DrishtiSharma
commited on
Commit
•
73b4039
1
Parent(s):
a3efd1e
Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +721 -0
- config.json +31 -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 +57 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 384,
|
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 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- sentence-transformers
|
4 |
+
- sentence-similarity
|
5 |
+
- feature-extraction
|
6 |
+
- generated_from_trainer
|
7 |
+
- dataset_size:22291
|
8 |
+
- loss:MultipleNegativesRankingLoss
|
9 |
+
base_model: BAAI/bge-small-en
|
10 |
+
widget:
|
11 |
+
- source_sentence: What rights and obligations does an Authorised Person have if a
|
12 |
+
storage facility holding Accepted Spot Commodities becomes insolvent?
|
13 |
+
sentences:
|
14 |
+
- "MTF (using Virtual Assets): using third-party issued fiat tokens as a payment/transaction\
|
15 |
+
\ mechanism:\n\ni.\tIn the context of using third party fiat tokens, the Authorised\
|
16 |
+
\ Person must directly meet the requirements of the Accepted Virtual Assets, Technology\
|
17 |
+
\ Governance and AML/CFT sections of this Guidance.\n\nii.\tFor the related fiat\
|
18 |
+
\ currency custody activities, FSRA preference is to have the MTF utilise a Virtual\
|
19 |
+
\ Asset/Fiat Custodian authorised on the basis of paragraphs 139 - 145 or 166(b)\
|
20 |
+
\ above.\n\niii.\tIn relation to the issuance of the related fiat token, in circumstances\
|
21 |
+
\ where the issuer is not authorised under paragraph 166(a) above, it is expected\
|
22 |
+
\ that the Authorised Person undertake the same due diligence as that it would\
|
23 |
+
\ apply for the purposes of determining Accepted Virtual Assets (focusing on Technology\
|
24 |
+
\ Governance requirements, the seven factors used to determine an Accepted Virtual\
|
25 |
+
\ Asset, and requirements relating to reporting and reconciliation).\n"
|
26 |
+
- 'Valuation adjustments. The Regulator expects the following valuation adjustments
|
27 |
+
to be formally considered at a minimum: unearned credit spreads, close out costs,
|
28 |
+
Operational Risks, early termination, investing and funding costs, and future
|
29 |
+
administrative costs and, where appropriate, model risk.
|
30 |
+
|
31 |
+
'
|
32 |
+
- "Storage Facilities. An Authorised Person must have arrangements in place for\
|
33 |
+
\ the approval, management, monitoring and control for Accepted Spot Commodities\
|
34 |
+
\ and the storage facilities operated by itself or by third parties, including\
|
35 |
+
\ in relation to:\n(a)\tsecurity arrangements;\n(b)\tperiodic stock reports;\n\
|
36 |
+
(c)\tperiodic inventory audits;\n(d)\tdispute resolution procedures where the\
|
37 |
+
\ storage facility materially fails to meet any of its obligations to the title\
|
38 |
+
\ holder;\n(e)\tstorage or other fees; and\n(f)\trights and obligations in the\
|
39 |
+
\ event of storage facility insolvency, as per the rules, terms, conditions and\
|
40 |
+
\ other obligations of the Authorised Person."
|
41 |
+
- source_sentence: Regarding GEN Rule 3.3, can you provide examples of what constitutes
|
42 |
+
effective and responsible management of an Authorised Person's affairs in the
|
43 |
+
context of Virtual Assets?
|
44 |
+
sentences:
|
45 |
+
- 'REGULATORY REQUIREMENTS - SPOT COMMODITY ACTIVITIES
|
46 |
+
|
47 |
+
Custody
|
48 |
+
|
49 |
+
Due to their psychical nature, Spot Commodities may require specialist Custody
|
50 |
+
arrangements, with the holding of Accepted Spot Commodities introducing additional
|
51 |
+
operational risks. For example, the safekeeping of gold bullion would require
|
52 |
+
a custodian with appropriate secure vault facilities.
|
53 |
+
|
54 |
+
'
|
55 |
+
- "Measurement of E for pre settlement Counterparty Exposures arising from SFTs.\
|
56 |
+
\ An Authorised Person must determine E, for a pre settlement Counterparty Exposure\
|
57 |
+
\ arising from an SFT which is not covered by a qualifying cross product Netting\
|
58 |
+
\ agreement as follows:\n(a)\tin the case where the Authorised Person has lent\
|
59 |
+
\ Securities to a Counterparty or sold Securities to a Counterparty with a commitment\
|
60 |
+
\ to repurchase those Securities at a specified price on a specified future date,\
|
61 |
+
\ the latest fair value of the Securities lent or sold; and\n(b)\tin the case\
|
62 |
+
\ where the Authorised Person has lent cash to a Counterparty through the borrowing\
|
63 |
+
\ of Securities from the Counterparty or paid cash for the purchase of Securities\
|
64 |
+
\ from a Counterparty with a commitment to resell those Securities at a specified\
|
65 |
+
\ price on a specified future date, the amount of cash lent or paid."
|
66 |
+
- "The base figure for the size factor component is determined by aggregating the\
|
67 |
+
\ following components, for the Long Term Insurance Fund:\n(a)\tthe default risk\
|
68 |
+
\ components determined in accordance with Rule A8.4;\n(b)\tthe investment volatility\
|
69 |
+
\ risk component determined in accordance with Rule A8.5; and\n(c)\tthe concentration\
|
70 |
+
\ risk component determined in accordance with Rule A8.8."
