borjasoutoprego
commited on
Commit
•
0658dfd
1
Parent(s):
6650432
End of training
Browse files- added_tokens.json +6 -34
- special_tokens_map.json +0 -196
- tokenizer.json +5 -257
- tokenizer_config.json +5 -257
added_tokens.json
CHANGED
@@ -1,41 +1,13 @@
|
|
1 |
{
|
2 |
-
"</s_address>":
|
3 |
-
"</
|
4 |
-
"</
|
5 |
-
"</s_date>": 57554,
|
6 |
-
"</s_description>": 57546,
|
7 |
-
"</s_discount>": 57552,
|
8 |
-
"</s_email>": 57550,
|
9 |
-
"</s_id>": 57544,
|
10 |
-
"</s_invoice_number>": 57548,
|
11 |
-
"</s_items>": 57536,
|
12 |
-
"</s_name>": 57542,
|
13 |
-
"</s_phone>": 57534,
|
14 |
-
"</s_price>": 57540,
|
15 |
-
"</s_qty>": 57538,
|
16 |
-
"</s_shipping>": 57532,
|
17 |
-
"</s_subtotal>": 57530,
|
18 |
-
"</s_tax>": 57528,
|
19 |
"</s_total>": 57526,
|
20 |
-
"<s_address>":
|
21 |
-
"<
|
22 |
-
"<
|
23 |
-
"<s_date>": 57553,
|
24 |
-
"<s_description>": 57545,
|
25 |
-
"<s_discount>": 57551,
|
26 |
-
"<s_email>": 57549,
|
27 |
-
"<s_id>": 57543,
|
28 |
"<s_iitcdip>": 57523,
|
29 |
-
"<s_invoice_number>": 57547,
|
30 |
-
"<s_items>": 57535,
|
31 |
-
"<s_name>": 57541,
|
32 |
-
"<s_phone>": 57533,
|
33 |
-
"<s_price>": 57539,
|
34 |
-
"<s_qty>": 57537,
|
35 |
-
"<s_shipping>": 57531,
|
36 |
-
"<s_subtotal>": 57529,
|
37 |
"<s_synthdog>": 57524,
|
38 |
-
"<s_tax>": 57527,
|
39 |
"<s_total>": 57525,
|
40 |
"<sep/>": 57522
|
41 |
}
|
|
|
1 |
{
|
2 |
+
"</s_address>": 57532,
|
3 |
+
"</s_company>": 57530,
|
4 |
+
"</s_date>": 57528,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"</s_total>": 57526,
|
6 |
+
"<s_address>": 57531,
|
7 |
+
"<s_company>": 57529,
|
8 |
+
"<s_date>": 57527,
|
|
|
|
|
|
|
|
|
|
|
9 |
"<s_iitcdip>": 57523,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"<s_synthdog>": 57524,
|
|
|
11 |
"<s_total>": 57525,
|
12 |
"<sep/>": 57522
|
13 |
}
|
special_tokens_map.json
CHANGED
@@ -14,188 +14,6 @@
|
|
14 |
"rstrip": false,
|
15 |
"single_word": false
|
16 |
},
|
17 |
-
{
|
18 |
-
"content": "<s_tax>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"content": "</s_tax>",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": false,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"content": "<s_subtotal>",
|
33 |
-
"lstrip": false,
|
34 |
-
"normalized": false,
|
35 |
-
"rstrip": false,
|
36 |
-
"single_word": false
|
37 |
-
},
|
38 |
-
{
|
39 |
-
"content": "</s_subtotal>",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false
|
44 |
-
},
|
45 |
-
{
|
46 |
-
"content": "<s_shipping>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"content": "</s_shipping>",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false
|
58 |
-
},
|
59 |
-
{
|
60 |
-
"content": "<s_phone>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": false,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false
|
65 |
-
},
|
66 |
-
{
|
67 |
-
"content": "</s_phone>",
|
68 |
-
"lstrip": false,
|
69 |
-
"normalized": false,
|
70 |
-
"rstrip": false,
|
71 |
-
"single_word": false
|
72 |
-
},
|
73 |
-
{
|
74 |
-
"content": "<s_items>",
|
75 |
-
"lstrip": false,
|
76 |
-
"normalized": false,
|
77 |
-
"rstrip": false,
|
78 |
-
"single_word": false
|
79 |
