Training done
Browse files- added_tokens.json +21 -15
- tokenizer.json +68 -14
- tokenizer_config.json +62 -14
added_tokens.json
CHANGED
@@ -1,20 +1,26 @@
|
|
1 |
{
|
2 |
-
"</
|
3 |
-
"</
|
4 |
-
"</s_item_desc>":
|
5 |
-
"</
|
6 |
-
"</
|
7 |
-
"</
|
8 |
-
"</
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
|
|
|
|
11 |
"<s_iitcdip>": 57523,
|
12 |
-
"<
|
13 |
-
"<
|
14 |
-
"<s_item_qty>":
|
15 |
-
"<
|
16 |
-
"<
|
|
|
|
|
17 |
"<s_synthdog>": 57524,
|
18 |
-
"<s_total_vat>":
|
19 |
"<sep/>": 57522
|
20 |
}
|
|
|
1 |
{
|
2 |
+
"</s_date>": 57540,
|
3 |
+
"</s_header>": 57538,
|
4 |
+
"</s_item_desc>": 57528,
|
5 |
+
"</s_item_price>": 57530,
|
6 |
+
"</s_item_qty>": 57532,
|
7 |
+
"</s_item_ref>": 57544,
|
8 |
+
"</s_items>": 57526,
|
9 |
+
"</s_quotation_no>": 57542,
|
10 |
+
"</s_summary>": 57534,
|
11 |
+
"</s_total_vat>": 57536,
|
12 |
+
"<s_cord-v2>": 57545,
|
13 |
+
"<s_date>": 57539,
|
14 |
+
"<s_header>": 57537,
|
15 |
"<s_iitcdip>": 57523,
|
16 |
+
"<s_item_desc>": 57527,
|
17 |
+
"<s_item_price>": 57529,
|
18 |
+
"<s_item_qty>": 57531,
|
19 |
+
"<s_item_ref>": 57543,
|
20 |
+
"<s_items>": 57525,
|
21 |
+
"<s_quotation_no>": 57541,
|
22 |
+
"<s_summary>": 57533,
|
23 |
"<s_synthdog>": 57524,
|
24 |
+
"<s_total_vat>": 57535,
|
25 |
"<sep/>": 57522
|
26 |
}
|
tokenizer.json
CHANGED
@@ -91,7 +91,7 @@
|
|
91 |
},
|
92 |
{
|
93 |
"id": 57525,
|
94 |
-
"content": "<
|
95 |
"single_word": false,
|
96 |
"lstrip": false,
|
97 |
"rstrip": false,
|
@@ -100,7 +100,7 @@
|
|
100 |
},
|
101 |
{
|
102 |
"id": 57526,
|
103 |
-
"content": "</
|
104 |
"single_word": false,
|
105 |
"lstrip": false,
|
106 |
"rstrip": false,
|
@@ -109,7 +109,7 @@
|
|
109 |
},
|
110 |
{
|
111 |
"id": 57527,
|
112 |
-
"content": "<
|
113 |
"single_word": false,
|
114 |
"lstrip": false,
|
115 |
"rstrip": false,
|
@@ -118,7 +118,7 @@
|
|
118 |
},
|
119 |
{
|
120 |
"id": 57528,
|
121 |
-
"content": "</
|
122 |
"single_word": false,
|
123 |
"lstrip": false,
|
124 |
"rstrip": false,
|
@@ -127,7 +127,7 @@
|
|
127 |
},
|
128 |
{
|
129 |
"id": 57529,
|
130 |
-
"content": "<
|
131 |
"single_word": false,
|
132 |
"lstrip": false,
|
133 |
"rstrip": false,
|
@@ -136,7 +136,7 @@
|
|
136 |
},
|
137 |
{
|
138 |
"id": 57530,
|
139 |
-
"content": "</
|
140 |
"single_word": false,
|
141 |
"lstrip": false,
|
142 |
"rstrip": false,
|
@@ -145,7 +145,7 @@
|
|
145 |
},
|
146 |
{
|
147 |
"id": 57531,
|
148 |
-
"content": "<
|
149 |
"single_word": false,
|
150 |
"lstrip": false,
|
151 |
"rstrip": false,
|
@@ -154,7 +154,7 @@
|
|
154 |
},
|
155 |
{
|
156 |
"id": 57532,
|
157 |
-
"content": "</
|
158 |
"single_word": false,
|
159 |
"lstrip": false,
|
160 |
"rstrip": false,
|
@@ -163,7 +163,7 @@
|
|
163 |
},
|
164 |
{
|
165 |
"id": 57533,
|
166 |
-
