Training in progress, step 500
Browse files- added_tokens.json +90 -0
- config.json +1 -1
- model.safetensors +2 -2
- runs/May17_17-45-55_c48d5225a06f/events.out.tfevents.1715967957.c48d5225a06f.1539.0 +3 -0
- tokenizer.json +793 -1
- tokenizer_config.json +704 -0
- training_args.bin +2 -2
added_tokens.json
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"%all%": 50352,
|
3 |
+
"%none%": 50351,
|
4 |
+
"</access_instructions>": 50304,
|
5 |
+
"</accommodation>": 50266,
|
6 |
+
"</activity>": 50268,
|
7 |
+
"</address>": 50290,
|
8 |
+
"</arrival_location>": 50270,
|
9 |
+
"</attendee>": 50272,
|
10 |
+
"</availability>": 50312,
|
11 |
+
"</car_rental>": 50332,
|
12 |
+
"</chat_title>": 50324,
|
13 |
+
"</check_in_date>": 50320,
|
14 |
+
"</child>": 50348,
|
15 |
+
"</child_of>": 50346,
|
16 |
+
"</context>": 50330,
|
17 |
+
"</cost>": 50274,
|
18 |
+
"</date>": 50276,
|
19 |
+
"</flight>": 50338,
|
20 |
+
"</flight_type>": 50308,
|
21 |
+
"</identifier>": 50344,
|
22 |
+
"</item_description>": 50342,
|
23 |
+
"</itinerary>": 50286,
|
24 |
+
"</link>": 50298,
|
25 |
+
"</location>": 50278,
|
26 |
+
"</metadata>": 50328,
|
27 |
+
"</occupancy>": 50302,
|
28 |
+
"</parent>": 50340,
|
29 |
+
"</participants>": 50322,
|
30 |
+
"</payment>": 50334,
|
31 |
+
"</payment_target>": 50336,
|
32 |
+
"</person>": 50310,
|
33 |
+
"</pickup_location>": 50314,
|
34 |
+
"</planner>": 50284,
|
35 |
+
"</preference>": 50318,
|
36 |
+
"</probability>": 50306,
|
37 |
+
"</readable_date>": 50326,
|
38 |
+
"</seat>": 50288,
|
39 |
+
"</sender>": 50280,
|
40 |
+
"</text_body>": 50350,
|
41 |
+
"</thing_needed>": 50292,
|
42 |
+
"</time>": 50282,
|
43 |
+
"</travel>": 50294,
|
44 |
+
"</trip>": 50300,
|
45 |
+
"</type>": 50296,
|
46 |
+
"</unstructured_information>": 50316,
|
47 |
+
"<access_instructions>": 50303,
|
48 |
+
"<accommodation>": 50265,
|
49 |
+
"<activity>": 50267,
|
50 |
+
"<address>": 50289,
|
51 |
+
"<arrival_location>": 50269,
|
52 |
+
"<attendee>": 50271,
|
53 |
+
"<availability>": 50311,
|
54 |
+
"<car_rental>": 50331,
|
55 |
+
"<chat_title>": 50323,
|
56 |
+
"<check_in_date>": 50319,
|
57 |
+
"<child>": 50347,
|
58 |
+
"<child_of>": 50345,
|
59 |
+
"<context>": 50329,
|
60 |
+
"<cost>": 50273,
|
61 |
+
"<date>": 50275,
|
62 |
+
"<flight>": 50337,
|
63 |
+
"<flight_type>": 50307,
|
64 |
+
"<identifier>": 50343,
|
65 |
+
"<item_description>": 50341,
|
66 |
+
"<itinerary>": 50285,
|
67 |
+
"<link>": 50297,
|
68 |
+
"<location>": 50277,
|
69 |
+
"<metadata>": 50327,
|
70 |
+
"<occupancy>": 50301,
|
71 |
+
"<parent>": 50339,
|
72 |
+
"<participants>": 50321,
|
73 |
+
"<payment>": 50333,
|
74 |
+
"<payment_target>": 50335,
|
75 |
+
"<person>": 50309,
|
76 |
+
"<pickup_location>": 50313,
|
77 |
+
"<planner>": 50283,
|
78 |
+
"<preference>": 50317,
|
79 |
+
"<probability>": 50305,
|
80 |
+
"<readable_date>": 50325,
|
81 |
+
"<seat>": 50287,
|
82 |
+
"<sender>": 50279,
|
83 |
+
"<text_body>": 50349,
|
84 |
+
"<thing_needed>": 50291,
|
85 |
+
"<time>": 50281,
|
86 |
+
"<travel>": 50293,
|
87 |
+
"<trip>": 50299,
|
88 |
+
"<type>": 50295,
|
89 |
+
"<unstructured_information>": 50315
|
90 |
+
}
|
config.json
CHANGED
@@ -66,5 +66,5 @@
|
|
66 |
"torch_dtype": "float32",
|
67 |
"transformers_version": "4.40.2",
|
68 |
"use_cache": true,
|
69 |
-
"vocab_size":
|
70 |
}
|
|
|
66 |
"torch_dtype": "float32",
|
67 |
"transformers_version": "4.40.2",
|
68 |
"use_cache": true,
|
69 |
+
"vocab_size": 50353
|
70 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc093c67ef70f3814d14839e7ec0da42ddd96502f3a84e65afbf14b5afa77543
|
3 |
+
size 1625787796
|
runs/May17_17-45-55_c48d5225a06f/events.out.tfevents.1715967957.c48d5225a06f.1539.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64f048c81b371bcbc56dfa29a8adb9ae550acbf3db582b612a9d345cd11123ae
|
3 |
+
size 11560
|
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
@@ -52,6 +52,798 @@
|
|
52 |
"rstrip": false,
|
53 |
"normalized": true,
|
54 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"normalizer": null,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
52 |
"rstrip": false,
|
53 |
"normalized": true,
|
54 |
"special": true
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"id": 50265,
|
58 |
+
"content": "<accommodation>",
|
59 |
+
"single_word": false,
|
60 |
+
"lstrip": false,
|
61 |
+
"rstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"special": false
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"id": 50266,
|
67 |
+
"content": "</accommodation>",
|
68 |
+
"single_word": false,
|
69 |
+
"lstrip": false,
|
70 |
+
"rstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"special": false
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"id": 50267,
|
76 |
+
"content": "<activity>",
|
77 |
+
"single_word": false,
|
78 |
+
"lstrip": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"normalized": true,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"id": 50268,
|
85 |
+
"content": "</activity>",
|
86 |
+
"single_word": false,
|
87 |
+
"lstrip": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"id": 50269,