|
71 |
+
- source_sentence: In the case of non-compliance with Part 17 of FSMR, what are the
|
72 |
+
typical steps or actions the ADGM might take against an authorised firm?
|
73 |
+
sentences:
|
74 |
+
- 'The Regulatory Authority shall, within thirty (30) days of the date of the notification
|
75 |
+
mentioned in subparagraph (2), notify the Account Holder or the Controlling Person
|
76 |
+
of the violation, the amount of the fine and the payment request of the fine within
|
77 |
+
no later than thirty (30) days from receipt of the notice.
|
78 |
+
|
79 |
+
'
|
80 |
+
- "When employing an eKYC System to assist with CDD, a Relevant Person should:\n\
|
81 |
+
a.\tensure that it has a thorough understanding of the eKYC System itself and\
|
82 |
+
\ the risks of eKYC, including those outlined by relevant guidance from FATF and\
|
83 |
+
\ other international standard setting bodies;\nb.\tcomply with all the Rules\
|
84 |
+
\ of the Regulator relevant to eKYC including, but not limited to, applicable\
|
85 |
+
\ requirements regarding the business risk assessment, as per Rule 6.1, and outsourcing,\
|
86 |
+
\ as per Rule 9.3;\nc.\tcombine eKYC with transaction monitoring, anti-fraud\
|
87 |
+
\ and cyber-security measures to support a wider framework preventing applicable\
|
88 |
+
\ Financial Crime; and\nd.\ttake appropriate steps to identify, assess and mitigate\
|
89 |
+
\ the risk of the eKYC system being misused for the purposes of Financial Crime."
|
90 |
+
- This Chapter deals with the regulatory requirements arising out of the need for
|
91 |
+
Authorised Persons to carry out a self assessment of their risk which can be reviewed
|
92 |
+
and assessed by the Regulator. This Chapter details the Rules stipulating the
|
93 |
+
need to complete internal risk assessments by Authorised Persons in defined frequencies
|
94 |
+
and the Regulator's role in reviewing the results of such assessments. In the
|
95 |
+
case of Authorised Persons facing financial risks, the requirements in this Chapter
|
96 |
+
mandate completion of an Internal Capital Adequacy Assessment Process. The Regulator
|
97 |
+
will review the results of such internal risk assessments. This Chapter also sets
|
98 |
+
out how the Regulator may impose an additional Capital Requirement on a firm specific
|
99 |
+
basis in addition to the minimum requirement specified in Chapter 3 of these Rules
|
100 |
+
to address higher-than-normal risk.
|
101 |
+
- source_sentence: In terms of basis risk, are there any preferred methods or models
|
102 |
+
that the ADGM recommends for assessing the impact of divergences in market rates,
|
103 |
+
such as the prime rate versus deposit and benchmark rates?
|
104 |
+
sentences:
|
105 |
+
- "In performing its functions and exercising its powers, the Regulator shall pursue\
|
106 |
+
\ the following objectives—\n(a)\tto foster and maintain fairness, transparency\
|
107 |
+
\ and efficiency in the Abu Dhabi Global Market;\n(b)\tto foster and maintain\
|
108 |
+
\ confidence in the Abu Dhabi Global Market;\n(c)\tto ensure that the financial\
|
109 |
+
\ markets in the Abu Dhabi Global Market are supported by safe and efficient infrastructure;\n\
|
110 |
+
(d)\tto foster and maintain financial stability in the Abu Dhabi Global Market,\
|
111 |
+
\ including the reduction of systemic risk;\n(e)\tto promote and enhance the integrity\
|
112 |
+
\ of the Abu Dhabi Global Market Financial System;\n(f)\tto prevent, detect and\
|
113 |
+
\ restrain conduct that causes or may cause damage to the reputation of the Abu\
|
114 |
+
\ Dhabi Global Market through appropriate means including the imposition of sanctions;\n\
|
115 |
+
(g)\tto secure an appropriate degree of protection for direct and indirect users,\
|
116 |
+
\ and prospective users of the Abu Dhabi Global Market;\n(h)\tto promote public\
|
117 |
+
\ understanding of the regulation of the Abu Dhabi Global Market;\n(i)\tto further\
|
118 |
+
\ the interests of the Abu Dhabi Global Market;\n(j)\tto promote the safety and\
|
119 |
+
\ soundness of Authorised Persons and Recognised Bodies; and\n(k)\tto pursue any\
|
120 |
+
\ other objectives as the Board may set."
|
121 |
+
- Two-year validity period. During the two-year validity period, the Regulator will
|
122 |
+
engage with and support the FinTech Participant and ensure the FinTech Participant
|
123 |
+
operates within the parameters as set and agreed to prior to the grant of the
|
124 |
+
FSP.
|
125 |
+
- "Without limiting compliance with Rules 6.1.1 and 6.1.2, prior to launching\
|
126 |
+
\ any new product, service, or business practice, or using a new or developing\
|
127 |
+
\ technology, a Relevant Person must take reasonable steps to ensure that it has:\n\
|
128 |
+
(a)\tassessed and identified the money laundering risks relating to the product,\
|
129 |
+
\ service, business practice or technology; and\n(b)\ttaken appropriate steps\
|
130 |
+
\ to mitigate or eliminate the risks identified under (a)."
|
131 |
+
- source_sentence: How should an Authorised Person document and justify any deviations
|
132 |
+
when mapping activities into business lines for Operational Risk capital purposes,
|
133 |
+
particularly when they differ from regulatory capital calculations in other risk
|
134 |
+
categories?
