RonanMcGovern
commited on
Commit
•
bd97ef3
1
Parent(s):
19351f6
Add new SentenceTransformer model.
Browse files- 1_Pooling/config.json +10 -0
- README.md +537 -0
- config.json +26 -0
- config_sentence_transformers.json +10 -0
- model.safetensors +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -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 +1,537 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: sentence-transformers/multi-qa-MiniLM-L6-dot-v1
|
3 |
+
datasets: []
|
4 |
+
language: []
|
5 |
+
library_name: sentence-transformers
|
6 |
+
pipeline_tag: sentence-similarity
|
7 |
+
tags:
|
8 |
+
- sentence-transformers
|
9 |
+
- sentence-similarity
|
10 |
+
- feature-extraction
|
11 |
+
- generated_from_trainer
|
12 |
+
- dataset_size:211
|
13 |
+
- loss:MultipleNegativesRankingLoss
|
14 |
+
widget:
|
15 |
+
- source_sentence: What happens if a player in possession enters the defending team's
|
16 |
+
seven-metre zone?
|
17 |
+
sentences:
|
18 |
+
- 10. 8 if a touch is made in the in - goal area before the ball is grounded, the
|
19 |
+
player in possession is to perform a rollball seven ( 7 ) metres from the team
|
20 |
+
’ s attacking try line, provided it is not the sixth touch and the player is not
|
21 |
+
half. 10. 9 if a player in possession is touched while on or behind their defending
|
22 |
+
try line, the touch counts and once the referee sets the mark seven ( 7 ) metres
|
23 |
+
directly forward of the contact point from the defending team ’ s try line, a
|
24 |
+
rollball is performed. 10. 10 if a player in possession intentionally makes a
|
25 |
+
touch on an offside defender who is making every effort to retire and remain out
|
26 |
+
of play, the touch counts. fit playing rules - 5th edition copyright © touch football
|
27 |
+
australia 2020 9 10. 11 if a touch is made on a player in possession while the
|
28 |
+
player is juggling the ball in an attempt to maintain control of it, the touch
|
29 |
+
counts if the attacking player following the touch retains possession.
|
30 |
+
- 9. 2 on the change of possession due to an intercept, the first touch will be
|
31 |
+
zero ( 0 ) touch. 9. 3 following the sixth touch or a loss of possession due to
|
32 |
+
any other means, the ball must be returned to the mark without delay. ruling =
|
33 |
+
a deliberate delay in the changeover procedure will result in a penalty awarded
|
34 |
+
to the non - offending team ten ( 10 ) metres forward of the mark for the change
|
35 |
+
of possession. 9. 4 if the ball is dropped or passed and goes to ground during
|
36 |
+
play, a change of possession results. ruling = the mark for the change of possession
|
37 |
+
is where the ball makes initial contact with the ground. 9. 5 if the ball, while
|
38 |
+
still under the control of the half, contacts the ground in the in - goal area,
|
39 |
+
possession is lost. ruling = play will restart with a rollball at the nearest
|
40 |
+
point on the seven ( 7 ) metre line. fit playing rules - 5th edition 8 copyright
|
41 |
+
© touch football australia 2020 9. 6 if a player mishandles the ball and even
|
42 |
+
if in an effort to gain control, the ball is accidentally knocked forward into
|
43 |
+
any other player, a change of possession results.
|
44 |
+
- fit playing rules - 5th edition copyright © touch football australia 2020 9 10.
|
45 |
+
11 if a touch is made on a player in possession while the player is juggling the
|
46 |
+
ball in an attempt to maintain control of it, the touch counts if the attacking
|
47 |
+
player following the touch retains possession. 10. 12 if a player in possession
|
48 |
+
is touched and subsequently makes contact with either the sideline, a field marker
|
49 |
+
or the ground outside the field of play, the touch counts and play continues with
|
50 |
+
a rollball at the mark where the touch occurred. 10. 13 when a player from the
|
51 |
+
defending team enters its defensive seven metre zone, the defending team must
|
52 |
+
move forward at a reasonable pace until a touch is imminent or made. ruling =
|
53 |
+
a penalty to the attacking team at the point of the infringement. 10. 14 when
|
54 |
+
a player in possession enters the defending teams ’ seven metre zone the defending
|
55 |
+
team is not obliged to move forward but cannot retire back towards their try line
|
56 |
+
until a touch is imminent or made. ruling = a penalty to the attacking team at
|
57 |
+
the seven ( 7 ) metre line in line with the point of the infringement.