|
94 |
+
"content": "<arrival_location>",
|
95 |
+
"single_word": false,
|
96 |
+
"lstrip": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"normalized": true,
|
99 |
+
"special": false
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"id": 50270,
|
103 |
+
"content": "</arrival_location>",
|
104 |
+
"single_word": false,
|
105 |
+
"lstrip": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"normalized": true,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"id": 50271,
|
112 |
+
"content": "<attendee>",
|
113 |
+
"single_word": false,
|
114 |
+
"lstrip": false,
|
115 |
+
"rstrip": false,
|
116 |
+
"normalized": true,
|
117 |
+
"special": false
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"id": 50272,
|
121 |
+
"content": "</attendee>",
|
122 |
+
"single_word": false,
|
123 |
+
"lstrip": false,
|
124 |
+
"rstrip": false,
|
125 |
+
"normalized": true,
|
126 |
+
"special": false
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"id": 50273,
|
130 |
+
"content": "<cost>",
|
131 |
+
"single_word": false,
|
132 |
+
"lstrip": false,
|
133 |
+
"rstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"special": false
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"id": 50274,
|
139 |
+
"content": "</cost>",
|
140 |
+
"single_word": false,
|
141 |
+
"lstrip": false,
|
142 |
+
"rstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"special": false
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"id": 50275,
|
148 |
+
"content": "<date>",
|
149 |
+
"single_word": false,
|
150 |
+
"lstrip": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"normalized": true,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"id": 50276,
|
157 |
+
"content": "</date>",
|
158 |
+
"single_word": false,
|
159 |
+
"lstrip": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"id": 50277,
|
166 |
+
"content": "<location>",
|
167 |
+
"single_word": false,
|
168 |
+
"lstrip": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"normalized": true,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"id": 50278,
|
175 |
+
"content": "</location>",
|
176 |
+
"single_word": false,
|
177 |
+
"lstrip": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"normalized": true,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"id": 50279,
|
184 |
+
"content": "<sender>",
|
185 |
+
"single_word": false,
|
186 |
+
"lstrip": false,
|
187 |
+
"rstrip": false,
|
188 |
+
"normalized": true,
|
189 |
+
"special": false
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"id": 50280,
|
193 |
+
"content": "</sender>",
|
194 |
+
"single_word": false,
|
195 |
+
"lstrip": false,
|
196 |
+
"rstrip": false,
|
197 |
+
"normalized": true,
|
198 |
+
"special": false
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"id": 50281,
|
202 |
+
"content": "<time>",
|
203 |
+
"single_word": false,
|
204 |
+
"lstrip": false,
|
205 |
+
"rstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"special": false
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"id": 50282,
|
211 |
+
"content": "</time>",
|
212 |
+
"single_word": false,
|
213 |
+
"lstrip": false,
|
214 |
+
"rstrip": false,
|
215 |
+
"normalized": true,
|
216 |
+
"special": false
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"id": 50283,
|
220 |
+
"content": "<planner>",
|
221 |
+
"single_word": false,
|
222 |
+
"lstrip": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"normalized": true,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"id": 50284,
|
229 |
+
"content": "</planner>",
|
230 |
+
"single_word": false,
|
231 |
+
"lstrip": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"normalized": true,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"id": 50285,
|
238 |
+
"content": "<itinerary>",
|
239 |
+
"single_word": false,
|
240 |
+
"lstrip": false,
|
241 |
+
"rstrip": false,
|
242 |
+
"normalized": true,
|
243 |
+
"special": false
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"id": 50286,
|
247 |
+
"content": "</itinerary>",
|
248 |
+
"single_word": false,
|
249 |
+
"lstrip": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"normalized": true,
|
252 |
+
"special": false
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"id": 50287,
|
256 |
+
"content": "<seat>",
|
257 |
+
"single_word": false,
|
258 |
+
"lstrip": false,
|
259 |
+
"rstrip": false,
|
260 |
+
"normalized": true,
|
261 |
+
"special": false
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"id": 50288,
|
265 |
+
"content": "</seat>",
|
266 |
+
"single_word": false,
|
267 |
+
"lstrip": false,
|
268 |
+
"rstrip": false,
|
269 |
+
"normalized": true,
|
270 |
+
"special": false
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"id": 50289,
|
274 |
+
"content": "<address>",
|
275 |
+
"single_word": false,
|
276 |
+
"lstrip": false,
|
277 |
+
"rstrip": false,
|
278 |
+
"normalized": true,
|
279 |
+
"special": false
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"id": 50290,
|
283 |
+
"content": "</address>",
|
284 |
+
"single_word": false,
|
285 |
+
"lstrip": false,
|
286 |
+
"rstrip": false,
|
287 |
+
