine_accuracy@1
|
402 |
+
- cosine_accuracy@3
|
403 |
+
- cosine_accuracy@5
|
404 |
+
- cosine_accuracy@10
|
405 |
+
- cosine_precision@1
|
406 |
+
- cosine_precision@3
|
407 |
+
- cosine_precision@5
|
408 |
+
- cosine_precision@10
|
409 |
+
- cosine_recall@1
|
410 |
+
- cosine_recall@3
|
411 |
+
- cosine_recall@5
|
412 |
+
- cosine_recall@10
|
413 |
+
- cosine_ndcg@10
|
414 |
+
- cosine_mrr@10
|
415 |
+
- cosine_map@100
|
416 |
+
model-index:
|
417 |
+
- name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
|
418 |
+
results:
|
419 |
+
- task:
|
420 |
+
type: information-retrieval
|
421 |
+
name: Information Retrieval
|
422 |
+
dataset:
|
423 |
+
name: Unknown
|
424 |
+
type: unknown
|
425 |
+
metrics:
|
426 |
+
- type: cosine_accuracy@1
|
427 |
+
value: 0.9318181818181818
|
428 |
+
name: Cosine Accuracy@1
|
429 |
+
- type: cosine_accuracy@3
|
430 |
+
value: 0.9318181818181818
|
431 |
+
name: Cosine Accuracy@3
|
432 |
+
- type: cosine_accuracy@5
|
433 |
+
value: 0.9545454545454546
|
434 |
+
name: Cosine Accuracy@5
|
435 |
+
- type: cosine_accuracy@10
|
436 |
+
value: 1.0
|
437 |
+
name: Cosine Accuracy@10
|
438 |
+
- type: cosine_precision@1
|
439 |
+
value: 0.9318181818181818
|
440 |
+
name: Cosine Precision@1
|
441 |
+
- type: cosine_precision@3
|
442 |
+
value: 0.3106060606060606
|
443 |
+
name: Cosine Precision@3
|
444 |
+
- type: cosine_precision@5
|
445 |
+
value: 0.1909090909090909
|
446 |
+
name: Cosine Precision@5
|
447 |
+
- type: cosine_precision@10
|
448 |
+
value: 0.09999999999999996
|
449 |
+
name: Cosine Precision@10
|
450 |
+
- type: cosine_recall@1
|
451 |
+
value: 0.9318181818181818
|
452 |
+
name: Cosine Recall@1
|
453 |
+
- type: cosine_recall@3
|
454 |
+
value: 0.9318181818181818
|
455 |
+
name: Cosine Recall@3
|
456 |
+
- type: cosine_recall@5
|
457 |
+
value: 0.9545454545454546
|
458 |
+
name: Cosine Recall@5
|
459 |
+
- type: cosine_recall@10
|
460 |
+
value: 1.0
|
461 |
+
name: Cosine Recall@10
|
462 |
+
- type: cosine_ndcg@10
|
463 |
+
value: 0.9565434941101226
|
464 |
+
name: Cosine Ndcg@10
|
465 |
+
- type: cosine_mrr@10
|
466 |
+
value: 0.9438131313131314
|
467 |
+
name: Cosine Mrr@10
|
468 |
+
- type: cosine_map@100
|
469 |
+
value: 0.9438131313131314
|
470 |
+
name: Cosine Map@100
|
471 |
+
---
|
472 |
+
|
473 |
+
# SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
|
474 |
+
|
475 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l). It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
476 |
+
|
477 |
+
## Model Details
|
478 |
+
|
479 |
+
### Model Description
|
480 |
+
- **Model Type:** Sentence Transformer
|
481 |
+
- **Base model:** [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l) <!-- at revision d8fb21ca8d905d2832ee8b96c894d3298964346b -->
|
482 |
+
- **Maximum Sequence Length:** 512 tokens
|
483 |
+
- **Output Dimensionality:** 1024 dimensions
|
484 |
+
- **Similarity Function:** Cosine Similarity
|
485 |
+
<!-- - **Training Dataset:** Unknown -->
|
486 |
+
<!-- - **Language:** Unknown -->
|
487 |
+
<!-- - **License:** Unknown -->
|
488 |
+
|
489 |
+
### Model Sources
|
490 |
+
|
491 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
492 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
493 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
494 |
+
|
495 |
+
### Full Model Architecture
|
496 |
+
|
497 |
+
```
|
498 |
+
SentenceTransformer(
|
499 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
500 |
+
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
501 |
+
(2): Normalize()
|
502 |
+
)
|
503 |
+
```
|
504 |
+
|
505 |
+
## Usage
|
506 |
+
|
507 |
+
### Direct Usage (Sentence Transformers)
|
508 |
+
|
509 |
+
First install the Sentence Transformers library:
|
510 |
+
|
511 |
+
```bash
|
512 |
+
pip install -U sentence-transformers
|
513 |
+
```
|
514 |
+
|
515 |
+
Then you can load this model and run inference.