|
58 |
+
- source_sentence: What is the maximum number of touches a team can have before a
|
59 |
+
change of possession?
|
60 |
+
sentences:
|
61 |
+
- touch count the progressive number of touches that each team has before a change
|
62 |
+
of possession, from zero ( 0 ) to six ( 6 ). try the result of any attacking player,
|
63 |
+
except the half, placing the ball on or over the team ’ s attacking try line before
|
64 |
+
being touched. try lines the lines separating the in - goal areas from the field
|
65 |
+
of play. see appendix 1. voluntary rollball the player in possession performs
|
66 |
+
a rollball before a touch is made with a defending player. wing the player outside
|
67 |
+
the link player. winner the team that scores the most tries during the match.
|
68 |
+
fit playing rules - 5th edition 4 copyright © touch football australia 2020 rules
|
69 |
+
of play mode of play the object of the game of touch is for each team to score
|
70 |
+
tries and to prevent the opposition from scoring. the ball may be passed, knocked
|
71 |
+
or handed between players of the attacking team who may in turn run or otherwise
|
72 |
+
move with the ball in an attempt to gain territorial advantage and to score tries.
|
73 |
+
defending players prevent the attacking team from gaining a territorial advantage
|
74 |
+
by touching the ball carrier.
|
75 |
+
- 4. 3. 1 identifying numbers must feature no more than two ( 2 ) digits. 4. 4 hats
|
76 |
+
or caps are permitted to be worn during a match provided they are safe and meet
|
77 |
+
any nta regulations. 4. 5 safe footwear must be worn with exceptions allowed for
|
78 |
+
game variants such as beach touch. 4. 6 light leather or synthetic boots with
|
79 |
+
soft moulded soles are permitted. 4. 6. 1 shoes with screw - in studs are not
|
80 |
+
to be worn by any player or referee. 4. 7 players are not to participate in any
|
81 |
+
match wearing any item of jewellery, chain, identification band / bracelet or
|
82 |
+
similar item that may prove dangerous. any jewellery or other items that cannot
|
83 |
+
be removed are to be taped to the satisfaction of the referee. 4. 8 long ( extend
|
84 |
+
beyond the finger flesh when viewed from the palm ) or sharp fingernails are not
|
85 |
+
allowed. 4. 9 referees and players may wear spectacles or sunglasses provided
|
86 |
+
they are safe and securely attached. 4. 10 referees and players may wear sport
|
87 |
+
monitoring equipment and medical supports such as knee or ankle braces provided,
|
88 |
+
at the sole discretion of competition ’ s controlling body, the items are not
|
89 |
+
dangerous.
|
90 |
+
- a player with both feet on or behind their defending try line. pass the act of
|
91 |
+
changing possession between individual attacking players by propelling the ball
|
92 |
+
laterally and / or backwards and may include a flick, knock or throw. perimeter
|
93 |
+
a border not less than five ( 5 ) metres from the boundary of the field of play.
|
94 |
+
see appendix 1. penalty the ruling by a referee to award a tap when a player or
|
95 |
+
team infringes the rules of the game. possession refers to the player or team
|
96 |
+
that has control of the ball. providing other rules do not apply, the team with
|
97 |
+
the ball is entitled to six ( 6 ) touches. referee the match official ( s ) appointed
|
98 |
+
to make rulings during the conduct of a match. rollball the act of bringing the
|
99 |
+
ball into play following a touch or a change of possession. ruck / rollball area
|
100 |
+
the area, not exceeding one ( 1 ) metre in distance, between the player performing
|
101 |
+
a rollball and the half. ruling the decision made by a referee as a result of
|
102 |
+
particular circumstance and may result in a play on, a tap penalty, a discipline
|
103 |
+
option, change of possession or a try. seven metre zone the area between the seven
|
104 |
+
( 7 ) metre line and the try line.
|
105 |
+
- source_sentence: What is the definition of 'forward' in Touch Rugby?