"normalized": true,
|
288 |
+
"special": false
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"id": 50291,
|
292 |
+
"content": "<thing_needed>",
|
293 |
+
"single_word": false,
|
294 |
+
"lstrip": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"normalized": true,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"id": 50292,
|
301 |
+
"content": "</thing_needed>",
|
302 |
+
"single_word": false,
|
303 |
+
"lstrip": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"normalized": true,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"id": 50293,
|
310 |
+
"content": "<travel>",
|
311 |
+
"single_word": false,
|
312 |
+
"lstrip": false,
|
313 |
+
"rstrip": false,
|
314 |
+
"normalized": true,
|
315 |
+
"special": false
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"id": 50294,
|
319 |
+
"content": "</travel>",
|
320 |
+
"single_word": false,
|
321 |
+
"lstrip": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"normalized": true,
|
324 |
+
"special": false
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"id": 50295,
|
328 |
+
"content": "<type>",
|
329 |
+
"single_word": false,
|
330 |
+
"lstrip": false,
|
331 |
+
"rstrip": false,
|
332 |
+
"normalized": true,
|
333 |
+
"special": false
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"id": 50296,
|
337 |
+
"content": "</type>",
|
338 |
+
"single_word": false,
|
339 |
+
"lstrip": false,
|
340 |
+
"rstrip": false,
|
341 |
+
"normalized": true,
|
342 |
+
"special": false
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"id": 50297,
|
346 |
+
"content": "<link>",
|
347 |
+
"single_word": false,
|
348 |
+
"lstrip": false,
|
349 |
+
"rstrip": false,
|
350 |
+
"normalized": true,
|
351 |
+
"special": false
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"id": 50298,
|
355 |
+
"content": "</link>",
|
356 |
+
"single_word": false,
|
357 |
+
"lstrip": false,
|
358 |
+
"rstrip": false,
|
359 |
+
"normalized": true,
|
360 |
+
"special": false
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"id": 50299,
|
364 |
+
"content": "<trip>",
|
365 |
+
"single_word": false,
|
366 |
+
"lstrip": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"normalized": true,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"id": 50300,
|
373 |
+
"content": "</trip>",
|
374 |
+
"single_word": false,
|
375 |
+
"lstrip": false,
|
376 |
+
"rstrip": false,
|
377 |
+
"normalized": true,
|
378 |
+
"special": false
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"id": 50301,
|
382 |
+
"content": "<occupancy>",
|
383 |
+
"single_word": false,
|
384 |
+
"lstrip": false,
|
385 |
+
"rstrip": false,
|
386 |
+
"normalized": true,
|
387 |
+
"special": false
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"id": 50302,
|
391 |
+
"content": "</occupancy>",
|
392 |
+
"single_word": false,
|
393 |
+
"lstrip": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"normalized": true,
|
396 |
+
"special": false
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"id": 50303,
|
400 |
+
"content": "<access_instructions>",
|
401 |
+
"single_word": false,
|
402 |
+
"lstrip": false,
|
403 |
+
"rstrip": false,
|
404 |
+
"normalized": true,
|
405 |
+
"special": false
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"id": 50304,
|
409 |
+
"content": "</access_instructions>",
|
410 |
+
"single_word": false,
|
411 |
+
"lstrip": false,
|
412 |
+
"rstrip": false,
|
413 |
+
"normalized": true,
|
414 |
+
"special": false
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"id": 50305,
|
418 |
+
"content": "<probability>",
|
419 |
+
"single_word": false,
|
420 |
+
"lstrip": false,
|
421 |
+
"rstrip": false,
|
422 |
+
"normalized": true,
|
423 |
+
"special": false
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"id": 50306,
|
427 |
+
"content": "</probability>",
|
428 |
+
"single_word": false,
|
429 |
+
"lstrip": false,
|
430 |
+
"rstrip": false,
|
431 |
+
"normalized": true,
|
432 |
+
"special": false
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"id": 50307,
|
436 |
+
"content": "<flight_type>",
|
437 |
+
"single_word": false,
|
438 |
+
"lstrip": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"normalized": true,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"id": 50308,
|
445 |
+
"content": "</flight_type>",
|
446 |
+
"single_word": false,
|
447 |
+
"lstrip": false,
|
448 |
+
"rstrip": false,
|
449 |
+
"normalized": true,
|
450 |
+
"special": false
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"id": 50309,
|
454 |
+
"content": "<person>",
|
455 |
+
"single_word": false,
|
456 |
+
"lstrip": false,
|
457 |
+
"rstrip": false,
|
458 |
+
"normalized": true,
|
459 |
+
"special": false
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"id": 50310,
|
463 |
+
"content": "</person>",
|
464 |
+
"single_word": false,
|
465 |
+
"lstrip": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"normalized": true,
|
468 |
+
"special": false
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"id": 50311,
|
472 |
+
"content": "<availability>",
|
473 |
+
"single_word": false,
|
474 |
+
"lstrip": false,
|
475 |