|
135 |
+
sentences:
|
136 |
+
- "For the purposes of 8.1.2(1), in determining when it is appropriate to apply\
|
137 |
+
\ CDD measures in relation to existing customers, a Relevant Person must take\
|
138 |
+
\ into account, amongst other things:\n(a)\tany indication that the identity of\
|
139 |
+
\ the customer, or the customer’s Beneficial Owners, has changed;\n(b)\tany Transactions\
|
140 |
+
\ that are not reasonably consistent with the Relevant Person’s knowledge of the\
|
141 |
+
\ customer;\n(c)\tany change in the purpose or intended nature of the Relevant\
|
142 |
+
\ Person’s relationship with the customer; or\n(d)\tany other matter that might\
|
143 |
+
\ affect the Relevant Person’s risk assessment of the customer."
|
144 |
+
- Principles for business line mapping. The mapping of activities into business
|
145 |
+
lines for Operational Risk capital purposes should be consistent with the definitions
|
146 |
+
of business lines used for regulatory capital calculations in other risk categories,
|
147 |
+
i.e. credit and Market Risk. Any deviations from this principle should be clearly
|
148 |
+
motivated and documented.
|
149 |
+
- 'REGULATORY REQUIREMENTS FOR AUTHORISED PERSONS ENGAGED IN REGULATED ACTIVITIES
|
150 |
+
IN RELATION TO VIRTUAL ASSETS
|
151 |
+
|
152 |
+
Planned and Unplanned system outages
|
153 |
+
|
154 |
+
Authorised Persons should have a programme of planned systems outages to provide
|
155 |
+
for adequate opportunities to perform updates and testing. Authorised Persons
|
156 |
+
should also have multiple communication channels to ensure that its Clients are
|
157 |
+
informed, ahead of time, of any outages which may affect them.
|
158 |
+
|
159 |
+
'
|
160 |
+
pipeline_tag: sentence-similarity
|
161 |
+
library_name: sentence-transformers
|
162 |
+
metrics:
|
163 |
+
- cosine_accuracy@1
|
164 |
+
- cosine_accuracy@3
|
165 |
+
- cosine_accuracy@5
|
166 |
+
- cosine_accuracy@10
|
167 |
+
- cosine_precision@1
|
168 |
+
- cosine_precision@3
|
169 |
+
- cosine_precision@5
|
170 |
+
- cosine_precision@10
|
171 |
+
- cosine_recall@1
|
172 |
+
- cosine_recall@3
|
173 |
+
- cosine_recall@5
|
174 |
+
- cosine_recall@10
|
175 |
+
- cosine_ndcg@10
|
176 |
+
- cosine_mrr@10
|
177 |
+
- cosine_map@100
|
178 |
+
- dot_accuracy@1
|
179 |
+
- dot_accuracy@3
|
180 |
+
- dot_accuracy@5
|
181 |
+
- dot_accuracy@10
|
182 |
+
- dot_precision@1
|
183 |
+
- dot_precision@3
|
184 |
+
- dot_precision@5
|
185 |
+
- dot_precision@10
|
186 |
+
- dot_recall@1
|
187 |
+
- dot_recall@3
|
188 |
+
- dot_recall@5
|
189 |
+
- dot_recall@10
|
190 |
+
- dot_ndcg@10
|
191 |
+
- dot_mrr@10
|
192 |
+
- dot_map@100
|
193 |
+
model-index:
|
194 |
+
- name: SentenceTransformer based on BAAI/bge-small-en
|
195 |
+
results:
|
196 |
+
- task:
|
197 |
+
type: information-retrieval
|
198 |
+
name: Information Retrieval
|
199 |
+
dataset:
|
200 |
+
name: Unknown
|
201 |
+
type: unknown
|
202 |
+
metrics:
|
203 |
+
- type: cosine_accuracy@1
|
204 |
+
value: 0.6255380200860832
|
205 |
+
name: Cosine Accuracy@1
|
206 |
+
- type: cosine_accuracy@3
|
207 |
+
value: 0.7517934002869441
|
208 |
+
name: Cosine Accuracy@3
|
209 |
+
- type: cosine_accuracy@5
|
210 |
+
value: 0.793400286944046
|
211 |
+
name: Cosine Accuracy@5
|
212 |
+
- type: cosine_accuracy@10
|
213 |
+
value: 0.8368005738880918
|
214 |
+
name: Cosine Accuracy@10
|
215 |
+
- type: cosine_precision@1
|
216 |
+
value: 0.6255380200860832
|
217 |
+
name: Cosine Precision@1
|
218 |
+
- type: cosine_precision@3
|
219 |
+
value: 0.26410808225729315
|
220 |
+
name: Cosine Precision@3
|
221 |
+
- type: cosine_precision@5
|
222 |
+
value: 0.1703012912482066
|
223 |
+
name: Cosine Precision@5
|
224 |
+
- type: cosine_precision@10
|
225 |
+
value: 0.09314921090387374
|
226 |
+