|
106 |
+
sentences:
|
107 |
+
- end of play when the referee indicates completion of the match. exclusion when
|
108 |
+
a player is sent to the nearest sin bin area following three ( 3 ) penalties by
|
109 |
+
the defending team upon entering their seven metre zone. the player is counted
|
110 |
+
as a player on the field of play and cannot be replaced or interchanged. fit playing
|
111 |
+
rules - 5th edition copyright © touch football australia 2020 1 fit federation
|
112 |
+
of international touch field of play the playing area bounded by the sidelines
|
113 |
+
and dead ball lines, both of which are out of bounds. see appendix 1. forced interchange
|
114 |
+
when a player is required to undertake a compulsory interchange for an infringement
|
115 |
+
ruled more serious than a penalty but less serious than a permanent interchange,
|
116 |
+
sin bin or dismissal. forward a position or direction towards the dead ball line
|
117 |
+
beyond the team ’ s attacking try line. full time the expiration of the second
|
118 |
+
period of time allowed for play. half the player who takes possession following
|
119 |
+
a rollball. half time the break in play between the two halves of a match. imminent
|
120 |
+
about to occur, it is almost certain to occur. infringement the action of a player
|
121 |
+
contrary to the rules of the game.
|
122 |
+
- fit playing rules - 5th edition copyright © touch football australia 2020 9 10.
|
123 |
+
11 if a touch is made on a player in possession while the player is juggling the
|
124 |
+
ball in an attempt to maintain control of it, the touch counts if the attacking
|
125 |
+
player following the touch retains possession. 10. 12 if a player in possession
|
126 |
+
is touched and subsequently makes contact with either the sideline, a field marker
|
127 |
+
or the ground outside the field of play, the touch counts and play continues with
|
128 |
+
a rollball at the mark where the touch occurred. 10. 13 when a player from the
|
129 |
+
defending team enters its defensive seven metre zone, the defending team must
|
130 |
+
move forward at a reasonable pace until a touch is imminent or made. ruling =
|
131 |
+
a penalty to the attacking team at the point of the infringement. 10. 14 when
|
132 |
+
a player in possession enters the defending teams ’ seven metre zone the defending
|
133 |
+
team is not obliged to move forward but cannot retire back towards their try line
|
134 |
+
until a touch is imminent or made. ruling = a penalty to the attacking team at
|
135 |
+
the seven ( 7 ) metre line in line with the point of the infringement.
|
136 |
+
- 10. 8 if a touch is made in the in - goal area before the ball is grounded, the
|
137 |
+
player in possession is to perform a rollball seven ( 7 ) metres from the team
|
138 |
+
’ s attacking try line, provided it is not the sixth touch and the player is not
|
139 |
+
half. 10. 9 if a player in possession is touched while on or behind their defending
|
140 |
+
try line, the touch counts and once the referee sets the mark seven ( 7 ) metres
|
141 |
+
directly forward of the contact point from the defending team ’ s try line, a
|
142 |
+
rollball is performed. 10. 10 if a player in possession intentionally makes a
|
143 |
+
touch on an offside defender who is making every effort to retire and remain out
|
144 |
+
of play, the touch counts. fit playing rules - 5th edition copyright © touch football
|
145 |
+
australia 2020 9 10. 11 if a touch is made on a player in possession while the
|
146 |
+
player is juggling the ball in an attempt to maintain control of it, the touch
|
147 |
+
counts if the attacking player following the touch retains possession.
|
148 |
+
- source_sentence: What happens if neither team is leading at the end of the two-minute
|
149 |
+
period of extra time?
|
150 |
+
sentences:
|
151 |
+
- infringement the action of a player contrary to the rules of the game. in - goal
|
152 |
+
area the area in the field of play bounded by the sidelines, the try lines and
|
153 |
+
the dead ball lines. there are two ( 2 ), one ( 1 ) at each end of the field of
|
154 |
+
play. see appendix 1. interchange the act of an on - field player leaving the
|
155 |
+
field of play to be replaced by an off - field player entering the field of play.
|
156 |
+
interchange area a marked rectangle for each team on opposite sides of the field
|
157 |
+
of play usually measuring 20 metres long by no more than five ( 5 ) metres wide,
|
158 |
+
extending ten ( 10 ) metres either side of the halfway line and not less than
|
159 |
+
one ( 1 ) metre from the sideline. it is the area in which all off - field players
|
160 |
+
must remain until an interchange is initiated. see appendix 1. kick strike or
|
161 |
+
propel forcibly with the foot, a blow or forceful thrust with the foot to the
|
162 |
+
ball. a tap to commence or recommence play or a penalty tap is not defined as
|
163 |
+
a kick. line markings markings of the field of play. see appendix 1. link the
|
164 |
+
player beside the wing player.