|
516 |
+
```python
|
517 |
+
from sentence_transformers import SentenceTransformer
|
518 |
+
|
519 |
+
# Download from the 🤗 Hub
|
520 |
+
model = SentenceTransformer("vin00d/snowflake-arctic-legal-ft-1")
|
521 |
+
# Run inference
|
522 |
+
sentences = [
|
523 |
+
"How does a fraudulent transfer relate to a debtor's intent in bankruptcy cases?",
|
524 |
+
"A serious crime, usually punishable by at least one year in prison.\nFile\nTo place a paper in the official custody of the clerk of court to enter into the files or records\nof a case.\nFraudulent transfer\nA transfer of a debtor's property made with intent to defraud or for which the debtor\nreceives less than the transferred property's value.\nFresh start\nThe characterization of a debtor's status after bankruptcy, i.e., free of most debts. (Giving\ndebtors a fresh start is one purpose of the Bankruptcy Code.)\nG\nGrand jury\nA body of 16-23 citizens who listen to evidence of criminal allegations, which is presented by\nthe prosecutors, and determine whether there is probable cause to believe an individual",
|
525 |
+
'-3-\nArgument: A reason given in proof or rebuttal to persuade a judge or jury.\nAt Issue: Whenever the parties to an action come to a point in the pleadings or argument which\nis affirmed on one side and denied on the other, the points are said to be "at issue".\nAttachment: The taking of property into legal custody by an enforcement officer (See specialty\nsection: Recovery of Chattel).\nAttestation: The act of witnessing an instrument in writing at the request of the party making the\ninstrument and signing it as a witness.\nAttorney of Record: Attorney whose name appears in the court’s records or files of a case.\nAward: A decision of an Arbitrator, judge or jury.\n-B-',
|
526 |
+
]
|
527 |
+
embeddings = model.encode(sentences)
|
528 |
+
print(embeddings.shape)
|
529 |
+
# [3, 1024]
|
530 |
+
|
531 |
+
# Get the similarity scores for the embeddings
|
532 |
+
similarities = model.similarity(embeddings, embeddings)
|
533 |
+
print(similarities.shape)
|
534 |
+
# [3, 3]
|
535 |
+
```
|
536 |
+
|
537 |
+
<!--
|
538 |
+
### Direct Usage (Transformers)
|
539 |
+
|
540 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
541 |
+
|
542 |
+
</details>
|
543 |
+
-->
|
544 |
+
|
545 |
+
<!--
|
546 |
+
### Downstream Usage (Sentence Transformers)
|
547 |
+
|
548 |
+
You can finetune this model on your own dataset.