name: Cosine Precision@10
|
227 |
+
- type: cosine_recall@1
|
228 |
+
value: 0.5488103778096605
|
229 |
+
name: Cosine Recall@1
|
230 |
+
- type: cosine_recall@3
|
231 |
+
value: 0.670468675274988
|
232 |
+
name: Cosine Recall@3
|
233 |
+
- type: cosine_recall@5
|
234 |
+
value: 0.7117168818747011
|
235 |
+
name: Cosine Recall@5
|
236 |
+
- type: cosine_recall@10
|
237 |
+
value: 0.7628347680535629
|
238 |
+
name: Cosine Recall@10
|
239 |
+
- type: cosine_ndcg@10
|
240 |
+
value: 0.6800021713111875
|
241 |
+
name: Cosine Ndcg@10
|
242 |
+
- type: cosine_mrr@10
|
243 |
+
value: 0.6975649609437263
|
244 |
+
name: Cosine Mrr@10
|
245 |
+
- type: cosine_map@100
|
246 |
+
value: 0.6393436933673565
|
247 |
+
name: Cosine Map@100
|
248 |
+
- type: dot_accuracy@1
|
249 |
+
value: 0.6255380200860832
|
250 |
+
name: Dot Accuracy@1
|
251 |
+
- type: dot_accuracy@3
|
252 |
+
value: 0.7517934002869441
|
253 |
+
name: Dot Accuracy@3
|
254 |
+
- type: dot_accuracy@5
|
255 |
+
value: 0.793400286944046
|
256 |
+
name: Dot Accuracy@5
|
257 |
+
- type: dot_accuracy@10
|
258 |
+
value: 0.8368005738880918
|
259 |
+
name: Dot Accuracy@10
|
260 |
+
- type: dot_precision@1
|
261 |
+
value: 0.6255380200860832
|
262 |
+
name: Dot Precision@1
|
263 |
+
- type: dot_precision@3
|
264 |
+
value: 0.26410808225729315
|
265 |
+
name: Dot Precision@3
|
266 |
+
- type: dot_precision@5
|
267 |
+
value: 0.1703012912482066
|
268 |
+
name: Dot Precision@5
|
269 |
+
- type: dot_precision@10
|
270 |
+
value: 0.09314921090387374
|
271 |
+
name: Dot Precision@10
|
272 |
+
- type: dot_recall@1
|
273 |
+
value: 0.5488103778096605
|
274 |
+
name: Dot Recall@1
|
275 |
+
- type: dot_recall@3
|
276 |
+
value: 0.670468675274988
|
277 |
+
name: Dot Recall@3
|
278 |
+
- type: dot_recall@5
|
279 |
+
value: 0.7117168818747011
|
280 |
+
name: Dot Recall@5
|
281 |
+
- type: dot_recall@10
|
282 |
+
value: 0.7628347680535629
|
283 |
+
name: Dot Recall@10
|
284 |
+
- type: dot_ndcg@10
|
285 |
+
value: 0.6800021713111875
|
286 |
+
name: Dot Ndcg@10
|
287 |
+
- type: dot_mrr@10
|
288 |
+
value: 0.6975649609437263
|
289 |
+
name: Dot Mrr@10
|
290 |
+
- type: dot_map@100
|
291 |
+
value: 0.6393436933673565
|
292 |
+
name: Dot Map@100
|
293 |
+
---
|
294 |
+
|
295 |
+
# SentenceTransformer based on BAAI/bge-small-en
|
296 |
+
|
297 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
298 |
+
|
299 |
+
## Model Details
|
300 |
+
|
301 |
+
### Model Description
|
302 |
+
- **Model Type:** Sentence Transformer
|
303 |
+
- **Base model:** [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) <!-- at revision 2275a7bdee235e9b4f01fa73aa60d3311983cfea -->
|
304 |
+
- **Maximum Sequence Length:** 512 tokens
|
305 |
+
- **Output Dimensionality:** 384 tokens
|
306 |
+
- **Similarity Function:** Cosine Similarity
|
307 |
+
<!-- - **Training Dataset:** Unknown -->
|
308 |
+
<!-- - **Language:** Unknown -->
|
309 |
+
<!-- - **License:** Unknown -->
|
310 |
+
|
311 |
+
### Model Sources
|
312 |
+
|
313 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
314 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
315 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
316 |
+
|
317 |
+
### Full Model Architecture
|
318 |
+
|
319 |
+
```
|
320 |
+
SentenceTransformer(
|
321 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel
|
322 |
+
(1): Pooling({'word_embedding_dimension': 384, '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})
|
323 |
+
(2): Normalize()
|
324 |
+
)
|
325 |
+
```
|
326 |
+
|
327 |
+
## Usage
|
328 |
+
|
329 |
+
### Direct Usage (Sentence Transformers)
|
330 |
+
|
331 |
+
First install the Sentence Transformers library:
|
332 |
+
|
333 |
+
```bash
|
334 |
+
pip install -U sentence-transformers
|
335 |
+
```
|
336 |
+
|
337 |
+
Then you can load this model and run inference.