|
165 |
+
- touch count the progressive number of touches that each team has before a change
|
166 |
+
of possession, from zero ( 0 ) to six ( 6 ). try the result of any attacking player,
|
167 |
+
except the half, placing the ball on or over the team ’ s attacking try line before
|
168 |
+
being touched. try lines the lines separating the in - goal areas from the field
|
169 |
+
of play. see appendix 1. voluntary rollball the player in possession performs
|
170 |
+
a rollball before a touch is made with a defending player. wing the player outside
|
171 |
+
the link player. winner the team that scores the most tries during the match.
|
172 |
+
fit playing rules - 5th edition 4 copyright © touch football australia 2020 rules
|
173 |
+
of play mode of play the object of the game of touch is for each team to score
|
174 |
+
tries and to prevent the opposition from scoring. the ball may be passed, knocked
|
175 |
+
or handed between players of the attacking team who may in turn run or otherwise
|
176 |
+
move with the ball in an attempt to gain territorial advantage and to score tries.
|
177 |
+
defending players prevent the attacking team from gaining a territorial advantage
|
178 |
+
by touching the ball carrier.
|
179 |
+
- 24. 1. 2 the drop - off commences with a tap from the centre of the halfway line
|
180 |
+
by the team that did not commence the match with possession. 24. 1. 3 the drop
|
181 |
+
- off will commence with a two ( 2 ) minute period of extra time. 24. 1. 4 should
|
182 |
+
a team be leading at the expiration of the two ( 2 ) minute period of extra time
|
183 |
+
then that team will be declared the winner and match complete. 24. 1. 5 should
|
184 |
+
neither team be leading at the expiration of two ( 2 ) minutes, a signal is given
|
185 |
+
and the match will pause at the next touch or dead ball. each team will then remove
|
186 |
+
another player from the field of play. 24. 1. 6 the match will recommence immediately
|
187 |
+
after the players have left the field at the same place where it paused ( i. e.
|
188 |
+
the team retains possession at the designated number of touches, or at change
|
189 |
+
of possession due to some infringement or the sixth touch ) and the match will
|
190 |
+
continue until a try is scored. 24. 1. 7 there is no time off during the drop
|
191 |
+
- off and the clock does not stop at the two ( 2 ) minute interval.
|
192 |
+
- source_sentence: What happens if a team is leading at the end of the two-minute
|
193 |
+
period of extra time?
|
194 |
+
sentences:
|
195 |
+
- 24. 1. 2 the drop - off commences with a tap from the centre of the halfway line
|
196 |
+
by the team that did not commence the match with possession. 24. 1. 3 the drop
|
197 |
+
- off will commence with a two ( 2 ) minute period of extra time. 24. 1. 4 should
|
198 |
+
a team be leading at the expiration of the two ( 2 ) minute period of extra time
|
199 |
+
then that team will be declared the winner and match complete. 24. 1. 5 should
|
200 |
+
neither team be leading at the expiration of two ( 2 ) minutes, a signal is given
|
201 |
+
and the match will pause at the next touch or dead ball. each team will then remove
|
202 |
+
another player from the field of play. 24. 1. 6 the match will recommence immediately
|
203 |
+
after the players have left the field at the same place where it paused ( i. e.
|
204 |
+
the team retains possession at the designated number of touches, or at change
|
205 |
+
of possession due to some infringement or the sixth touch ) and the match will
|
206 |
+
continue until a try is scored. 24. 1. 7 there is no time off during the drop
|
207 |
+
- off and the clock does not stop at the two ( 2 ) minute interval.
|
208 |
+
- 7. 7 the tap to commence or recommence play must be performed without delay. ruling
|
209 |
+
= a penalty to the non - offending team at the centre of the halfway line. 8 match
|
210 |
+
duration 8. 1 a match is 40 minutes in duration, consisting of two ( 2 ) x 20
|
211 |
+
minute halves with a half time break. 8. 1. 1 there is no time off for injury
|
212 |
+
during a match. 8. 2 local competition and tournament conditions may vary the
|
213 |
+
duration of a match. 8. 3 when time expires, play is to continue until the next
|
214 |
+
touch or dead ball and end of play is signaled by the referee. 8. 3. 1 should
|
215 |
+
a penalty be awarded during this period, the penalty is to be taken. 8. 4 if a
|
216 |
+
match is abandoned in any circumstances other than those referred to in clause
|
217 |
+
24. 1. 6 the nta or nta competition provider in its sole discretion shall determine
|
218 |
+
the result of the match. 9 possession 9. 1 the team with the ball is entitled
|
219 |
+
to six ( 6 ) touches prior to a change of possession. 9. 2 on the change of possession
|
220 |
+
due to an intercept, the first touch will be zero ( 0 ) touch.