|
549 |
+
|
550 |
+
<details><summary>Click to expand</summary>
|
551 |
+
|
552 |
+
</details>
|
553 |
+
-->
|
554 |
+
|
555 |
+
<!--
|
556 |
+
### Out-of-Scope Use
|
557 |
+
|
558 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
559 |
+
-->
|
560 |
+
|
561 |
+
## Evaluation
|
562 |
+
|
563 |
+
### Metrics
|
564 |
+
|
565 |
+
#### Information Retrieval
|
566 |
+
|
567 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
568 |
+
|
569 |
+
| Metric | Value |
|
570 |
+
|:--------------------|:-----------|
|
571 |
+
| cosine_accuracy@1 | 0.9318 |
|
572 |
+
| cosine_accuracy@3 | 0.9318 |
|
573 |
+
| cosine_accuracy@5 | 0.9545 |
|
574 |
+
| cosine_accuracy@10 | 1.0 |
|
575 |
+
| cosine_precision@1 | 0.9318 |
|
576 |
+
| cosine_precision@3 | 0.3106 |
|
577 |
+
| cosine_precision@5 | 0.1909 |
|
578 |
+
| cosine_precision@10 | 0.1 |
|
579 |
+
| cosine_recall@1 | 0.9318 |
|
580 |
+
| cosine_recall@3 | 0.9318 |
|
581 |
+
| cosine_recall@5 | 0.9545 |
|
582 |
+
| cosine_recall@10 | 1.0 |
|
583 |
+
| **cosine_ndcg@10** | **0.9565** |
|
584 |
+
| cosine_mrr@10 | 0.9438 |
|
585 |
+
| cosine_map@100 | 0.9438 |
|
586 |
+
|
587 |
+
<!--
|
588 |
+
## Bias, Risks and Limitations
|
589 |
+
|
590 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
591 |
+
-->
|
592 |
+
|
593 |
+
<!--
|
594 |
+
### Recommendations
|
595 |
+
|
596 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
597 |
+
-->
|
598 |
+
|
599 |
+
## Training Details
|
600 |
+
|
601 |
+
### Training Dataset
|
602 |
+
|
603 |
+
#### Unnamed Dataset
|
604 |
+
|
605 |
+
* Size: 210 training samples
|
606 |
+
* Columns: <code>sentence_0</code> and <code>sentence_1</code>
|
607 |
+
* Approximate statistics based on the first 210 samples:
|
608 |
+
| | sentence_0 | sentence_1 |
|
609 |
+
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
610 |
+
| type | string | string |
|
611 |
+
| details | <ul><li>min: 9 tokens</li><li>mean: 17.36 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 122.9 tokens</li><li>max: 192 tokens</li></ul> |
|
612 |
+
* Samples:
|
613 |
+
| sentence_0 | sentence_1 |
|
614 |
+
|:---------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
615 |
+
| <code>What is the purpose of the glossary of common legal terms provided in the context? </code> | <code>GLOSSARY ‐ COMMON LEGAL TERMS<br>NOTE: The following definitions are not legal definitions. Rather, these definitions are<br>intended to give you a general idea of the meanings of common legal words. For <br>comprehensive Definitions of legal terms, you may wish to consult a legal dictionary<br> “Black’s Law Dictionary” is one such legal dictionary which is usually available at<br> most law libraries.<br>This glossary of common legal terms is also available on‐line at:<br>http://www.nycourts.gov/lawlibraries/glossary.shtml<br> <br>ADDITIONAL ON‐LINE RESOURCES:<br>http://www.nolo.com/glossary.cfm <br>Nolo’s on‐line legal dictionary.<br>http://www.law‐dictionary.org/<br>Free on‐line legal dictionary search engine.<br>http://www.law.cornell.edu/wex</code> |
|
616 |
+