+
"rstrip": false,
|
476 |
+
"normalized": true,
|
477 |
+
"special": false
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"id": 50312,
|
481 |
+
"content": "</availability>",
|
482 |
+
"single_word": false,
|
483 |
+
"lstrip": false,
|
484 |
+
"rstrip": false,
|
485 |
+
"normalized": true,
|
486 |
+
"special": false
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"id": 50313,
|
490 |
+
"content": "<pickup_location>",
|
491 |
+
"single_word": false,
|
492 |
+
"lstrip": false,
|
493 |
+
"rstrip": false,
|
494 |
+
"normalized": true,
|
495 |
+
"special": false
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"id": 50314,
|
499 |
+
"content": "</pickup_location>",
|
500 |
+
"single_word": false,
|
501 |
+
"lstrip": false,
|
502 |
+
"rstrip": false,
|
503 |
+
"normalized": true,
|
504 |
+
"special": false
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"id": 50315,
|
508 |
+
"content": "<unstructured_information>",
|
509 |
+
"single_word": false,
|
510 |
+
"lstrip": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"normalized": true,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"id": 50316,
|
517 |
+
"content": "</unstructured_information>",
|
518 |
+
"single_word": false,
|
519 |
+
"lstrip": false,
|
520 |
+
"rstrip": false,
|
521 |
+
"normalized": true,
|
522 |
+
"special": false
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"id": 50317,
|
526 |
+
"content": "<preference>",
|
527 |
+
"single_word": false,
|
528 |
+
"lstrip": false,
|
529 |
+
"rstrip": false,
|
530 |
+
"normalized": true,
|
531 |
+
"special": false
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"id": 50318,
|
535 |
+
"content": "</preference>",
|
536 |
+
"single_word": false,
|
537 |
+
"lstrip": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"normalized": true,
|
540 |
+
"special": false
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"id": 50319,
|
544 |
+
"content": "<check_in_date>",
|
545 |
+
"single_word": false,
|
546 |
+
"lstrip": false,
|
547 |
+
"rstrip": false,
|
548 |
+
"normalized": true,
|
549 |
+
"special": false
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"id": 50320,
|
553 |
+
"content": "</check_in_date>",
|
554 |
+
"single_word": false,
|
555 |
+
"lstrip": false,
|
556 |
+
"rstrip": false,
|
557 |
+
"normalized": true,
|
558 |
+
"special": false
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"id": 50321,
|
562 |
+
"content": "<participants>",
|
563 |
+
"single_word": false,
|
564 |
+
"lstrip": false,
|
565 |
+
"rstrip": false,
|
566 |
+
"normalized": true,
|
567 |
+
"special": false
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"id": 50322,
|
571 |
+
"content": "</participants>",
|
572 |
+
"single_word": false,
|
573 |
+
"lstrip": false,
|
574 |
+
"rstrip": false,
|
575 |
+
"normalized": true,
|
576 |
+
"special": false
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"id": 50323,
|
580 |
+
"content": "<chat_title>",
|
581 |
+
"single_word": false,
|
582 |
+
"lstrip": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"normalized": true,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"id": 50324,
|
589 |
+
"content": "</chat_title>",
|
590 |
+
"single_word": false,
|
591 |
+
"lstrip": false,
|
592 |
+
"rstrip": false,
|
593 |
+
"normalized": true,
|
594 |
+
"special": false
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"id": 50325,
|
598 |
+
"content": "<readable_date>",
|
599 |
+
"single_word": false,
|
600 |
+
"lstrip": false,
|
601 |
+
"rstrip": false,
|
602 |
+
"normalized": true,
|
603 |
+
"special": false
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"id": 50326,
|
607 |
+
"content": "</readable_date>",
|
608 |
+
"single_word": false,
|
609 |
+
"lstrip": false,
|
610 |
+
"rstrip": false,
|
611 |
+
"normalized": true,
|
612 |
+
"special": false
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"id": 50327,
|
616 |
+
"content": "<metadata>",
|
617 |
+
"single_word": false,
|
618 |
+
"lstrip": false,
|
619 |
+
"rstrip": false,
|
620 |
+
"normalized": true,
|
621 |
+
"special": false
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"id": 50328,
|
625 |
+
"content": "</metadata>",
|
626 |
+
"single_word": false,
|
627 |
+
"lstrip": false,
|
628 |
+
"rstrip": false,
|
629 |
+
"normalized": true,
|
630 |
+
"special": false
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"id": 50329,
|
634 |
+
"content": "<context>",
|
635 |
+
"single_word": false,
|
636 |
+
"lstrip": false,
|
637 |
+
"rstrip": false,
|
638 |
+
"normalized": true,
|
639 |
+
"special": false
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"id": 50330,
|
643 |
+
"content": "</context>",
|
644 |
+
"single_word": false,
|
645 |
+
"lstrip": false,
|
646 |
+
"rstrip": false,
|
647 |
+
"normalized": true,
|
648 |
+
"special": false
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"id": 50331,
|
652 |
+
"content": "<car_rental>",
|
653 |
+
"single_word": false,
|
654 |
+
"lstrip": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"normalized": true,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"id": 50332,