|
221 |
+
- '12. 6 if a player from the defending team unintentionally makes contact with
|
222 |
+
the ball in flight and the ball is retrieved by an attacking player, play and
|
223 |
+
the touch count continues. 12. 7 a player from the attacking team cannot pass
|
224 |
+
the ball into a defending player intentionally seeking a rebound or a restart
|
225 |
+
of the touch count. ruling = a penalty to the defending team at the point of the
|
226 |
+
pass. 13 the rollball 13. 1 the attacking player is to position on the mark, face
|
227 |
+
the opponent ’ s try line, make a genuine attempt to stand parallel to the sidelines,
|
228 |
+
place the ball on the ground between the feet in a controlled manner and : 13.
|
229 |
+
1. 1 step forward over the ball ; or 13. 1. 2 roll the ball back between the feet
|
230 |
+
no more than one ( 1 ) metre ; or 13. 1. 3 pass a foot over the ball. ruling =
|
231 |
+
a change of possession to the defending team at the point of the infringement.
|
232 |
+
13. 2 a player must perform the rollball on the mark. ruling = a penalty to the
|
233 |
+
defending team at the point of the infringement. 13. 3 a player must not perform
|
234 |
+
a voluntary rollball.'
|
235 |
+
---
|
236 |
+
|
237 |
+
# SentenceTransformer based on sentence-transformers/multi-qa-MiniLM-L6-dot-v1
|
238 |
+
|
239 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/multi-qa-MiniLM-L6-dot-v1](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-dot-v1). 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.
|
240 |
+
|
241 |
+
## Model Details
|
242 |
+
|
243 |
+
### Model Description
|
244 |
+
- **Model Type:** Sentence Transformer
|
245 |
+
- **Base model:** [sentence-transformers/multi-qa-MiniLM-L6-dot-v1](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-dot-v1) <!-- at revision c3bdeb02464bc83f9b85156a3386a50bfbf3e6a8 -->
|
246 |
+
- **Maximum Sequence Length:** 512 tokens
|
247 |
+
- **Output Dimensionality:** 384 tokens
|
248 |
+
- **Similarity Function:** Dot Product
|
249 |
+
<!-- - **Training Dataset:** Unknown -->
|
250 |
+
<!-- - **Language:** Unknown -->
|
251 |
+
<!-- - **License:** Unknown -->
|
252 |
+
|
253 |
+
### Model Sources
|
254 |
+
|
255 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
256 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
257 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
258 |
+
|
259 |
+
### Full Model Architecture
|
260 |
+
|
261 |
+
```
|
262 |
+
SentenceTransformer(
|
263 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
264 |
+
(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})
|
265 |
+
)
|
266 |
+
```
|
267 |
+
|
268 |
+
## Usage
|
269 |
+
|
270 |
+
### Direct Usage (Sentence Transformers)
|
271 |
+
|
272 |
+
First install the Sentence Transformers library:
|
273 |
+
|
274 |
+
```bash
|
275 |
+
pip install -U sentence-transformers
|
276 |
+
```
|
277 |
+
|
278 |
+
Then you can load this model and run inference.