| <code>Where can one find a comprehensive legal dictionary for more detailed definitions of legal terms?</code> | <code>GLOSSARY ‐ COMMON LEGAL TERMS<br>NOTE: The following definitions are not legal definitions. Rather, these definitions are<br>intended to give you a general idea of the meanings of common legal words. For <br>comprehensive Definitions of legal terms, you may wish to consult a legal dictionary<br> “Black’s Law Dictionary” is one such legal dictionary which is usually available at<br> most law libraries.<br>This glossary of common legal terms is also available on‐line at:<br>http://www.nycourts.gov/lawlibraries/glossary.shtml<br> <br>ADDITIONAL ON‐LINE RESOURCES:<br>http://www.nolo.com/glossary.cfm <br>Nolo’s on‐line legal dictionary.<br>http://www.law‐dictionary.org/<br>Free on‐line legal dictionary search engine.<br>http://www.law.cornell.edu/wex</code> |
|
617 |
+
| <code>What organization maintains the legal dictionary and encyclopedia mentioned in the context? </code> | <code>Legal dictionary and encyclopedia maintained by the<br>Legal Information Institute at Cornell Law School.</code> |
|
618 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
619 |
+
```json
|
620 |
+
{
|
621 |
+
"loss": "MultipleNegativesRankingLoss",
|
622 |
+
"matryoshka_dims": [
|
623 |
+
768,
|
624 |
+
512,
|
625 |
+
256,
|
626 |
+
128,
|
627 |
+
64
|
628 |
+
],
|
629 |
+
"matryoshka_weights": [
|
630 |
+
1,
|
631 |
+
1,
|
632 |
+
1,
|
633 |
+
1,
|
634 |
+
1
|
635 |
+
],
|
636 |
+
"n_dims_per_step": -1
|
637 |
+
}
|
638 |
+
```
|
639 |
+
|
640 |
+
### Training Hyperparameters
|
641 |
+
#### Non-Default Hyperparameters
|
642 |
+
|
643 |
+
- `eval_strategy`: steps
|
644 |
+
- `per_device_train_batch_size`: 10
|
645 |
+
- `per_device_eval_batch_size`: 10
|
646 |
+
- `num_train_epochs`: 10
|
647 |
+
- `multi_dataset_batch_sampler`: round_robin
|
648 |
+
|
649 |
+
#### All Hyperparameters
|
650 |
+
<details><summary>Click to expand</summary>
|
651 |
+
|
652 |
+
- `overwrite_output_dir`: False
|
653 |
+
- `do_predict`: False
|
654 |
+
- `eval_strategy`: steps
|
655 |
+
- `prediction_loss_only`: True
|
656 |
+
- `per_device_train_batch_size`: 10
|
657 |
+
- `per_device_eval_batch_size`: 10
|
658 |
+
- `per_gpu_train_batch_size`: None
|
659 |
+
- `per_gpu_eval_batch_size`: None
|
660 |
+
- `gradient_accumulation_steps`: 1
|
661 |
+
- `eval_accumulation_steps`: None
|
662 |
+
- `torch_empty_cache_steps`: None
|
663 |
+
- `learning_rate`: 5e-05
|
664 |
+
- `weight_decay`: 0.0
|
665 |
+
- `adam_beta1`: 0.9
|
666 |
+
- `adam_beta2`: 0.999
|
667 |
+
- `adam_epsilon`: 1e-08
|
668 |
+
- `max_grad_norm`: 1
|
669 |
+
- `num_train_epochs`: 10
|
670 |
+
- `max_steps`: -1
|
671 |
+
- `lr_scheduler_type`: linear
|
672 |
+
- `lr_scheduler_kwargs`: {}
|
673 |
+
- `warmup_ratio`: 0.0
|
674 |
+
- `warmup_steps`: 0
|
675 |
+
- `log_level`: passive
|
676 |
+
- `log_level_replica`: warning
|
677 |
+
- `log_on_each_node`: True
|
678 |
+
- `logging_nan_inf_filter`: True
|
679 |
+
- `save_safetensors`: True
|
680 |
+
- `save_on_each_node`: False
|
681 |
+
- `save_only_model`: False
|
682 |
+
- `restore_callback_states_from_checkpoint`: False
|
683 |
+
- `no_cuda`: False
|
684 |
+
- `use_cpu`: False
|
685 |
+
- `use_mps_device`: False
|
686 |
+
- `seed`: 42
|
687 |
+
- `data_seed`: None
|
688 |
+
- `jit_mode_eval`: False
|
689 |
+
- `use_ipex`: False
|
690 |
+
- `bf16`: False
|
691 |
+
- `fp16`: False
|
692 |
+
- `fp16_opt_level`: O1
|
693 |
+
- `half_precision_backend`: auto
|
694 |
+
- `bf16_full_eval`: False
|
695 |
+
- `fp16_full_eval`: False
|
696 |
+
- `tf32`: None
|
697 |
+
- `local_rank`: 0
|
698 |
+
- `ddp_backend`: None
|