|
661 |
+
"content": "</car_rental>",
|
662 |
+
"single_word": false,
|
663 |
+
"lstrip": false,
|
664 |
+
"rstrip": false,
|
665 |
+
"normalized": true,
|
666 |
+
"special": false
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"id": 50333,
|
670 |
+
"content": "<payment>",
|
671 |
+
"single_word": false,
|
672 |
+
"lstrip": false,
|
673 |
+
"rstrip": false,
|
674 |
+
"normalized": true,
|
675 |
+
"special": false
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"id": 50334,
|
679 |
+
"content": "</payment>",
|
680 |
+
"single_word": false,
|
681 |
+
"lstrip": false,
|
682 |
+
"rstrip": false,
|
683 |
+
"normalized": true,
|
684 |
+
"special": false
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"id": 50335,
|
688 |
+
"content": "<payment_target>",
|
689 |
+
"single_word": false,
|
690 |
+
"lstrip": false,
|
691 |
+
"rstrip": false,
|
692 |
+
"normalized": true,
|
693 |
+
"special": false
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"id": 50336,
|
697 |
+
"content": "</payment_target>",
|
698 |
+
"single_word": false,
|
699 |
+
"lstrip": false,
|
700 |
+
"rstrip": false,
|
701 |
+
"normalized": true,
|
702 |
+
"special": false
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"id": 50337,
|
706 |
+
"content": "<flight>",
|
707 |
+
"single_word": false,
|
708 |
+
"lstrip": false,
|
709 |
+
"rstrip": false,
|
710 |
+
"normalized": true,
|
711 |
+
"special": false
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"id": 50338,
|
715 |
+
"content": "</flight>",
|
716 |
+
"single_word": false,
|
717 |
+
"lstrip": false,
|
718 |
+
"rstrip": false,
|
719 |
+
"normalized": true,
|
720 |
+
"special": false
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"id": 50339,
|
724 |
+
"content": "<parent>",
|
725 |
+
"single_word": false,
|
726 |
+
"lstrip": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"normalized": true,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"id": 50340,
|
733 |
+
"content": "</parent>",
|
734 |
+
"single_word": false,
|
735 |
+
"lstrip": false,
|
736 |
+
"rstrip": false,
|
737 |
+
"normalized": true,
|
738 |
+
"special": false
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"id": 50341,
|
742 |
+
"content": "<item_description>",
|
743 |
+
"single_word": false,
|
744 |
+
"lstrip": false,
|
745 |
+
"rstrip": false,
|
746 |
+
"normalized": true,
|
747 |
+
"special": false
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"id": 50342,
|
751 |
+
"content": "</item_description>",
|
752 |
+
"single_word": false,
|
753 |
+
"lstrip": false,
|
754 |
+
"rstrip": false,
|
755 |
+
"normalized": true,
|
756 |
+
"special": false
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"id": 50343,
|
760 |
+
"content": "<identifier>",
|
761 |
+
"single_word": false,
|
762 |
+
"lstrip": false,
|
763 |
+
"rstrip": false,
|
764 |
+
"normalized": true,
|
765 |
+
"special": false
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"id": 50344,
|
769 |
+
"content": "</identifier>",
|
770 |
+
"single_word": false,
|
771 |
+
"lstrip": false,
|
772 |
+
"rstrip": false,
|
773 |
+
"normalized": true,
|
774 |
+
"special": false
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"id": 50345,
|
778 |
+
"content": "<child_of>",
|
779 |
+
"single_word": false,
|
780 |
+
"lstrip": false,
|
781 |
+
"rstrip": false,
|
782 |
+
"normalized": true,
|
783 |
+
"special": false
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"id": 50346,
|
787 |
+
"content": "</child_of>",
|
788 |
+
"single_word": false,
|
789 |
+
"lstrip": false,
|
790 |
+
"rstrip": false,
|
791 |
+
"normalized": true,
|
792 |
+
"special": false
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"id": 50347,
|
796 |
+
"content": "<child>",
|
797 |
+
"single_word": false,
|
798 |
+
"lstrip": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"normalized": true,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"id": 50348,
|
805 |
+
"content": "</child>",
|
806 |
+
"single_word": false,
|
807 |
+
"lstrip": false,
|
808 |
+
"rstrip": false,
|
809 |
+
"normalized": true,
|
810 |
+
"special": false
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"id": 50349,
|
814 |
+
"content": "<text_body>",
|
815 |
+
"single_word": false,
|
816 |
+
"lstrip": false,
|
817 |
+
"rstrip": false,
|
818 |
+
"normalized": true,
|
819 |
+
"special": false
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"id": 50350,
|
823 |
+
"content": "</text_body>",
|
824 |
+
"single_word": false,
|
825 |
+
"lstrip": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"normalized": true,
|
828 |
+
"special": false
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"id": 50351,
|
832 |
+
"content": "%none%",
|
833 |
+
"single_word": false,
|
834 |
+
"lstrip": false,
|
835 |
+
"rstrip": false,
|
836 |
+
"normalized": true,
|
837 |
+
"special": false
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"id": 50352,
|
841 |
+
"content": "%all%",
|
842 |
+
"single_word": false,
|
843 |
+
"lstrip": false,
|
844 |
+
"rstrip": false,
|
845 |
+
"normalized": true,
|
846 |
+
"special": false
|
847 |
}