-
},
|
80 |
-
{
|
81 |
-
"content": "</s_items>",
|
82 |
-
"lstrip": false,
|
83 |
-
"normalized": false,
|
84 |
-
"rstrip": false,
|
85 |
-
"single_word": false
|
86 |
-
},
|
87 |
-
{
|
88 |
-
"content": "<s_qty>",
|
89 |
-
"lstrip": false,
|
90 |
-
"normalized": false,
|
91 |
-
"rstrip": false,
|
92 |
-
"single_word": false
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"content": "</s_qty>",
|
96 |
-
"lstrip": false,
|
97 |
-
"normalized": false,
|
98 |
-
"rstrip": false,
|
99 |
-
"single_word": false
|
100 |
-
},
|
101 |
-
{
|
102 |
-
"content": "<s_price>",
|
103 |
-
"lstrip": false,
|
104 |
-
"normalized": false,
|
105 |
-
"rstrip": false,
|
106 |
-
"single_word": false
|
107 |
-
},
|
108 |
-
{
|
109 |
-
"content": "</s_price>",
|
110 |
-
"lstrip": false,
|
111 |
-
"normalized": false,
|
112 |
-
"rstrip": false,
|
113 |
-
"single_word": false
|
114 |
-
},
|
115 |
-
{
|
116 |
-
"content": "<s_name>",
|
117 |
-
"lstrip": false,
|
118 |
-
"normalized": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"single_word": false
|
121 |
-
},
|
122 |
-
{
|
123 |
-
"content": "</s_name>",
|
124 |
-
"lstrip": false,
|
125 |
-
"normalized": false,
|
126 |
-
"rstrip": false,
|
127 |
-
"single_word": false
|
128 |
-
},
|
129 |
-
{
|
130 |
-
"content": "<s_id>",
|
131 |
-
"lstrip": false,
|
132 |
-
"normalized": false,
|
133 |
-
"rstrip": false,
|
134 |
-
"single_word": false
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"content": "</s_id>",
|
138 |
-
"lstrip": false,
|
139 |
-
"normalized": false,
|
140 |
-
"rstrip": false,
|
141 |
-
"single_word": false
|
142 |
-
},
|
143 |
-
{
|
144 |
-
"content": "<s_description>",
|
145 |
-
"lstrip": false,
|
146 |
-
"normalized": false,
|
147 |
-
"rstrip": false,
|
148 |
-
"single_word": false
|
149 |
-
},
|
150 |
-
{
|
151 |
-
"content": "</s_description>",
|
152 |
-
"lstrip": false,
|
153 |
-
"normalized": false,
|
154 |
-
"rstrip": false,
|
155 |
-
"single_word": false
|
156 |
-
},
|
157 |
-
{
|
158 |
-
"content": "<s_invoice_number>",
|
159 |
-
"lstrip": false,
|
160 |
-
"normalized": false,
|
161 |
-
"rstrip": false,
|
162 |
-
"single_word": false
|
163 |
-
},
|
164 |
-
{
|
165 |
-
"content": "</s_invoice_number>",
|
166 |
-
"lstrip": false,
|
167 |
-
"normalized": false,
|
168 |
-
"rstrip": false,
|
169 |
-
"single_word": false
|
170 |
-
},
|
171 |
-
{
|
172 |
-
"content": "<s_email>",
|
173 |
-
"lstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"rstrip": false,
|
176 |
-
"single_word": false
|
177 |
-
},
|
178 |
-
{
|
179 |
-
"content": "</s_email>",
|
180 |
-
"lstrip": false,
|
181 |
-
"normalized": false,
|
182 |
-
"rstrip": false,
|
183 |
-
"single_word": false
|
184 |
-
},
|
185 |
-
{
|
186 |
-
"content": "<s_discount>",
|
187 |
-
"lstrip": false,
|
188 |
-
"normalized": false,
|
189 |
-
"rstrip": false,
|
190 |
-
"single_word": false
|
191 |
-
},
|
192 |
-
{
|
193 |
-
"content": "</s_discount>",
|
194 |
-
"lstrip": false,
|
195 |
-
"normalized": false,
|
196 |
-
"rstrip": false,
|
197 |
-
"single_word": false
|
198 |
-
},
|
199 |
{
|
200 |
"content": "<s_date>",
|
201 |
"lstrip": false,
|
@@ -224,20 +42,6 @@