|
279 |
+
```python
|
280 |
+
from sentence_transformers import SentenceTransformer
|
281 |
+
|
282 |
+
# Download from the 🤗 Hub
|
283 |
+
model = SentenceTransformer("Trelis/multi-qa-MiniLM-L6-dot-v1-ft-pairs-4-cst-epoch-s1-overlap")
|
284 |
+
# Run inference
|
285 |
+
sentences = [
|
286 |
+
'What happens if a team is leading at the end of the two-minute period of extra time?',
|
287 |
+
'24. 1. 2 the drop - off commences with a tap from the centre of the halfway line by the team that did not commence the match with possession. 24. 1. 3 the drop - off will commence with a two ( 2 ) minute period of extra time. 24. 1. 4 should a team be leading at the expiration of the two ( 2 ) minute period of extra time then that team will be declared the winner and match complete. 24. 1. 5 should neither team be leading at the expiration of two ( 2 ) minutes, a signal is given and the match will pause at the next touch or dead ball. each team will then remove another player from the field of play. 24. 1. 6 the match will recommence immediately after the players have left the field at the same place where it paused ( i. e. the team retains possession at the designated number of touches, or at change of possession due to some infringement or the sixth touch ) and the match will continue until a try is scored. 24. 1. 7 there is no time off during the drop - off and the clock does not stop at the two ( 2 ) minute interval.',
|
288 |
+
'7. 7 the tap to commence or recommence play must be performed without delay. ruling = a penalty to the non - offending team at the centre of the halfway line. 8 match duration 8. 1 a match is 40 minutes in duration, consisting of two ( 2 ) x 20 minute halves with a half time break. 8. 1. 1 there is no time off for injury during a match. 8. 2 local competition and tournament conditions may vary the duration of a match. 8. 3 when time expires, play is to continue until the next touch or dead ball and end of play is signaled by the referee. 8. 3. 1 should a penalty be awarded during this period, the penalty is to be taken. 8. 4 if a match is abandoned in any circumstances other than those referred to in clause 24. 1. 6 the nta or nta competition provider in its sole discretion shall determine the result of the match. 9 possession 9. 1 the team with the ball is entitled to six ( 6 ) touches prior to a change of possession. 9. 2 on the change of possession due to an intercept, the first touch will be zero ( 0 ) touch.',
|
289 |
+
]
|
290 |
+
embeddings = model.encode(sentences)
|
291 |
+
print(embeddings.shape)
|
292 |
+
# [3, 384]
|
293 |
+
|
294 |
+
# Get the similarity scores for the embeddings
|
295 |
+
similarities = model.similarity(embeddings, embeddings)
|
296 |
+
print(similarities.shape)
|
297 |
+
# [3, 3]
|
298 |
+
```
|
299 |
+
|
300 |
+
<!--
|
301 |
+
### Direct Usage (Transformers)
|
302 |
+
|
303 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
304 |
+
|
305 |
+
</details>
|
306 |
+
-->
|
307 |
+
|
308 |
+
<!--
|
309 |
+
### Downstream Usage (Sentence Transformers)
|
310 |
+
|
311 |
+
You can finetune this model on your own dataset.
|
312 |
+
|
313 |
+
<details><summary>Click to expand</summary>
|
314 |
+
|
315 |
+
</details>
|
316 |
+
-->
|
317 |
+
|
318 |
+
<!--
|
319 |
+
### Out-of-Scope Use
|
320 |
+
|
321 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
322 |
+
-->
|
323 |
+
|
324 |
+
<!--
|
325 |
+
## Bias, Risks and Limitations
|
326 |
+
|
327 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
328 |
+
-->
|
329 |
+
|
330 |
+
<!--
|
331 |
+
### Recommendations
|
332 |
+
|
333 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
334 |
+
-->
|
335 |
+
|
336 |
+
## Training Details
|
337 |
+
|
338 |
+
### Training Hyperparameters
|
339 |
+
#### Non-Default Hyperparameters
|
340 |
+
|
341 |
+
- `eval_strategy`: steps
|
342 |
+
- `per_device_train_batch_size`: 32
|
343 |
+