|
338 |
+
```python
|
339 |
+
from sentence_transformers import SentenceTransformer
|
340 |
+
|
341 |
+
# Download from the 🤗 Hub
|
342 |
+
model = SentenceTransformer("DrishtiSharma/bge-small-en-obliqa-5-epochs")
|
343 |
+
# Run inference
|
344 |
+
sentences = [
|
345 |
+
'How should an Authorised Person document and justify any deviations when mapping activities into business lines for Operational Risk capital purposes, particularly when they differ from regulatory capital calculations in other risk categories?',
|
346 |
+
'Principles for business line mapping. The mapping of activities into business lines for Operational Risk capital purposes should be consistent with the definitions of business lines used for regulatory capital calculations in other risk categories, i.e. credit and Market Risk. Any deviations from this principle should be clearly motivated and documented.',
|
347 |
+
'REGULATORY REQUIREMENTS FOR AUTHORISED PERSONS ENGAGED IN REGULATED ACTIVITIES IN RELATION TO VIRTUAL ASSETS\nPlanned and Unplanned system outages\nAuthorised Persons should have a programme of planned systems outages to provide for adequate opportunities to perform updates and testing. Authorised Persons should also have multiple communication channels to ensure that its Clients are informed, ahead of time, of any outages which may affect them.\n',
|
348 |
+
]
|
349 |
+
embeddings = model.encode(sentences)
|
350 |
+
print(embeddings.shape)
|
351 |
+
# [3, 384]
|
352 |
+
|
353 |
+
# Get the similarity scores for the embeddings
|
354 |
+
similarities = model.similarity(embeddings, embeddings)
|
355 |
+
print(similarities.shape)
|
356 |
+
# [3, 3]
|
357 |
+
```
|
358 |
+
|
359 |
+
<!--
|
360 |
+
### Direct Usage (Transformers)
|
361 |
+
|
362 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
363 |
+
|
364 |
+
</details>
|
365 |
+
-->
|
366 |
+
|
367 |
+
<!--
|
368 |
+
### Downstream Usage (Sentence Transformers)
|
369 |
+
|
370 |
+
You can finetune this model on your own dataset.
|
371 |
+
|
372 |
+
<details><summary>Click to expand</summary>
|
373 |
+
|
374 |
+
</details>
|
375 |
+
-->
|
376 |
+
|
377 |
+
<!--
|
378 |
+
### Out-of-Scope Use
|
379 |
+
|
380 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
381 |
+
-->
|
382 |
+
|
383 |
+
## Evaluation
|
384 |
+
|
385 |
+
### Metrics
|
386 |
+
|
387 |
+
#### Information Retrieval
|
388 |
+
|
389 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
390 |
+
|
391 |
+
| Metric | Value |
|
392 |
+
|:--------------------|:-----------|
|
393 |
+
| cosine_accuracy@1 | 0.6255 |
|
394 |
+
| cosine_accuracy@3 | 0.7518 |
|
395 |
+
| cosine_accuracy@5 | 0.7934 |
|
396 |
+
| cosine_accuracy@10 | 0.8368 |
|
397 |
+
| cosine_precision@1 | 0.6255 |
|
398 |
+
| cosine_precision@3 | 0.2641 |
|
399 |
+
| cosine_precision@5 | 0.1703 |
|
400 |
+
| cosine_precision@10 | 0.0931 |
|
401 |
+
| cosine_recall@1 | 0.5488 |
|
402 |
+
| cosine_recall@3 | 0.6705 |
|
403 |
+
| cosine_recall@5 | 0.7117 |
|
404 |
+
| cosine_recall@10 | 0.7628 |
|
405 |
+
| cosine_ndcg@10 | 0.68 |
|
406 |
+
| cosine_mrr@10 | 0.6976 |
|
407 |
+
| **cosine_map@100** | **0.6393** |
|
408 |
+
| dot_accuracy@1 | 0.6255 |
|
409 |
+
| dot_accuracy@3 | 0.7518 |
|
410 |
+
| dot_accuracy@5 | 0.7934 |
|
411 |
+
| dot_accuracy@10 | 0.8368 |
|
412 |
+
| dot_precision@1 | 0.6255 |
|
413 |
+
| dot_precision@3 | 0.2641 |
|
414 |
+
| dot_precision@5 | 0.1703 |
|
415 |
+
| dot_precision@10 | 0.0931 |
|
416 |
+
| dot_recall@1 | 0.5488 |
|
417 |
+
| dot_recall@3 | 0.6705 |
|
418 |
+
| dot_recall@5 | 0.7117 |
|
419 |
+
| dot_recall@10 | 0.7628 |
|
420 |
+
| dot_ndcg@10 | 0.68 |
|
421 |
+
| dot_mrr@10 | 0.6976 |
|
422 |
+
| dot_map@100 | 0.6393 |
|
423 |
+
|
424 |
+
<!--
|
425 |
+
## Bias, Risks and Limitations
|
426 |
+
|
427 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
428 |
+
-->
|
429 |
+
|
430 |
+
<!--
|
431 |
+
### Recommendations
|
432 |
+
|
433 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
434 |
+
-->
|
435 |
+
|
436 |
+
## Training Details
|
437 |
+
|
438 |
+
### Training Dataset
|
439 |
+
|
440 |
+
#### Unnamed Dataset
|
441 |
+
|
442 |
+
|
443 |
+
* Size: 22,291 training samples
|
444 |
+
* Columns: <code>sentence_0</code> and <code>sentence_1</code>
|
445 |
+
* Approximate statistics based on the first 1000 samples:
|
446 |
+
| | sentence_0 | sentence_1 |