"content": "<
|
167 |
"single_word": false,
|
168 |
"lstrip": false,
|
169 |
"rstrip": false,
|
@@ -172,7 +172,7 @@
|
|
172 |
},
|
173 |
{
|
174 |
"id": 57534,
|
175 |
-
"content": "</
|
176 |
"single_word": false,
|
177 |
"lstrip": false,
|
178 |
"rstrip": false,
|
@@ -181,7 +181,7 @@
|
|
181 |
},
|
182 |
{
|
183 |
"id": 57535,
|
184 |
-
"content": "<
|
185 |
"single_word": false,
|
186 |
"lstrip": false,
|
187 |
"rstrip": false,
|
@@ -190,7 +190,7 @@
|
|
190 |
},
|
191 |
{
|
192 |
"id": 57536,
|
193 |
-
"content": "</
|
194 |
"single_word": false,
|
195 |
"lstrip": false,
|
196 |
"rstrip": false,
|
@@ -199,7 +199,7 @@
|
|
199 |
},
|
200 |
{
|
201 |
"id": 57537,
|
202 |
-
"content": "<
|
203 |
"single_word": false,
|
204 |
"lstrip": false,
|
205 |
"rstrip": false,
|
@@ -208,7 +208,7 @@
|
|
208 |
},
|
209 |
{
|
210 |
"id": 57538,
|
211 |
-
"content": "</
|
212 |
"single_word": false,
|
213 |
"lstrip": false,
|
214 |
"rstrip": false,
|
@@ -217,6 +217,60 @@
|
|
217 |
},
|
218 |
{
|
219 |
"id": 57539,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
"content": "<s_cord-v2>",
|
221 |
"single_word": false,
|
222 |
"lstrip": false,
|
|
|
91 |
},
|
92 |
{
|
93 |
"id": 57525,
|
94 |
+
"content": "<s_items>",
|
95 |
"single_word": false,
|
96 |
"lstrip": false,
|
97 |
"rstrip": false,
|
|
|
100 |
},
|
101 |
{
|
102 |
"id": 57526,
|
103 |
+
"content": "</s_items>",
|
104 |
"single_word": false,
|
105 |
"lstrip": false,
|
106 |
"rstrip": false,
|
|
|
109 |
},
|
110 |
{
|
111 |
"id": 57527,
|
112 |
+
"content": "<s_item_desc>",
|
113 |
"single_word": false,
|
114 |
"lstrip": false,
|
115 |
"rstrip": false,
|
|
|
118 |
},
|
119 |
{
|
120 |
"id": 57528,
|
121 |
+
"content": "</s_item_desc>",
|
122 |
"single_word": false,
|
123 |
"lstrip": false,
|
124 |
"rstrip": false,
|
|
|
127 |
},
|
128 |
{
|
129 |
"id": 57529,
|
130 |
+
"content": "<s_item_price>",
|
131 |
"single_word": false,
|
132 |
"lstrip": false,
|
133 |
"rstrip": false,
|
|
|
136 |
},
|
137 |
{
|
138 |
"id": 57530,
|
139 |
+
"content": "</s_item_price>",
|
140 |
"single_word": false,
|
141 |
"lstrip": false,
|
142 |
"rstrip": false,
|
|
|
145 |
},
|
146 |
{
|
147 |
"id": 57531,
|
148 |
+
"content": "<s_item_qty>",
|
149 |
"single_word": false,
|
150 |
"lstrip": false,
|
151 |
"rstrip": false,
|
|
|
154 |
},
|
155 |
{
|
156 |
"id": 57532,
|
157 |
+
"content": "</s_item_qty>",
|
158 |
"single_word": false,
|
159 |
"lstrip": false,
|
160 |
"rstrip": false,
|
|
|
163 |
},
|
164 |
{
|
165 |
"id": 57533,
|
166 |
+
"content": "<s_summary>",
|
167 |
"single_word": false,
|
168 |
"lstrip": false,
|
169 |
"rstrip": false,
|
|
|
172 |
},
|
173 |
{
|
174 |
"id": 57534,
|
175 |
+
"content": "</s_summary>",
|
176 |
"single_word": false,
|
177 |
"lstrip": false,
|
178 |