- `per_device_eval_batch_size`: 32
|
344 |
+
- `learning_rate`: 2e-05
|
345 |
+
- `num_train_epochs`: 4
|
346 |
+
- `lr_scheduler_type`: constant
|
347 |
+
- `warmup_ratio`: 0.3
|
348 |
+
|
349 |
+
#### All Hyperparameters
|
350 |
+
<details><summary>Click to expand</summary>
|
351 |
+
|
352 |
+
- `overwrite_output_dir`: False
|
353 |
+
- `do_predict`: False
|
354 |
+
- `eval_strategy`: steps
|
355 |
+
- `prediction_loss_only`: True
|
356 |
+
- `per_device_train_batch_size`: 32
|
357 |
+
- `per_device_eval_batch_size`: 32
|
358 |
+
- `per_gpu_train_batch_size`: None
|
359 |
+
- `per_gpu_eval_batch_size`: None
|
360 |
+
- `gradient_accumulation_steps`: 1
|
361 |
+
- `eval_accumulation_steps`: None
|
362 |
+
- `learning_rate`: 2e-05
|
363 |
+
- `weight_decay`: 0.0
|
364 |
+
- `adam_beta1`: 0.9
|
365 |
+
- `adam_beta2`: 0.999
|
366 |
+
- `adam_epsilon`: 1e-08
|
367 |
+
- `max_grad_norm`: 1.0
|
368 |
+
- `num_train_epochs`: 4
|
369 |
+
- `max_steps`: -1
|
370 |
+
- `lr_scheduler_type`: constant
|
371 |
+
- `lr_scheduler_kwargs`: {}
|
372 |
+
- `warmup_ratio`: 0.3
|
373 |
+
- `warmup_steps`: 0
|
374 |
+
- `log_level`: passive
|
375 |
+
- `log_level_replica`: warning
|
376 |
+
- `log_on_each_node`: True
|
377 |
+
- `logging_nan_inf_filter`: True
|
378 |
+
- `save_safetensors`: True
|
379 |
+
- `save_on_each_node`: False
|
380 |
+
- `save_only_model`: False
|
381 |
+
- `restore_callback_states_from_checkpoint`: False
|
382 |
+
- `no_cuda`: False
|
383 |
+
- `use_cpu`: False
|
384 |
+
- `use_mps_device`: False
|
385 |
+
- `seed`: 42
|
386 |
+
- `data_seed`: None
|
387 |
+
- `jit_mode_eval`: False
|
388 |
+
- `use_ipex`: False
|
389 |
+
- `bf16`: False
|
390 |
+
- `fp16`: False
|
391 |
+
- `fp16_opt_level`: O1
|
392 |
+
- `half_precision_backend`: auto
|
393 |
+
- `bf16_full_eval`: False
|
394 |
+
- `fp16_full_eval`: False
|
395 |
+
- `tf32`: None
|
396 |
+
- `local_rank`: 0
|
397 |
+
- `ddp_backend`: None
|
398 |
+
- `tpu_num_cores`: None
|
399 |
+
- `tpu_metrics_debug`: False
|
400 |
+
- `debug`: []
|
401 |
+
- `dataloader_drop_last`: False
|
402 |
+
- `dataloader_num_workers`: 0
|
403 |
+
- `dataloader_prefetch_factor`: None
|
404 |
+
- `past_index`: -1
|
405 |
+
- `disable_tqdm`: False
|
406 |
+
- `remove_unused_columns`: True
|
407 |
+
- `label_names`: None
|
408 |
+
- `load_best_model_at_end`: False
|
409 |
+
- `ignore_data_skip`: False
|
410 |
+
- `fsdp`: []
|
411 |
+
- `fsdp_min_num_params`: 0
|
412 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
413 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
414 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
415 |
+
- `deepspeed`: None
|
416 |
+
- `label_smoothing_factor`: 0.0
|
417 |
+
- `optim`: adamw_torch
|
418 |
+
- `optim_args`: None
|
419 |
+
- `adafactor`: False
|
420 |
+
- `group_by_length`: False
|
421 |
+
- `length_column_name`: length
|
422 |
+
- `ddp_find_unused_parameters`: None
|
423 |
+
- `ddp_bucket_cap_mb`: None
|
424 |
+
- `ddp_broadcast_buffers`: False
|
425 |
+
- `dataloader_pin_memory`: True
|
426 |
+
- `dataloader_persistent_workers`: False
|
427 |
+
- `skip_memory_metrics`: True
|
428 |
+
- `use_legacy_prediction_loop`: False
|
429 |
+
- `push_to_hub`: False
|
430 |
+
- `resume_from_checkpoint`: None
|
431 |
+
- `hub_model_id`: None
|
432 |
+
- `hub_strategy`: every_save
|
433 |
+
- `hub_private_repo`: False
|
434 |
+
- `hub_always_push`: False
|
435 |
+
- `gradient_checkpointing`: False
|
436 |
+
- `gradient_checkpointing_kwargs`: None
|
437 |
+
- `include_inputs_for_metrics`: False
|
438 |
+
- `eval_do_concat_batches`: True
|
439 |
+
- `fp16_backend`: auto
|
440 |
+
- `push_to_hub_model_id`: None
|
441 |
+
- `push_to_hub_organization`: None
|
442 |
+
- `mp_parameters`:
|
443 |
+
- `auto_find_batch_size`: False
|
444 |
+
- `full_determinism`: False
|
445 |
+
- `torchdynamo`: None
|
446 |
+
- `ray_scope`: last
|
447 |
+
- `ddp_timeout`: 1800
|
448 |
+