|
|
224 |
"rstrip": false,
|
225 |
"single_word": false
|
226 |
},
|
227 |
-
{
|
228 |
-
"content": "<s_buyer>",
|
229 |
-
"lstrip": false,
|
230 |
-
"normalized": false,
|
231 |
-
"rstrip": false,
|
232 |
-
"single_word": false
|
233 |
-
},
|
234 |
-
{
|
235 |
-
"content": "</s_buyer>",
|
236 |
-
"lstrip": false,
|
237 |
-
"normalized": false,
|
238 |
-
"rstrip": false,
|
239 |
-
"single_word": false
|
240 |
-
},
|
241 |
{
|
242 |
"content": "<s_address>",
|
243 |
"lstrip": false,
|
|
|
14 |
"rstrip": false,
|
15 |
"single_word": false
|
16 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
{
|
18 |
"content": "<s_date>",
|
19 |
"lstrip": false,
|
|
|
42 |
"rstrip": false,
|
43 |
"single_word": false
|
44 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
{
|
46 |
"content": "<s_address>",
|
47 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -109,240 +109,6 @@
|
|
109 |
},
|
110 |
{
|
111 |
"id": 57527,
|
112 |
-
"content": "<s_tax>",
|
113 |
-
"single_word": false,
|
114 |
-
"lstrip": false,
|
115 |
-
"rstrip": false,
|
116 |
-
"normalized": false,
|
117 |
-
"special": true
|
118 |
-
},
|
119 |
-
{
|
120 |
-
"id": 57528,
|
121 |
-
"content": "</s_tax>",
|
122 |
-
"single_word": false,
|
123 |
-
"lstrip": false,
|
124 |
-
"rstrip": false,
|
125 |
-
"normalized": false,
|
126 |
-
"special": true
|
127 |
-
},
|
128 |
-
{
|
129 |
-
"id": 57529,
|
130 |
-
"content": "<s_subtotal>",
|
131 |
-
"single_word": false,
|
132 |
-
"lstrip": false,
|
133 |
-
"rstrip": false,
|
134 |
-
"normalized": false,
|
135 |
-
"special": true
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"id": 57530,
|
139 |
-
"content": "</s_subtotal>",
|
140 |
-
"single_word": false,
|
141 |
-
"lstrip": false,
|
142 |
-
"rstrip": false,
|
143 |
-
"normalized": false,
|
144 |
-
"special": true
|
145 |
-
},
|
146 |
-
{
|
147 |
-
"id": 57531,
|
148 |
-
"content": "<s_shipping>",
|
149 |
-
"single_word": false,
|
150 |
-
"lstrip": false,
|
151 |
-
"rstrip": false,
|
152 |
-
"normalized": false,
|
153 |
-
"special": true
|
154 |
-
},
|
155 |
-
{
|
156 |
-
"id": 57532,
|
157 |
-
"content": "</s_shipping>",
|
158 |
-
"single_word": false,
|
159 |
-
"lstrip": false,
|
160 |
-
"rstrip": false,
|
161 |
-
"normalized": false,
|
162 |
-
"special": true
|
163 |
-
},
|
164 |
-
{
|
165 |
-
"id": 57533,
|
166 |
-
"content": "<s_phone>",
|
167 |
-
"single_word": false,
|
168 |
-
"lstrip": false,
|
169 |
-
"rstrip": false,
|
170 |
-
"normalized": false,
|
171 |
-
"special": true
|
172 |
-
},
|
173 |
-
{
|
174 |
-
"id": 57534,
|
175 |
-
"content": "</s_phone>",
|
176 |
-
"single_word": false,
|
177 |
-
"lstrip": false,
|
178 |
-
"rstrip": false,
|
179 |
-
"normalized": false,
|
180 |
-
"special": true
|
181 |
-
},
|
182 |
-
{
|
183 |
-
"id": 57535,
|
184 |
-
"content": "<s_items>",
|
185 |
-
"single_word": false,
|
186 |
-
"lstrip": false,
|
187 |
-
"rstrip": false,
|
188 |
-
"normalized": false,
|
189 |
-
"special": true
|
190 |
-
},
|
191 |
-
{
|
192 |
-
"id": 57536,
|
193 |
-
"content": "</s_items>",
|
194 |
-
"single_word": false,
|
195 |
-
"lstrip": false,
|
196 |
-
"rstrip": false,
|
197 |
-