699 |
+
- `tpu_num_cores`: None
|
700 |
+
- `tpu_metrics_debug`: False
|
701 |
+
- `debug`: []
|
702 |
+
- `dataloader_drop_last`: False
|
703 |
+
- `dataloader_num_workers`: 0
|
704 |
+
- `dataloader_prefetch_factor`: None
|
705 |
+
- `past_index`: -1
|
706 |
+
- `disable_tqdm`: False
|
707 |
+
- `remove_unused_columns`: True
|
708 |
+
- `label_names`: None
|
709 |
+
- `load_best_model_at_end`: False
|
710 |
+
- `ignore_data_skip`: False
|
711 |
+
- `fsdp`: []
|
712 |
+
- `fsdp_min_num_params`: 0
|
713 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
714 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
715 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
716 |
+
- `deepspeed`: None
|
717 |
+
- `label_smoothing_factor`: 0.0
|
718 |
+
- `optim`: adamw_torch
|
719 |
+
- `optim_args`: None
|
720 |
+
- `adafactor`: False
|
721 |
+
- `group_by_length`: False
|
722 |
+
- `length_column_name`: length
|
723 |
+
- `ddp_find_unused_parameters`: None
|
724 |
+
- `ddp_bucket_cap_mb`: None
|
725 |
+
- `ddp_broadcast_buffers`: False
|
726 |
+
- `dataloader_pin_memory`: True
|
727 |
+
- `dataloader_persistent_workers`: False
|
728 |
+
- `skip_memory_metrics`: True
|
729 |
+
- `use_legacy_prediction_loop`: False
|
730 |
+
- `push_to_hub`: False
|
731 |
+
- `resume_from_checkpoint`: None
|
732 |
+
- `hub_model_id`: None
|
733 |
+
- `hub_strategy`: every_save
|
734 |
+
- `hub_private_repo`: None
|
735 |
+
- `hub_always_push`: False
|
736 |
+
- `gradient_checkpointing`: False
|
737 |
+
- `gradient_checkpointing_kwargs`: None
|
738 |
+
- `include_inputs_for_metrics`: False
|
739 |
+
- `include_for_metrics`: []
|
740 |
+
- `eval_do_concat_batches`: True
|
741 |
+
- `fp16_backend`: auto
|
742 |
+
- `push_to_hub_model_id`: None
|
743 |
+
- `push_to_hub_organization`: None
|
744 |
+
- `mp_parameters`:
|
745 |
+
- `auto_find_batch_size`: False
|
746 |
+
- `full_determinism`: False
|
747 |
+
- `torchdynamo`: None
|
748 |
+
- `ray_scope`: last
|
749 |
+
- `ddp_timeout`: 1800
|
750 |
+
- `torch_compile`: False
|
751 |
+
- `torch_compile_backend`: None
|
752 |
+
- `torch_compile_mode`: None
|
753 |
+
- `dispatch_batches`: None
|
754 |
+
- `split_batches`: None
|
755 |
+
- `include_tokens_per_second`: False
|
756 |
+
- `include_num_input_tokens_seen`: False
|
757 |
+
- `neftune_noise_alpha`: None
|
758 |
+
- `optim_target_modules`: None
|
759 |
+
- `batch_eval_metrics`: False
|
760 |
+
- `eval_on_start`: False
|
761 |
+
- `use_liger_kernel`: False
|
762 |
+
- `eval_use_gather_object`: False
|
763 |
+
- `average_tokens_across_devices`: False
|
764 |
+
- `prompts`: None
|
765 |
+
- `batch_sampler`: batch_sampler
|
766 |
+
- `multi_dataset_batch_sampler`: round_robin
|
767 |
+
|
768 |
+
</details>
|
769 |
+
|
770 |
+
### Training Logs
|
771 |
+
| Epoch | Step | cosine_ndcg@10 |
|
772 |
+
|:------:|:----:|:--------------:|
|
773 |
+
| 1.0 | 21 | 0.9240 |
|
774 |
+
| 2.0 | 42 | 0.9628 |
|
775 |
+
| 2.3810 | 50 | 0.9628 |
|
776 |
+
| 3.0 | 63 | 0.9502 |
|
777 |
+
| 4.0 | 84 | 0.9569 |
|
778 |
+
| 4.7619 | 100 | 0.9563 |
|
779 |
+
| 5.0 | 105 | 0.9556 |
|
780 |
+
| 6.0 | 126 | 0.9569 |
|
781 |
+
| 7.0 | 147 | 0.9555 |
|
782 |
+
| 7.1429 | 150 | 0.9555 |
|
783 |
+
| 8.0 | 168 | 0.9565 |
|
784 |
+
| 9.0 | 189 | 0.9565 |
|
785 |
+
| 9.5238 | 200 | 0.9565 |
|
786 |
+
| 10.0 | 210 | 0.9565 |
|
787 |
+
|
788 |
+
|
789 |
+