"rstrip": false,
|
|
|
181 |
},
|
182 |
{
|
183 |
"id": 57535,
|
184 |
+
"content": "<s_total_vat>",
|
185 |
"single_word": false,
|
186 |
"lstrip": false,
|
187 |
"rstrip": false,
|
|
|
190 |
},
|
191 |
{
|
192 |
"id": 57536,
|
193 |
+
"content": "</s_total_vat>",
|
194 |
"single_word": false,
|
195 |
"lstrip": false,
|
196 |
"rstrip": false,
|
|
|
199 |
},
|
200 |
{
|
201 |
"id": 57537,
|
202 |
+
"content": "<s_header>",
|
203 |
"single_word": false,
|
204 |
"lstrip": false,
|
205 |
"rstrip": false,
|
|
|
208 |
},
|
209 |
{
|
210 |
"id": 57538,
|
211 |
+
"content": "</s_header>",
|
212 |
"single_word": false,
|
213 |
"lstrip": false,
|
214 |
"rstrip": false,
|
|
|
217 |
},
|
218 |
{
|
219 |
"id": 57539,
|
220 |
+
"content": "<s_date>",
|
221 |
+
"single_word": false,
|
222 |
+
"lstrip": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"normalized": true,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"id": 57540,
|
229 |
+
"content": "</s_date>",
|
230 |
+
"single_word": false,
|
231 |
+
"lstrip": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"normalized": true,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"id": 57541,
|
238 |
+
"content": "<s_quotation_no>",
|
239 |
+
"single_word": false,
|
240 |
+
"lstrip": false,
|
241 |
+
"rstrip": false,
|
242 |
+
"normalized": true,
|
243 |
+
"special": false
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"id": 57542,
|
247 |
+
"content": "</s_quotation_no>",
|
248 |
+
"single_word": false,
|
249 |
+
"lstrip": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"normalized": true,
|
252 |
+
"special": false
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"id": 57543,
|
256 |
+
"content": "<s_item_ref>",
|
257 |
+
"single_word": false,
|
258 |
+
"lstrip": false,
|
259 |
+
"rstrip": false,
|
260 |
+
"normalized": true,
|
261 |
+
"special": false
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"id": 57544,
|
265 |
+
"content": "</s_item_ref>",
|
266 |
+
"single_word": false,
|
267 |
+
"lstrip": false,
|
268 |
+
"rstrip": false,
|
269 |
+
"normalized": true,
|
270 |
+
"special": false
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"id": 57545,
|
274 |
"content": "<s_cord-v2>",
|
275 |
"single_word": false,
|
276 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -65,7 +65,7 @@
|
|
65 |
"special": true
|
66 |
},
|
67 |
"57525": {
|
68 |
-
"content": "<
|
69 |
"lstrip": false,
|
70 |
"normalized": true,
|
71 |
"rstrip": false,
|
@@ -73,7 +73,7 @@
|
|
73 |
"special": false
|
74 |
},
|
75 |
"57526": {
|
76 |
-
"content": "</
|
77 |
"lstrip": false,
|
78 |
"normalized": true,
|
79 |
"rstrip": false,
|
@@ -81,7 +81,7 @@
|
|
81 |
"special": false
|
82 |
},
|
83 |
"57527": {
|
84 |
-
"content": "<
|
85 |
"lstrip": false,
|
86 |