"normalized": false,
|
198 |
-
"special": true
|
199 |
-
},
|
200 |
-
{
|
201 |
-
"id": 57537,
|
202 |
-
"content": "<s_qty>",
|
203 |
-
"single_word": false,
|
204 |
-
"lstrip": false,
|
205 |
-
"rstrip": false,
|
206 |
-
"normalized": false,
|
207 |
-
"special": true
|
208 |
-
},
|
209 |
-
{
|
210 |
-
"id": 57538,
|
211 |
-
"content": "</s_qty>",
|
212 |
-
"single_word": false,
|
213 |
-
"lstrip": false,
|
214 |
-
"rstrip": false,
|
215 |
-
"normalized": false,
|
216 |
-
"special": true
|
217 |
-
},
|
218 |
-
{
|
219 |
-
"id": 57539,
|
220 |
-
"content": "<s_price>",
|
221 |
-
"single_word": false,
|
222 |
-
"lstrip": false,
|
223 |
-
"rstrip": false,
|
224 |
-
"normalized": false,
|
225 |
-
"special": true
|
226 |
-
},
|
227 |
-
{
|
228 |
-
"id": 57540,
|
229 |
-
"content": "</s_price>",
|
230 |
-
"single_word": false,
|
231 |
-
"lstrip": false,
|
232 |
-
"rstrip": false,
|
233 |
-
"normalized": false,
|
234 |
-
"special": true
|
235 |
-
},
|
236 |
-
{
|
237 |
-
"id": 57541,
|
238 |
-
"content": "<s_name>",
|
239 |
-
"single_word": false,
|
240 |
-
"lstrip": false,
|
241 |
-
"rstrip": false,
|
242 |
-
"normalized": false,
|
243 |
-
"special": true
|
244 |
-
},
|
245 |
-
{
|
246 |
-
"id": 57542,
|
247 |
-
"content": "</s_name>",
|
248 |
-
"single_word": false,
|
249 |
-
"lstrip": false,
|
250 |
-
"rstrip": false,
|
251 |
-
"normalized": false,
|
252 |
-
"special": true
|
253 |
-
},
|
254 |
-
{
|
255 |
-
"id": 57543,
|
256 |
-
"content": "<s_id>",
|
257 |
-
"single_word": false,
|
258 |
-
"lstrip": false,
|
259 |
-
"rstrip": false,
|
260 |
-
"normalized": false,
|
261 |
-
"special": true
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"id": 57544,
|
265 |
-
"content": "</s_id>",
|
266 |
-
"single_word": false,
|
267 |
-
"lstrip": false,
|
268 |
-
"rstrip": false,
|
269 |
-
"normalized": false,
|
270 |
-
"special": true
|
271 |
-
},
|
272 |
-
{
|
273 |
-
"id": 57545,
|
274 |
-
"content": "<s_description>",
|
275 |
-
"single_word": false,
|
276 |
-
"lstrip": false,
|
277 |
-
"rstrip": false,
|
278 |
-
"normalized": false,
|
279 |
-
"special": true
|
280 |
-
},
|
281 |
-
{
|
282 |
-
"id": 57546,
|
283 |
-
"content": "</s_description>",
|
284 |
-
"single_word": false,
|
285 |
-
"lstrip": false,
|
286 |
-
"rstrip": false,
|
287 |
-
"normalized": false,
|
288 |
-
"special": true
|
289 |
-
},
|
290 |
-
{
|
291 |
-
"id": 57547,
|
292 |
-
"content": "<s_invoice_number>",
|
293 |
-
"single_word": false,
|
294 |
-
"lstrip": false,
|
295 |
-
"rstrip": false,
|
296 |
-
"normalized": false,
|
297 |
-
"special": true
|
298 |
-
},
|
299 |
-
{
|
300 |
-
"id": 57548,
|
301 |
-
"content": "</s_invoice_number>",
|
302 |
-
"single_word": false,
|
303 |
-
"lstrip": false,
|
304 |
-
"rstrip": false,
|
305 |
-
"normalized": false,
|
306 |
-
"special": true
|
307 |
-
},
|
308 |
-
{
|
309 |
-
"id": 57549,
|
310 |
-
"content": "<s_email>",
|
311 |
-
"single_word": false,
|
312 |
-
"lstrip": false,
|
313 |
-
"rstrip": false,
|
314 |
-
"normalized": false,
|
315 |
-
"special": true
|
316 |
-
},
|
317 |
-
{
|
318 |
-
"id": 57550,
|
319 |
-
"content": "</s_email>",
|
320 |
-
"single_word": false,