- `torch_compile`: False
|
449 |
+
- `torch_compile_backend`: None
|
450 |
+
- `torch_compile_mode`: None
|
451 |
+
- `dispatch_batches`: None
|
452 |
+
- `split_batches`: None
|
453 |
+
- `include_tokens_per_second`: False
|
454 |
+
- `include_num_input_tokens_seen`: False
|
455 |
+
- `neftune_noise_alpha`: None
|
456 |
+
- `optim_target_modules`: None
|
457 |
+
- `batch_eval_metrics`: False
|
458 |
+
- `eval_on_start`: False
|
459 |
+
- `batch_sampler`: batch_sampler
|
460 |
+
- `multi_dataset_batch_sampler`: proportional
|
461 |
+
|
462 |
+
</details>
|
463 |
+
|
464 |
+
### Training Logs
|
465 |
+
| Epoch | Step | Training Loss | loss |
|
466 |
+
|:------:|:----:|:-------------:|:------:|
|
467 |
+
| 0.2857 | 2 | 1.7892 | - |
|
468 |
+
| 0.5714 | 4 | 1.5998 | 1.3002 |
|
469 |
+
| 0.8571 | 6 | 1.5637 | - |
|
470 |
+
| 1.1429 | 8 | 1.3347 | 1.1748 |
|
471 |
+
| 1.4286 | 10 | 1.4256 | - |
|
472 |
+
| 1.7143 | 12 | 1.2205 | 1.1085 |
|
473 |
+
| 2.0 | 14 | 1.1307 | - |
|
474 |
+
| 2.2857 | 16 | 1.119 | 1.0558 |
|
475 |
+
| 2.5714 | 18 | 1.2639 | - |
|
476 |
+
| 2.8571 | 20 | 1.2834 | 1.0108 |
|
477 |
+
| 3.1429 | 22 | 0.9248 | - |
|
478 |
+
| 3.4286 | 24 | 1.1527 | 1.0074 |
|
479 |
+
| 3.7143 | 26 | 0.8702 | - |
|
480 |
+
| 4.0 | 28 | 0.725 | 1.0124 |
|
481 |
+
|
482 |
+
|
483 |
+
### Framework Versions
|
484 |
+
- Python: 3.10.12
|
485 |
+
- Sentence Transformers: 3.0.1
|
486 |
+
- Transformers: 4.42.3
|
487 |
+
- PyTorch: 2.1.1+cu121
|
488 |
+
- Accelerate: 0.31.0
|
489 |
+
- Datasets: 2.17.1
|
490 |
+
- Tokenizers: 0.19.1
|
491 |
+
|
492 |
+
## Citation
|
493 |
+
|
494 |
+
### BibTeX
|
495 |
+
|
496 |
+
#### Sentence Transformers
|
497 |
+
```bibtex
|
498 |
+
@inproceedings{reimers-2019-sentence-bert,
|
499 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
500 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
501 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
502 |
+
month = "11",
|
503 |
+
year = "2019",
|
504 |
+
publisher = "Association for Computational Linguistics",
|
505 |
+
url = "https://arxiv.org/abs/1908.10084",
|
506 |
+
}
|
507 |
+
```
|
508 |
+
|
509 |
+
#### MultipleNegativesRankingLoss
|
510 |
+
```bibtex
|
511 |
+
@misc{henderson2017efficient,
|
512 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
513 |
+
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},
|
514 |
+
year={2017},
|
515 |
+
eprint={1705.00652},
|
516 |
+
archivePrefix={arXiv},
|
517 |
+
primaryClass={cs.CL}
|
518 |
+
}
|
519 |
+
```
|
520 |
+
|
521 |
+
<!--
|
522 |
+
## Glossary
|
523 |
+
|
524 |
+
*Clearly define terms in order to be accessible across audiences.*
|
525 |
+
-->
|
526 |
+
|
527 |
+
<!--
|
528 |
+
## Model Card Authors
|
529 |
+
|
530 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
531 |
+
-->
|
532 |
+
|
533 |
+
<!--
|
534 |
+
## Model Card Contact
|
535 |
+
|
536 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
537 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sentence-transformers/multi-qa-MiniLM-L6-dot-v1",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 384,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1536,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.42.3",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "3.0.1",
|
4 |
+
"transformers": "4.42.3",
|
5 |
+
"pytorch": "2.1.1+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null,
|
9 |
+
"similarity_fn_name": "dot"
|
10 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e97cb020989005ea8f18391c2601d8c5f11f2314f2c3c63f27f1e081d1b8f35d
|
3 |
+
size 90864192
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
}
|
14 |
+
]
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 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 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"max_length": 250,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]"
|
64 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|