### Framework Versions
|
790 |
+
- Python: 3.11.11
|
791 |
+
- Sentence Transformers: 3.4.1
|
792 |
+
- Transformers: 4.48.3
|
793 |
+
- PyTorch: 2.5.1+cu124
|
794 |
+
- Accelerate: 1.3.0
|
795 |
+
- Datasets: 3.3.2
|
796 |
+
- Tokenizers: 0.21.0
|
797 |
+
|
798 |
+
## Citation
|
799 |
+
|
800 |
+
### BibTeX
|
801 |
+
|
802 |
+
#### Sentence Transformers
|
803 |
+
```bibtex
|
804 |
+
@inproceedings{reimers-2019-sentence-bert,
|
805 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
806 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
807 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
808 |
+
month = "11",
|
809 |
+
year = "2019",
|
810 |
+
publisher = "Association for Computational Linguistics",
|
811 |
+
url = "https://arxiv.org/abs/1908.10084",
|
812 |
+
}
|
813 |
+
```
|
814 |
+
|
815 |
+
#### MatryoshkaLoss
|
816 |
+
```bibtex
|
817 |
+
@misc{kusupati2024matryoshka,
|
818 |
+
title={Matryoshka Representation Learning},
|
819 |
+
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
|
820 |
+
year={2024},
|
821 |
+
eprint={2205.13147},
|
822 |
+
archivePrefix={arXiv},
|
823 |
+
primaryClass={cs.LG}
|
824 |
+
}
|
825 |
+
```
|
826 |
+
|
827 |
+
#### MultipleNegativesRankingLoss
|
828 |
+
```bibtex
|
829 |
+
@misc{henderson2017efficient,
|
830 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
831 |
+
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},
|
832 |
+
year={2017},
|
833 |
+
eprint={1705.00652},
|
834 |
+
archivePrefix={arXiv},
|
835 |
+
primaryClass={cs.CL}
|
836 |
+
}
|
837 |
+
```
|
838 |
+
|
839 |
+
<!--
|
840 |
+
## Glossary
|
841 |
+
|
842 |
+
*Clearly define terms in order to be accessible across audiences.*
|
843 |
+
-->
|
844 |
+
|
845 |
+
<!--
|
846 |
+
## Model Card Authors
|
847 |
+
|
848 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
849 |
+
-->
|
850 |
+
|
851 |
+
<!--
|
852 |
+
## Model Card Contact
|
853 |
+
|
854 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
855 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Snowflake/snowflake-arctic-embed-l",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4096,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.48.3",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.4.1",
|
4 |
+
"transformers": "4.48.3",
|
5 |
+
"pytorch": "2.5.1+cu124"
|
6 |
+
},
|
7 |
+
"prompts": {
|
8 |
+
"query": "Represent this sentence for searching relevant passages: "
|
9 |
+
},
|
10 |
+
"default_prompt_name": null,
|
11 |
+
"similarity_fn_name": "cosine"
|
12 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1555b48c1bf42a197ec1d33b0f0f5da39f4ad202b3a5a5372cabf87f6d845c18
|
3 |
+
size 1336413848
|
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_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
+
}
|
20 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_lower_case": true,
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_to_multiple_of": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"pad_token_type_id": 0,
|
54 |
+
"padding_side": "right",
|
55 |
+
"sep_token": "[SEP]",
|
56 |
+
"stride": 0,
|
57 |
+
"strip_accents": null,
|
58 |
+
"tokenize_chinese_chars": true,
|
59 |
+
"tokenizer_class": "BertTokenizer",
|
60 |
+
"truncation_side": "right",
|
61 |
+
"truncation_strategy": "longest_first",
|
62 |
+
"unk_token": "[UNK]"
|
63 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|