|
321 |
-
"lstrip": false,
|
322 |
-
"rstrip": false,
|
323 |
-
"normalized": false,
|
324 |
-
"special": true
|
325 |
-
},
|
326 |
-
{
|
327 |
-
"id": 57551,
|
328 |
-
"content": "<s_discount>",
|
329 |
-
"single_word": false,
|
330 |
-
"lstrip": false,
|
331 |
-
"rstrip": false,
|
332 |
-
"normalized": false,
|
333 |
-
"special": true
|
334 |
-
},
|
335 |
-
{
|
336 |
-
"id": 57552,
|
337 |
-
"content": "</s_discount>",
|
338 |
-
"single_word": false,
|
339 |
-
"lstrip": false,
|
340 |
-
"rstrip": false,
|
341 |
-
"normalized": false,
|
342 |
-
"special": true
|
343 |
-
},
|
344 |
-
{
|
345 |
-
"id": 57553,
|
346 |
"content": "<s_date>",
|
347 |
"single_word": false,
|
348 |
"lstrip": false,
|
@@ -351,7 +117,7 @@
|
|
351 |
"special": true
|
352 |
},
|
353 |
{
|
354 |
-
"id":
|
355 |
"content": "</s_date>",
|
356 |
"single_word": false,
|
357 |
"lstrip": false,
|
@@ -360,7 +126,7 @@
|
|
360 |
"special": true
|
361 |
},
|
362 |
{
|
363 |
-
"id":
|
364 |
"content": "<s_company>",
|
365 |
"single_word": false,
|
366 |
"lstrip": false,
|
@@ -369,7 +135,7 @@
|
|
369 |
"special": true
|
370 |
},
|
371 |
{
|
372 |
-
"id":
|
373 |
"content": "</s_company>",
|
374 |
"single_word": false,
|
375 |
"lstrip": false,
|
@@ -378,25 +144,7 @@
|
|
378 |
"special": true
|
379 |
},
|
380 |
{
|
381 |
-
"id":
|
382 |
-
"content": "<s_buyer>",
|
383 |
-
"single_word": false,
|
384 |
-
"lstrip": false,
|
385 |
-
"rstrip": false,
|
386 |
-
"normalized": false,
|
387 |
-
"special": true
|
388 |
-
},
|
389 |
-
{
|
390 |
-
"id": 57558,
|
391 |
-
"content": "</s_buyer>",
|
392 |
-
"single_word": false,
|
393 |
-
"lstrip": false,
|
394 |
-
"rstrip": false,
|
395 |
-
"normalized": false,
|
396 |
-
"special": true
|
397 |
-
},
|
398 |
-
{
|
399 |
-
"id": 57559,
|
400 |
"content": "<s_address>",
|
401 |
"single_word": false,
|
402 |
"lstrip": false,
|
@@ -405,7 +153,7 @@
|
|
405 |
"special": true
|
406 |
},
|
407 |
{
|
408 |
-
"id":
|
409 |
"content": "</s_address>",
|
410 |
"single_word": false,
|
411 |
"lstrip": false,
|
|
|
109 |
},
|
110 |
{
|
111 |
"id": 57527,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
112 |
"content": "<s_date>",
|
113 |
"single_word": false,
|
114 |
"lstrip": false,
|
|
|
117 |
"special": true
|
118 |
},
|
119 |
{
|
120 |
+
"id": 57528,
|
121 |
"content": "</s_date>",
|
122 |
"single_word": false,
|
123 |
"lstrip": false,
|
|
|
126 |
"special": true
|
127 |
},
|
128 |
{
|
129 |
+
"id": 57529,
|
130 |
"content": "<s_company>",
|
131 |
"single_word": false,
|
132 |
"lstrip": false,
|
|
|
135 |
"special": true
|
136 |
},
|
137 |
{
|
138 |
+
"id": 57530,
|
139 |
"content": "</s_company>",
|
140 |
"single_word": false,
|
141 |
"lstrip": false,
|
|
|
144 |
"special": true
|
145 |
},
|
146 |
{
|
147 |
+
"id": 57531,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
148 |
"content": "<s_address>",
|
149 |
"single_word": false,
|
150 |
"lstrip": false,
|
|
|
153 |
"special": true
|
154 |
},
|
155 |
{
|
156 |
+
"id": 57532,
|
157 |
"content": "</s_address>",
|
158 |
"single_word": false,
|
159 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -81,214 +81,6 @@
|
|
81 |