|
447 |
+
|:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
|
448 |
+
| type | string | string |
|
449 |
+
| details | <ul><li>min: 14 tokens</li><li>mean: 34.77 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 113.08 tokens</li><li>max: 369 tokens</li></ul> |
|
450 |
+
* Samples:
|
451 |
+
| sentence_0 | sentence_1 |
|
452 |
+
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
453 |
+
| <code>Could you outline the process for obtaining an ADGM Green Fund Designation or an ADGM Climate Transition Fund Designation, and what are the ongoing compliance obligations associated with these designations?</code> | <code>AUTHORISED PERSONS CONDUCTING A REGULATED ACTIVITY IN RELATION TO VIRTUAL ASSETS – EXTENSION INTO TO DIGITAL SECURITIES ACTIVITIES<br>MTFs using Virtual Assets – Becoming a Digital Securities RIE<br>Migration of a Virtual Assets MTF to a RIE is more complex than the extension of a Virtual Assets MTF into Digital Securities (as dealt with in paragraphs 63 - 67 above). This is due to a number of factors, including that a RIE is required to meet the full suite of requirements in Chapters 2 and 3 of MIR, and the primary market considerations associated with operating a RIE (e.g., requirement for Approved Prospectuses, admission to the Official List of Securities, and the ongoing technical/operational and regulatory requirements related to Digital Securities being admitted to trading and admitted to the Official List).<br></code> |
|
454 |
+
| <code>Can the ADGM provide examples of effective internal risk control and reporting mechanisms that ensure an accurate assessment of a Reporting Entity's financial position and prospects, as per Rule 9.2.8?</code> | <code>Risk control. Authorised Persons should recognise and control the Credit Risk arising from their new products and services. Well in advance of entering into business transactions involving new types of products and activities, they should ensure that they understand the risks fully and have established appropriate Credit Risk policies, procedures and controls, which should be approved by the Governing Body or its appropriate delegated committee. A formal risk assessment of new products and activities should also be performed and documented.</code> |
|
455 |
+
| <code>What are the specific criteria used by the FSRA to determine whether a company's ESG disclosures align with a globally recognized standard?</code> | <code>The Regulator may refuse to grant an application for an ADGM Green Bond Designation or an ADGM Sustainability-Linked Bond Designation if it is not satisfied that the requirements of this section have been met or will be met on an ongoing basis.<br></code> |
|
456 |
+
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
|
457 |
+
```json
|
458 |
+
{
|
459 |
+
"scale": 20.0,
|
460 |
+
"similarity_fct": "cos_sim"
|
461 |
+
}
|
462 |
+
```
|
463 |
+
|
464 |
+
### Training Hyperparameters
|
465 |
+
#### Non-Default Hyperparameters
|
466 |
+
|
467 |
+
- `eval_strategy`: steps
|
468 |
+
- `per_device_train_batch_size`: 10
|
469 |
+
- `per_device_eval_batch_size`: 10
|
470 |
+
- `num_train_epochs`: 5
|
471 |
+
- `multi_dataset_batch_sampler`: round_robin
|
472 |
+
|
473 |
+
#### All Hyperparameters
|
474 |
+
<details><summary>Click to expand</summary>
|
475 |
+
|
476 |
+
- `overwrite_output_dir`: False
|
477 |
+
- `do_predict`: False
|
478 |
+
- `eval_strategy`: steps
|
479 |
+
- `prediction_loss_only`: True
|
480 |
+
- `per_device_train_batch_size`: 10
|
481 |
+
- `per_device_eval_batch_size`: 10
|
482 |
+
- `per_gpu_train_batch_size`: None
|
483 |
+
- `per_gpu_eval_batch_size`: None
|
484 |
+
- `gradient_accumulation_steps`: 1
|
485 |
+
- `eval_accumulation_steps`: None
|
486 |
+
- `torch_empty_cache_steps`: None
|
487 |
+
- `learning_rate`: 5e-05
|
488 |
+
- `weight_decay`: 0.0
|
489 |
+
- `adam_beta1`: 0.9
|
490 |
+
- `adam_beta2`: 0.999
|
491 |
+
- `adam_epsilon`: 1e-08
|
492 |
+
- `max_grad_norm`: 1
|
493 |
+
- `num_train_epochs`: 5
|
494 |
+
- `max_steps`: -1
|
495 |
+
- `lr_scheduler_type`: linear
|
496 |
+
- `lr_scheduler_kwargs`: {}
|
497 |
+
- `warmup_ratio`: 0.0
|
498 |
+
- `warmup_steps`: 0
|
499 |
+
- `log_level`: passive
|
500 |
+
- `log_level_replica`: warning
|
501 |
+
- `log_on_each_node`: True
|
502 |
+
- `logging_nan_inf_filter`: True
|
503 |
+