|
848 |
],
|
849 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -40,6 +40,710 @@
|
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
}
|
44 |
},
|
45 |
"bos_token": "<s>",
|
|
|
40 |
"rstrip": false,
|
41 |
"single_word": false,
|
42 |
"special": true
|
43 |
+
},
|
44 |
+
"50265": {
|
45 |
+
"content": "<accommodation>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"50266": {
|
53 |
+
"content": "</accommodation>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"50267": {
|
61 |
+
"content": "<activity>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"50268": {
|
69 |
+
"content": "</activity>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"50269": {
|
77 |
+
"content": "<arrival_location>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"50270": {
|
85 |
+
"content": "</arrival_location>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"50271": {
|
93 |
+
"content": "<attendee>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"50272": {
|
101 |
+
"content": "</attendee>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"50273": {
|
109 |
+
"content": "<cost>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"50274": {
|
117 |
+
"content": "</cost>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"50275": {
|
125 |
+
"content": "<date>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"50276": {
|
133 |
+
"content": "</date>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"50277": {
|
141 |
+
"content": "<location>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"50278": {
|
149 |
+
"content": "</location>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"50279": {
|
157 |
+
"content": "<sender>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"50280": {
|
165 |
+
"content": "</sender>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"50281": {
|
173 |
+
"content": "<time>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"50282": {
|
181 |
+
"content": "</time>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"50283": {
|
189 |
+
"content": "<planner>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"50284": {
|
197 |
+
"content": "</planner>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"50285": {
|
205 |
+
"content": "<itinerary>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": true,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
},
|
212 |
+
"50286": {
|
213 |
+
"content": "</itinerary>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": true,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"50287": {
|
221 |
+
"content": "<seat>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": true,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": false
|
227 |
+
},
|
228 |
+
"50288": {
|
229 |
+
"content": "</seat>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": true,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
"50289": {
|
237 |
+
"content": "<address>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": true,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": false
|
243 |
+
},
|
244 |
+
"50290": {
|
245 |
+
"content": "</address>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": true,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": false
|
251 |
+
},
|
252 |
+
"50291": {
|
253 |
+
"content": "<thing_needed>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": true,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": false
|
259 |
+
},
|
260 |
+
"50292": {
|
261 |
+
"content": "</thing_needed>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": true,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": false
|
267 |
+
},
|
268 |
+
"50293": {
|
269 |
+
"content": "<travel>",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": true,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
"50294": {
|
277 |
+
"content": "</travel>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": true,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": false
|
283 |
+
},
|
284 |
+
"50295": {
|
285 |
+
"content": "<type>",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": true,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": false
|
291 |
+
},
|
292 |
+
"50296": {
|
293 |
+
"content": "</type>",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": true,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": false
|
299 |
+
},
|
300 |
+
"50297": {
|
301 |
+
"content": "<link>",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": true,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
"50298": {
|
309 |
+
"content": "</link>",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": true,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": false
|
315 |
+
},
|
316 |
+
"50299": {
|
317 |
+
"content": "<trip>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": true,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": false
|
323 |
+
},
|
324 |
+
"50300": {
|
325 |
+
"content": "</trip>",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": true,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": false
|
331 |