"special": true
|
82 |
},
|
83 |
"57527": {
|
84 |
-
"content": "<s_tax>",
|
85 |
-
"lstrip": false,
|
86 |
-
"normalized": false,
|
87 |
-
"rstrip": false,
|
88 |
-
"single_word": false,
|
89 |
-
"special": true
|
90 |
-
},
|
91 |
-
"57528": {
|
92 |
-
"content": "</s_tax>",
|
93 |
-
"lstrip": false,
|
94 |
-
"normalized": false,
|
95 |
-
"rstrip": false,
|
96 |
-
"single_word": false,
|
97 |
-
"special": true
|
98 |
-
},
|
99 |
-
"57529": {
|
100 |
-
"content": "<s_subtotal>",
|
101 |
-
"lstrip": false,
|
102 |
-
"normalized": false,
|
103 |
-
"rstrip": false,
|
104 |
-
"single_word": false,
|
105 |
-
"special": true
|
106 |
-
},
|
107 |
-
"57530": {
|
108 |
-
"content": "</s_subtotal>",
|
109 |
-
"lstrip": false,
|
110 |
-
"normalized": false,
|
111 |
-
"rstrip": false,
|
112 |
-
"single_word": false,
|
113 |
-
"special": true
|
114 |
-
},
|
115 |
-
"57531": {
|
116 |
-
"content": "<s_shipping>",
|
117 |
-
"lstrip": false,
|
118 |
-
"normalized": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"single_word": false,
|
121 |
-
"special": true
|
122 |
-
},
|
123 |
-
"57532": {
|
124 |
-
"content": "</s_shipping>",
|
125 |
-
"lstrip": false,
|
126 |
-
"normalized": false,
|
127 |
-
"rstrip": false,
|
128 |
-
"single_word": false,
|
129 |
-
"special": true
|
130 |
-
},
|
131 |
-
"57533": {
|
132 |
-
"content": "<s_phone>",
|
133 |
-
"lstrip": false,
|
134 |
-
"normalized": false,
|
135 |
-
"rstrip": false,
|
136 |
-
"single_word": false,
|
137 |
-
"special": true
|
138 |
-
},
|
139 |
-
"57534": {
|
140 |
-
"content": "</s_phone>",
|
141 |
-
"lstrip": false,
|
142 |
-
"normalized": false,
|
143 |
-
"rstrip": false,
|
144 |
-
"single_word": false,
|
145 |
-
"special": true
|
146 |
-
},
|
147 |
-
"57535": {
|
148 |
-
"content": "<s_items>",
|
149 |
-
"lstrip": false,
|
150 |
-
"normalized": false,
|
151 |
-
"rstrip": false,
|
152 |
-
"single_word": false,
|
153 |
-
"special": true
|
154 |
-
},
|
155 |
-
"57536": {
|
156 |
-
"content": "</s_items>",
|
157 |
-
"lstrip": false,
|
158 |
-
"normalized": false,
|
159 |
-
"rstrip": false,
|
160 |
-
"single_word": false,
|
161 |
-
"special": true
|
162 |
-
},
|
163 |
-
"57537": {
|
164 |
-
"content": "<s_qty>",
|
165 |
-
"lstrip": false,
|
166 |
-
"normalized": false,
|
167 |
-
"rstrip": false,
|
168 |
-
"single_word": false,
|
169 |
-
"special": true
|
170 |
-
},
|
171 |
-
"57538": {
|
172 |
-
"content": "</s_qty>",
|
173 |
-
"lstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"rstrip": false,
|
176 |
-
"single_word": false,
|
177 |
-
"special": true
|
178 |
-
},
|
179 |
-
"57539": {
|
180 |
-
"content": "<s_price>",
|
181 |
-
"lstrip": false,
|
182 |
-
"normalized": false,
|
183 |
-
"rstrip": false,
|
184 |
-
"single_word": false,
|
185 |
-
"special": true
|
186 |
-
},
|
187 |
-
"57540": {
|
188 |
-
"content": "</s_price>",
|
189 |
-
"lstrip": false,
|
190 |
-
"normalized": false,
|
191 |
-
"rstrip": false,
|
192 |
-
"single_word": false,
|
193 |
-
"special": true
|
194 |
-
},
|
195 |
-
"57541": {
|
196 |
-
"content": "<s_name>",
|
197 |
-
"lstrip": false,
|
198 |
-
"normalized": false,
|
199 |
-
"rstrip": false,
|