- `save_safetensors`: True
|
504 |
+
- `save_on_each_node`: False
|
505 |
+
- `save_only_model`: False
|
506 |
+
- `restore_callback_states_from_checkpoint`: False
|
507 |
+
- `no_cuda`: False
|
508 |
+
- `use_cpu`: False
|
509 |
+
- `use_mps_device`: False
|
510 |
+
- `seed`: 42
|
511 |
+
- `data_seed`: None
|
512 |
+
- `jit_mode_eval`: False
|
513 |
+
- `use_ipex`: False
|
514 |
+
- `bf16`: False
|
515 |
+
- `fp16`: False
|
516 |
+
- `fp16_opt_level`: O1
|
517 |
+
- `half_precision_backend`: auto
|
518 |
+
- `bf16_full_eval`: False
|
519 |
+
- `fp16_full_eval`: False
|
520 |
+
- `tf32`: None
|
521 |
+
- `local_rank`: 0
|
522 |
+
- `ddp_backend`: None
|
523 |
+
- `tpu_num_cores`: None
|
524 |
+
- `tpu_metrics_debug`: False
|
525 |
+
- `debug`: []
|
526 |
+
- `dataloader_drop_last`: False
|
527 |
+
- `dataloader_num_workers`: 0
|
528 |
+
- `dataloader_prefetch_factor`: None
|
529 |
+
- `past_index`: -1
|
530 |
+
- `disable_tqdm`: False
|
531 |
+
- `remove_unused_columns`: True
|
532 |
+
- `label_names`: None
|
533 |
+
- `load_best_model_at_end`: False
|
534 |
+
- `ignore_data_skip`: False
|
535 |
+
- `fsdp`: []
|
536 |
+
- `fsdp_min_num_params`: 0
|
537 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
538 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
539 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
540 |
+
- `deepspeed`: None
|
541 |
+
- `label_smoothing_factor`: 0.0
|
542 |
+
- `optim`: adamw_torch
|
543 |
+
- `optim_args`: None
|
544 |
+
- `adafactor`: False
|
545 |
+
- `group_by_length`: False
|
546 |
+
- `length_column_name`: length
|
547 |
+
- `ddp_find_unused_parameters`: None
|
548 |
+
- `ddp_bucket_cap_mb`: None
|
549 |
+
- `ddp_broadcast_buffers`: False
|
550 |
+
- `dataloader_pin_memory`: True
|
551 |
+
- `dataloader_persistent_workers`: False
|
552 |
+
- `skip_memory_metrics`: True
|
553 |
+
- `use_legacy_prediction_loop`: False
|
554 |
+
- `push_to_hub`: False
|
555 |
+
- `resume_from_checkpoint`: None
|
556 |
+
- `hub_model_id`: None
|
557 |
+
- `hub_strategy`: every_save
|
558 |
+
- `hub_private_repo`: False
|
559 |
+
- `hub_always_push`: False
|
560 |
+
- `gradient_checkpointing`: False
|
561 |
+
- `gradient_checkpointing_kwargs`: None
|
562 |
+
- `include_inputs_for_metrics`: False
|
563 |
+
- `eval_do_concat_batches`: True
|
564 |
+
- `fp16_backend`: auto
|
565 |
+
- `push_to_hub_model_id`: None
|
566 |
+
- `push_to_hub_organization`: None
|
567 |
+
- `mp_parameters`:
|
568 |
+
- `auto_find_batch_size`: False
|
569 |
+
- `full_determinism`: False
|
570 |
+
- `torchdynamo`: None
|
571 |
+
- `ray_scope`: last
|
572 |
+
- `ddp_timeout`: 1800
|
573 |
+
- `torch_compile`: False
|
574 |
+
- `torch_compile_backend`: None
|
575 |
+
- `torch_compile_mode`: None
|
576 |
+
- `dispatch_batches`: None
|
577 |
+
- `split_batches`: None
|
578 |
+
- `include_tokens_per_second`: False
|
579 |
+
- `include_num_input_tokens_seen`: False
|
580 |
+
- `neftune_noise_alpha`: None
|
581 |
+
- `optim_target_modules`: None
|
582 |
+
- `batch_eval_metrics`: False
|
583 |
+
- `eval_on_start`: False
|
584 |
+
- `use_liger_kernel`: False
|
585 |
+
- `eval_use_gather_object`: False
|
586 |
+
- `batch_sampler`: batch_sampler
|
587 |
+
- `multi_dataset_batch_sampler`: round_robin
|
588 |
+
|
589 |
+
</details>
|
590 |
+
|
591 |
+
### Training Logs
|
592 |
+
| Epoch | Step | Training Loss | cosine_map@100 |
|
593 |
+
|:------:|:-----:|:-------------:|:--------------:|
|
594 |
+
| 0.0897 | 200 | - | 0.5994 |
|
595 |
+
| 0.1794 | 400 | - | 0.6027 |
|
596 |
+
| 0.2242 | 500 | 0.925 | - |
|
597 |
+
| 0.2691 | 600 | - | 0.6053 |
|
598 |
+
| 0.3587 | 800 | - | 0.6123 |
|
599 |
+
| 0.4484 | 1000 | 0.5995 | 0.5981 |
|
600 |
+
| 0.5381 | 1200 | - | 0.6230 |
|
601 |
+
| 0.6278 | 1400 | - | 0.6236 |
|
602 |
+
| 0.6726 | 1500 | 0.5963 | - |
|
603 |
+
| 0.7175 | 1600 | - | 0.6082 |
|
604 |
+
| 0.8072 | 1800 | - | 0.6192 |
|
605 |
+
| 0.8969 | 2000 | 0.5078 | 0.6128 |
|
606 |
+
| 0.9865 | 2200 | - | 0.6159 |
|
607 |
+
| 1.0 | 2230 | - | 0.6235 |
|
608 |
+
| 1.0762 | 2400 | - | 0.6232 |
|
609 |
+
| 1.1211 | 2500 | 0.4599 | - |
|
610 |
+
| 1.1659 | 2600 | - | 0.6122 |
|
611 |
+
| 1.2556 | 2800 | - | 0.6242 |
|
612 |
+
| 1.3453 | 3000 | 0.4054 | 0.6246 |
|
613 |
+
| 1.4350 | 3200 | - | 0.6364 |
|
614 |
+
| 1.5247 | 3400 | - | 0.6260 |
|
615 |
+
| 1.5695 | 3500 | 0.4197 | - |