"normalized": true,
|
87 |
"rstrip": false,
|
@@ -89,7 +89,7 @@
|
|
89 |
"special": false
|
90 |
},
|
91 |
"57528": {
|
92 |
-
"content": "</
|
93 |
"lstrip": false,
|
94 |
"normalized": true,
|
95 |
"rstrip": false,
|
@@ -97,7 +97,7 @@
|
|
97 |
"special": false
|
98 |
},
|
99 |
"57529": {
|
100 |
-
"content": "<
|
101 |
"lstrip": false,
|
102 |
"normalized": true,
|
103 |
"rstrip": false,
|
@@ -105,7 +105,7 @@
|
|
105 |
"special": false
|
106 |
},
|
107 |
"57530": {
|
108 |
-
"content": "</
|
109 |
"lstrip": false,
|
110 |
"normalized": true,
|
111 |
"rstrip": false,
|
@@ -113,7 +113,7 @@
|
|
113 |
"special": false
|
114 |
},
|
115 |
"57531": {
|
116 |
-
"content": "<
|
117 |
"lstrip": false,
|
118 |
"normalized": true,
|
119 |
"rstrip": false,
|
@@ -121,7 +121,7 @@
|
|
121 |
"special": false
|
122 |
},
|
123 |
"57532": {
|
124 |
-
"content": "</
|
125 |
"lstrip": false,
|
126 |
"normalized": true,
|
127 |
"rstrip": false,
|
@@ -129,7 +129,7 @@
|
|
129 |
"special": false
|
130 |
},
|
131 |
"57533": {
|
132 |
-
"content": "<
|
133 |
"lstrip": false,
|
134 |
"normalized": true,
|
135 |
"rstrip": false,
|
@@ -137,7 +137,7 @@
|
|
137 |
"special": false
|
138 |
},
|
139 |
"57534": {
|
140 |
-
"content": "</
|
141 |
"lstrip": false,
|
142 |
"normalized": true,
|
143 |
"rstrip": false,
|
@@ -145,7 +145,7 @@
|
|
145 |
"special": false
|
146 |
},
|
147 |
"57535": {
|
148 |
-
"content": "<
|
149 |
"lstrip": false,
|
150 |
"normalized": true,
|
151 |
"rstrip": false,
|
@@ -153,7 +153,7 @@
|
|
153 |
"special": false
|
154 |
},
|
155 |
"57536": {
|
156 |
-
"content": "</
|
157 |
"lstrip": false,
|
158 |
"normalized": true,
|
159 |
"rstrip": false,
|
@@ -161,7 +161,7 @@
|
|
161 |
"special": false
|
162 |
},
|
163 |
"57537": {
|
164 |
-
"content": "<
|
165 |
"lstrip": false,
|
166 |
"normalized": true,
|
167 |
"rstrip": false,
|
@@ -169,7 +169,7 @@
|
|
169 |
"special": false
|
170 |
},
|
171 |
"57538": {
|
172 |
-
"content": "</
|
173 |
"lstrip": false,
|
174 |
"normalized": true,
|
175 |
"rstrip": false,
|
@@ -177,6 +177,54 @@
|
|
177 |
"special": false
|
178 |
},
|
179 |
"57539": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
180 |
"content": "<s_cord-v2>",
|
181 |
"lstrip": false,
|
182 |
"normalized": true,
|
|
|
65 |
"special": true
|
66 |
},
|
67 |
"57525": {
|
68 |
+
"content": "<s_items>",
|
69 |
"lstrip": false,
|
70 |
"normalized": true,
|
71 |
"rstrip": false,
|
|
|
73 |
"special": false
|
74 |
},
|
75 |
"57526": {
|
76 |
+
"content": "</s_items>",
|
77 |
"lstrip": false,
|
78 |
"normalized": true,
|
79 |
"rstrip": false,
|
|
|
81 |
"special": false
|
82 |
},
|
83 |
"57527": {
|
84 |
+
"content": "<s_item_desc>",
|
85 |
"lstrip": false,
|
86 |
"normalized": true,
|
87 |
"rstrip": false,
|
|
|
89 |