200 |
-
"single_word": false,
|
201 |
-
"special": true
|
202 |
-
},
|
203 |
-
"57542": {
|
204 |
-
"content": "</s_name>",
|
205 |
-
"lstrip": false,
|
206 |
-
"normalized": false,
|
207 |
-
"rstrip": false,
|
208 |
-
"single_word": false,
|
209 |
-
"special": true
|
210 |
-
},
|
211 |
-
"57543": {
|
212 |
-
"content": "<s_id>",
|
213 |
-
"lstrip": false,
|
214 |
-
"normalized": false,
|
215 |
-
"rstrip": false,
|
216 |
-
"single_word": false,
|
217 |
-
"special": true
|
218 |
-
},
|
219 |
-
"57544": {
|
220 |
-
"content": "</s_id>",
|
221 |
-
"lstrip": false,
|
222 |
-
"normalized": false,
|
223 |
-
"rstrip": false,
|
224 |
-
"single_word": false,
|
225 |
-
"special": true
|
226 |
-
},
|
227 |
-
"57545": {
|
228 |
-
"content": "<s_description>",
|
229 |
-
"lstrip": false,
|
230 |
-
"normalized": false,
|
231 |
-
"rstrip": false,
|
232 |
-
"single_word": false,
|
233 |
-
"special": true
|
234 |
-
},
|
235 |
-
"57546": {
|
236 |
-
"content": "</s_description>",
|
237 |
-
"lstrip": false,
|
238 |
-
"normalized": false,
|
239 |
-
"rstrip": false,
|
240 |
-
"single_word": false,
|
241 |
-
"special": true
|
242 |
-
},
|
243 |
-
"57547": {
|
244 |
-
"content": "<s_invoice_number>",
|
245 |
-
"lstrip": false,
|
246 |
-
"normalized": false,
|
247 |
-
"rstrip": false,
|
248 |
-
"single_word": false,
|
249 |
-
"special": true
|
250 |
-
},
|
251 |
-
"57548": {
|
252 |
-
"content": "</s_invoice_number>",
|
253 |
-
"lstrip": false,
|
254 |
-
"normalized": false,
|
255 |
-
"rstrip": false,
|
256 |
-
"single_word": false,
|
257 |
-
"special": true
|
258 |
-
},
|
259 |
-
"57549": {
|
260 |
-
"content": "<s_email>",
|
261 |
-
"lstrip": false,
|
262 |
-
"normalized": false,
|
263 |
-
"rstrip": false,
|
264 |
-
"single_word": false,
|
265 |
-
"special": true
|
266 |
-
},
|
267 |
-
"57550": {
|
268 |
-
"content": "</s_email>",
|
269 |
-
"lstrip": false,
|
270 |
-
"normalized": false,
|
271 |
-
"rstrip": false,
|
272 |
-
"single_word": false,
|
273 |
-
"special": true
|
274 |
-
},
|
275 |
-
"57551": {
|
276 |
-
"content": "<s_discount>",
|
277 |
-
"lstrip": false,
|
278 |
-
"normalized": false,
|
279 |
-
"rstrip": false,
|
280 |
-
"single_word": false,
|
281 |
-
"special": true
|
282 |
-
},
|
283 |
-
"57552": {
|
284 |
-
"content": "</s_discount>",
|
285 |
-
"lstrip": false,
|
286 |
-
"normalized": false,
|
287 |
-
"rstrip": false,
|
288 |
-
"single_word": false,
|
289 |
-
"special": true
|
290 |
-
},
|
291 |
-
"57553": {
|
292 |
"content": "<s_date>",
|
293 |
"lstrip": false,
|
294 |
"normalized": false,
|
@@ -296,7 +88,7 @@
|
|
296 |
"single_word": false,
|
297 |
"special": true
|
298 |
},
|
299 |
-
"
|
300 |
"content": "</s_date>",
|
301 |
"lstrip": false,
|
302 |
"normalized": false,
|
@@ -304,7 +96,7 @@
|
|
304 |
"single_word": false,
|
305 |
"special": true
|
306 |
},
|
307 |
-
"
|
308 |
"content": "<s_company>",
|
309 |
"lstrip": false,
|
310 |
"normalized": false,
|
@@ -312,7 +104,7 @@
|
|
312 |
"single_word": false,
|
313 |
"special": true
|
314 |
},
|
315 |
-
"
|
316 |
"content": "</s_company>",
|
317 |
"lstrip": false,
|
318 |
"normalized": false,
|
@@ -320,23 +112,7 @@
|
|
320 |