|
616 |
+
| 1.6143 | 3600 | - | 0.6230 |
|
617 |
+
| 1.7040 | 3800 | - | 0.6324 |
|
618 |
+
| 1.7937 | 4000 | 0.3896 | 0.6384 |
|
619 |
+
| 1.8834 | 4200 | - | 0.6346 |
|
620 |
+
| 1.9731 | 4400 | - | 0.6279 |
|
621 |
+
| 2.0 | 4460 | - | 0.6296 |
|
622 |
+
| 2.0179 | 4500 | 0.3875 | - |
|
623 |
+
| 2.0628 | 4600 | - | 0.6263 |
|
624 |
+
| 2.1525 | 4800 | - | 0.6326 |
|
625 |
+
| 2.2422 | 5000 | 0.3117 | 0.6306 |
|
626 |
+
| 2.3318 | 5200 | - | 0.6351 |
|
627 |
+
| 2.4215 | 5400 | - | 0.6330 |
|
628 |
+
| 2.4664 | 5500 | 0.3327 | - |
|
629 |
+
| 2.5112 | 5600 | - | 0.6355 |
|
630 |
+
| 2.6009 | 5800 | - | 0.6323 |
|
631 |
+
| 2.6906 | 6000 | 0.3017 | 0.6249 |
|
632 |
+
| 2.7803 | 6200 | - | 0.6324 |
|
633 |
+
| 2.8700 | 6400 | - | 0.6326 |
|
634 |
+
| 2.9148 | 6500 | 0.2971 | - |
|
635 |
+
| 2.9596 | 6600 | - | 0.6306 |
|
636 |
+
| 3.0 | 6690 | - | 0.6368 |
|
637 |
+
| 3.0493 | 6800 | - | 0.6351 |
|
638 |
+
| 3.1390 | 7000 | 0.2755 | 0.6308 |
|
639 |
+
| 3.2287 | 7200 | - | 0.6372 |
|
640 |
+
| 3.3184 | 7400 | - | 0.6390 |
|
641 |
+
| 3.3632 | 7500 | 0.2639 | - |
|
642 |
+
| 3.4081 | 7600 | - | 0.6326 |
|
643 |
+
| 3.4978 | 7800 | - | 0.6351 |
|
644 |
+
| 3.5874 | 8000 | 0.2474 | 0.6377 |
|
645 |
+
| 3.6771 | 8200 | - | 0.6375 |
|
646 |
+
| 3.7668 | 8400 | - | 0.6380 |
|
647 |
+
| 3.8117 | 8500 | 0.2402 | - |
|
648 |
+
| 3.8565 | 8600 | - | 0.6407 |
|
649 |
+
| 3.9462 | 8800 | - | 0.6401 |
|
650 |
+
| 4.0 | 8920 | - | 0.6433 |
|
651 |
+
| 4.0359 | 9000 | 0.2628 | 0.6452 |
|
652 |
+
| 4.1256 | 9200 | - | 0.6432 |
|
653 |
+
| 4.2152 | 9400 | - | 0.6426 |
|
654 |
+
| 4.2601 | 9500 | 0.2318 | - |
|
655 |
+
| 4.3049 | 9600 | - | 0.6404 |
|
656 |
+
| 4.3946 | 9800 | - | 0.6390 |
|
657 |
+
| 4.4843 | 10000 | 0.2246 | 0.6389 |
|
658 |
+
| 4.5740 | 10200 | - | 0.6394 |
|
659 |
+
| 4.6637 | 10400 | - | 0.6388 |
|
660 |
+
| 4.7085 | 10500 | 0.2054 | - |
|
661 |
+
| 4.7534 | 10600 | - | 0.6396 |
|
662 |
+
| 4.8430 | 10800 | - | 0.6389 |
|
663 |
+
| 4.9327 | 11000 | 0.2194 | 0.6394 |
|
664 |
+
| 5.0 | 11150 | - | 0.6393 |
|
665 |
+
|
666 |
+
|
667 |
+
### Framework Versions
|
668 |
+
- Python: 3.10.12
|
669 |
+
- Sentence Transformers: 3.1.1
|
670 |
+
- Transformers: 4.45.2
|
671 |
+
- PyTorch: 2.5.1+cu121
|
672 |
+
- Accelerate: 1.2.0.dev0
|
673 |
+
- Datasets: 3.1.0
|
674 |
+
- Tokenizers: 0.20.3
|
675 |
+
|
676 |
+
## Citation
|
677 |
+
|
678 |
+
### BibTeX
|
679 |
+
|
680 |
+
#### Sentence Transformers
|
681 |
+
```bibtex
|
682 |
+
@inproceedings{reimers-2019-sentence-bert,
|
683 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
684 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
685 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
686 |
+
month = "11",
|
687 |
+
year = "2019",
|
688 |
+
publisher = "Association for Computational Linguistics",
|
689 |
+
url = "https://arxiv.org/abs/1908.10084",
|
690 |
+
}
|
691 |
+
```
|
692 |
+
|
693 |
+
#### MultipleNegativesRankingLoss
|
694 |
+
```bibtex
|
695 |
+
@misc{henderson2017efficient,
|
696 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
697 |
+
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},
|
698 |
+
year={2017},
|
699 |
+
eprint={1705.00652},
|
700 |
+
archivePrefix={arXiv},
|
701 |
+
primaryClass={cs.CL}
|
702 |
+
}
|
703 |
+
```
|
704 |
+
|
705 |
+
<!--
|
706 |
+
## Glossary
|
707 |
+
|
708 |
+
*Clearly define terms in order to be accessible across audiences.*
|
709 |
+
-->
|
710 |
+
|
711 |
+
<!--
|
712 |
+
## Model Card Authors
|
713 |
+
|
714 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
715 |
+
-->
|
716 |
+
|
717 |
+
<!--
|
718 |
+
## Model Card Contact
|
719 |
+
|
720 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
721 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BAAI/bge-small-en",
|
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": 384,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 1536,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.45.2",
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.1.1",
|
4 |
+
"transformers": "4.45.2",
|
5 |
+
"pytorch": "2.5.1+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 sha256:96c52176dafa2d3ac17948a878f5dddfe6a55aee80ce9db3a8803ffccd03b544
|
3 |
+
size 133462128
|
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": true
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|