+
},
|
332 |
+
"50301": {
|
333 |
+
"content": "<occupancy>",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": true,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": false
|
339 |
+
},
|
340 |
+
"50302": {
|
341 |
+
"content": "</occupancy>",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": true,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": false
|
347 |
+
},
|
348 |
+
"50303": {
|
349 |
+
"content": "<access_instructions>",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": true,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": false
|
355 |
+
},
|
356 |
+
"50304": {
|
357 |
+
"content": "</access_instructions>",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": true,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": false
|
363 |
+
},
|
364 |
+
"50305": {
|
365 |
+
"content": "<probability>",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": true,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": false
|
371 |
+
},
|
372 |
+
"50306": {
|
373 |
+
"content": "</probability>",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": true,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": false
|
379 |
+
},
|
380 |
+
"50307": {
|
381 |
+
"content": "<flight_type>",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": true,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": false
|
387 |
+
},
|
388 |
+
"50308": {
|
389 |
+
"content": "</flight_type>",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": true,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": false
|
395 |
+
},
|
396 |
+
"50309": {
|
397 |
+
"content": "<person>",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": true,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": false
|
403 |
+
},
|
404 |
+
"50310": {
|
405 |
+
"content": "</person>",
|
406 |
+
"lstrip": false,
|
407 |
+
"normalized": true,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": false
|
411 |
+
},
|
412 |
+
"50311": {
|
413 |
+
"content": "<availability>",
|
414 |
+
"lstrip": false,
|
415 |
+
"normalized": true,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": false
|
419 |
+
},
|
420 |
+
"50312": {
|
421 |
+
"content": "</availability>",
|
422 |
+
"lstrip": false,
|
423 |
+
"normalized": true,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": false
|
427 |
+
},
|
428 |
+
"50313": {
|
429 |
+
"content": "<pickup_location>",
|
430 |
+
"lstrip": false,
|
431 |
+
"normalized": true,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": false
|
435 |
+
},
|
436 |
+
"50314": {
|
437 |
+
"content": "</pickup_location>",
|
438 |
+
"lstrip": false,
|
439 |
+
"normalized": true,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": false
|
443 |
+
},
|
444 |
+
"50315": {
|
445 |
+
"content": "<unstructured_information>",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": true,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": false
|
451 |
+
},
|
452 |
+
"50316": {
|
453 |
+
"content": "</unstructured_information>",
|
454 |
+
"lstrip": false,
|
455 |
+
"normalized": true,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": false
|
459 |
+
},
|
460 |
+
"50317": {
|
461 |
+
"content": "<preference>",
|
462 |
+
"lstrip": false,
|
463 |
+
"normalized": true,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": false
|
467 |
+
},
|
468 |
+
"50318": {
|
469 |
+
"content": "</preference>",
|
470 |
+
"lstrip": false,
|
471 |
+
"normalized": true,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": false
|
475 |
+
},
|
476 |
+
"50319": {
|
477 |
+
"content": "<check_in_date>",
|
478 |
+
"lstrip": false,
|
479 |
+
"normalized": true,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": false
|
483 |
+
},
|
484 |
+
"50320": {
|
485 |
+
"content": "</check_in_date>",
|
486 |
+
"lstrip": false,
|
487 |
+
"normalized": true,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": false
|
491 |
+
},
|
492 |
+
"50321": {
|
493 |
+
"content": "<participants>",
|
494 |
+
"lstrip": false,
|
495 |
+
"normalized": true,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": false
|
499 |
+
},
|
500 |
+
"50322": {
|
501 |
+
"content": "</participants>",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": true,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": false
|
507 |
+
},
|
508 |
+
"50323": {
|
509 |
+
"content": "<chat_title>",
|
510 |
+
"lstrip": false,
|
511 |
+
"normalized": true,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": false
|
515 |
+
},
|
516 |
+
"50324": {
|
517 |
+
"content": "</chat_title>",
|
518 |
+
"lstrip": false,
|
519 |
+
"normalized": true,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": false
|
523 |
+
},
|
524 |
+
"50325": {
|
525 |
+
"content": "<readable_date>",
|
526 |
+
"lstrip": false,
|
527 |
+
"normalized": true,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": false
|
531 |
+
},
|
532 |
+
"50326": {
|
533 |
+
"content": "</readable_date>",
|
534 |
+
"lstrip": false,
|
535 |
+
"normalized": true,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": false
|
539 |
+
},
|
540 |
+
"50327": {