"single_word": false,
|
321 |
"special": true
|
322 |
},
|
323 |
-
"
|
324 |
-
"content": "<s_buyer>",
|
325 |
-
"lstrip": false,
|
326 |
-
"normalized": false,
|
327 |
-
"rstrip": false,
|
328 |
-
"single_word": false,
|
329 |
-
"special": true
|
330 |
-
},
|
331 |
-
"57558": {
|
332 |
-
"content": "</s_buyer>",
|
333 |
-
"lstrip": false,
|
334 |
-
"normalized": false,
|
335 |
-
"rstrip": false,
|
336 |
-
"single_word": false,
|
337 |
-
"special": true
|
338 |
-
},
|
339 |
-
"57559": {
|
340 |
"content": "<s_address>",
|
341 |
"lstrip": false,
|
342 |
"normalized": false,
|
@@ -344,7 +120,7 @@
|
|
344 |
"single_word": false,
|
345 |
"special": true
|
346 |
},
|
347 |
-
"
|
348 |
"content": "</s_address>",
|
349 |
"lstrip": false,
|
350 |
"normalized": false,
|
@@ -356,38 +132,10 @@
|
|
356 |
"additional_special_tokens": [
|
357 |
"<s_total>",
|
358 |
"</s_total>",
|
359 |
-
"<s_tax>",
|
360 |
-
"</s_tax>",
|
361 |
-
"<s_subtotal>",
|
362 |
-
"</s_subtotal>",
|
363 |
-
"<s_shipping>",
|
364 |
-
"</s_shipping>",
|
365 |
-
"<s_phone>",
|
366 |
-
"</s_phone>",
|
367 |
-
"<s_items>",
|
368 |
-
"</s_items>",
|
369 |
-
"<s_qty>",
|
370 |
-
"</s_qty>",
|
371 |
-
"<s_price>",
|
372 |
-
"</s_price>",
|
373 |
-
"<s_name>",
|
374 |
-
"</s_name>",
|
375 |
-
"<s_id>",
|
376 |
-
"</s_id>",
|
377 |
-
"<s_description>",
|
378 |
-
"</s_description>",
|
379 |
-
"<s_invoice_number>",
|
380 |
-
"</s_invoice_number>",
|
381 |
-
"<s_email>",
|
382 |
-
"</s_email>",
|
383 |
-
"<s_discount>",
|
384 |
-
"</s_discount>",
|
385 |
"<s_date>",
|
386 |
"</s_date>",
|
387 |
"<s_company>",
|
388 |
"</s_company>",
|
389 |
-
"<s_buyer>",
|
390 |
-
"</s_buyer>",
|
391 |
"<s_address>",
|
392 |
"</s_address>",
|
393 |
"<s>",
|
|
|
81 |
"special": true
|
82 |
},
|
83 |
"57527": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
"content": "<s_date>",
|
85 |
"lstrip": false,
|
86 |
"normalized": false,
|
|
|
88 |
"single_word": false,
|
89 |
"special": true
|
90 |
},
|
91 |
+
"57528": {
|
92 |
"content": "</s_date>",
|
93 |
"lstrip": false,
|
94 |
"normalized": false,
|
|
|
96 |
"single_word": false,
|
97 |
"special": true
|
98 |
},
|
99 |
+
"57529": {
|
100 |
"content": "<s_company>",
|
101 |
"lstrip": false,
|
102 |
"normalized": false,
|
|
|
104 |
"single_word": false,
|
105 |
"special": true
|
106 |
},
|
107 |
+
"57530": {
|
108 |
"content": "</s_company>",
|
109 |
"lstrip": false,
|
110 |
"normalized": false,
|
|
|
112 |
"single_word": false,
|
113 |
"special": true
|
114 |
},
|
115 |
+
"57531": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
116 |
"content": "<s_address>",
|
117 |
"lstrip": false,
|
118 |
"normalized": false,
|
|
|
120 |
"single_word": false,
|
121 |
"special": true
|
122 |
},
|
123 |
+
"57532": {
|
124 |
"content": "</s_address>",
|
125 |
"lstrip": false,
|
126 |
"normalized": false,
|
|
|
132 |
"additional_special_tokens": [
|
133 |
"<s_total>",
|
134 |
"</s_total>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
135 |
"<s_date>",
|
136 |
"</s_date>",
|
137 |
"<s_company>",
|
138 |
"</s_company>",
|
|
|
|
|
139 |
"<s_address>",
|
140 |
"</s_address>",
|
141 |
"<s>",
|