"special": false
|
90 |
},
|
91 |
"57528": {
|
92 |
+
"content": "</s_item_desc>",
|
93 |
"lstrip": false,
|
94 |
"normalized": true,
|
95 |
"rstrip": false,
|
|
|
97 |
"special": false
|
98 |
},
|
99 |
"57529": {
|
100 |
+
"content": "<s_item_price>",
|
101 |
"lstrip": false,
|
102 |
"normalized": true,
|
103 |
"rstrip": false,
|
|
|
105 |
"special": false
|
106 |
},
|
107 |
"57530": {
|
108 |
+
"content": "</s_item_price>",
|
109 |
"lstrip": false,
|
110 |
"normalized": true,
|
111 |
"rstrip": false,
|
|
|
113 |
"special": false
|
114 |
},
|
115 |
"57531": {
|
116 |
+
"content": "<s_item_qty>",
|
117 |
"lstrip": false,
|
118 |
"normalized": true,
|
119 |
"rstrip": false,
|
|
|
121 |
"special": false
|
122 |
},
|
123 |
"57532": {
|
124 |
+
"content": "</s_item_qty>",
|
125 |
"lstrip": false,
|
126 |
"normalized": true,
|
127 |
"rstrip": false,
|
|
|
129 |
"special": false
|
130 |
},
|
131 |
"57533": {
|
132 |
+
"content": "<s_summary>",
|
133 |
"lstrip": false,
|
134 |
"normalized": true,
|
135 |
"rstrip": false,
|
|
|
137 |
"special": false
|
138 |
},
|
139 |
"57534": {
|
140 |
+
"content": "</s_summary>",
|
141 |
"lstrip": false,
|
142 |
"normalized": true,
|
143 |
"rstrip": false,
|
|
|
145 |
"special": false
|
146 |
},
|
147 |
"57535": {
|
148 |
+
"content": "<s_total_vat>",
|
149 |
"lstrip": false,
|
150 |
"normalized": true,
|
151 |
"rstrip": false,
|
|
|
153 |
"special": false
|
154 |
},
|
155 |
"57536": {
|
156 |
+
"content": "</s_total_vat>",
|
157 |
"lstrip": false,
|
158 |
"normalized": true,
|
159 |
"rstrip": false,
|
|
|
161 |
"special": false
|
162 |
},
|
163 |
"57537": {
|
164 |
+
"content": "<s_header>",
|
165 |
"lstrip": false,
|
166 |
"normalized": true,
|
167 |
"rstrip": false,
|
|
|
169 |
"special": false
|
170 |
},
|
171 |
"57538": {
|
172 |
+
"content": "</s_header>",
|
173 |
"lstrip": false,
|
174 |
"normalized": true,
|
175 |
"rstrip": false,
|
|
|
177 |
"special": false
|
178 |
},
|
179 |
"57539": {
|
180 |
+
"content": "<s_date>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"57540": {
|
188 |
+
"content": "</s_date>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"57541": {
|
196 |
+
"content": "<s_quotation_no>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"57542": {
|
204 |
+
"content": "</s_quotation_no>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"57543": {
|
212 |
+
"content": "<s_item_ref>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": true,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"57544": {
|
220 |
+
"content": "</s_item_ref>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": true,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
"57545": {
|
228 |
"content": "<s_cord-v2>",
|
229 |
"lstrip": false,
|
230 |
"normalized": true,
|