|
541 |
+
"content": "<metadata>",
|
542 |
+
"lstrip": false,
|
543 |
+
"normalized": true,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": false
|
547 |
+
},
|
548 |
+
"50328": {
|
549 |
+
"content": "</metadata>",
|
550 |
+
"lstrip": false,
|
551 |
+
"normalized": true,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": false
|
555 |
+
},
|
556 |
+
"50329": {
|
557 |
+
"content": "<context>",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": true,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": false
|
563 |
+
},
|
564 |
+
"50330": {
|
565 |
+
"content": "</context>",
|
566 |
+
"lstrip": false,
|
567 |
+
"normalized": true,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": false
|
571 |
+
},
|
572 |
+
"50331": {
|
573 |
+
"content": "<car_rental>",
|
574 |
+
"lstrip": false,
|
575 |
+
"normalized": true,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": false
|
579 |
+
},
|
580 |
+
"50332": {
|
581 |
+
"content": "</car_rental>",
|
582 |
+
"lstrip": false,
|
583 |
+
"normalized": true,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": false
|
587 |
+
},
|
588 |
+
"50333": {
|
589 |
+
"content": "<payment>",
|
590 |
+
"lstrip": false,
|
591 |
+
"normalized": true,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": false
|
595 |
+
},
|
596 |
+
"50334": {
|
597 |
+
"content": "</payment>",
|
598 |
+
"lstrip": false,
|
599 |
+
"normalized": true,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": false
|
603 |
+
},
|
604 |
+
"50335": {
|
605 |
+
"content": "<payment_target>",
|
606 |
+
"lstrip": false,
|
607 |
+
"normalized": true,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": false
|
611 |
+
},
|
612 |
+
"50336": {
|
613 |
+
"content": "</payment_target>",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": true,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": false
|
619 |
+
},
|
620 |
+
"50337": {
|
621 |
+
"content": "<flight>",
|
622 |
+
"lstrip": false,
|
623 |
+
"normalized": true,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": false
|
627 |
+
},
|
628 |
+
"50338": {
|
629 |
+
"content": "</flight>",
|
630 |
+
"lstrip": false,
|
631 |
+
"normalized": true,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": false
|
635 |
+
},
|
636 |
+
"50339": {
|
637 |
+
"content": "<parent>",
|
638 |
+
"lstrip": false,
|
639 |
+
"normalized": true,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": false
|
643 |
+
},
|
644 |
+
"50340": {
|
645 |
+
"content": "</parent>",
|
646 |
+
"lstrip": false,
|
647 |
+
"normalized": true,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": false
|
651 |
+
},
|
652 |
+
"50341": {
|
653 |
+
"content": "<item_description>",
|
654 |
+
"lstrip": false,
|
655 |
+
"normalized": true,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": false
|
659 |
+
},
|
660 |
+
"50342": {
|
661 |
+
"content": "</item_description>",
|
662 |
+
"lstrip": false,
|
663 |
+
"normalized": true,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": false
|
667 |
+
},
|
668 |
+
"50343": {
|
669 |
+
"content": "<identifier>",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": true,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": false
|
675 |
+
},
|
676 |
+
"50344": {
|
677 |
+
"content": "</identifier>",
|
678 |
+
"lstrip": false,
|
679 |
+
"normalized": true,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": false
|
683 |
+
},
|
684 |
+
"50345": {
|
685 |
+
"content": "<child_of>",
|
686 |
+
"lstrip": false,
|
687 |
+
"normalized": true,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": false
|
691 |
+
},
|
692 |
+
"50346": {
|
693 |
+
"content": "</child_of>",
|
694 |
+
"lstrip": false,
|
695 |
+
"normalized": true,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": false
|
699 |
+
},
|
700 |
+
"50347": {
|
701 |
+
"content": "<child>",
|
702 |
+
"lstrip": false,
|
703 |
+
"normalized": true,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": false
|
707 |
+
},
|
708 |
+
"50348": {
|
709 |
+
"content": "</child>",
|
710 |
+
"lstrip": false,
|
711 |
+
"normalized": true,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": false
|
715 |
+
},
|
716 |
+
"50349": {
|
717 |
+
"content": "<text_body>",
|
718 |
+
"lstrip": false,
|
719 |
+
"normalized": true,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": false
|
723 |
+
},
|
724 |
+
"50350": {
|
725 |
+
"content": "</text_body>",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": true,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": false
|
731 |
+
},
|
732 |
+
"50351": {
|
733 |
+
"content": "%none%",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": true,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": false
|
739 |
+
},
|
740 |
+
"50352": {
|
741 |
+
"content": "%all%",
|
742 |
+
"lstrip": false,
|
743 |
+
"normalized": true,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": false
|
747 |
}
|
748 |
},
|
749 |
"bos_token": "<s>",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56818c0c4ed62b1dbb0c29adf0086733ac0686b55d51b44b8429e36ef5e8ec31
|
3 |
+
size 6712
|