subhavarshith
commited on
Commit
•
59fb5c1
1
Parent(s):
36d76aa
Training done
Browse files- added_tokens.json +6 -0
- tokenizer.json +54 -0
- tokenizer_config.json +48 -0
added_tokens.json
CHANGED
@@ -1,11 +1,17 @@
|
|
1 |
{
|
|
|
2 |
"</s_Date>": 57528,
|
3 |
"</s_Invoice>": 57526,
|
|
|
4 |
"</s_num>": 57530,
|
|
|
|
|
5 |
"<s_Date>": 57527,
|
6 |
"<s_Invoice>": 57525,
|
|
|
7 |
"<s_iitcdip>": 57523,
|
8 |
"<s_num>": 57529,
|
|
|
9 |
"<s_synthdog>": 57524,
|
10 |
"<sep/>": 57522
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"</s_Address>": 57532,
|
3 |
"</s_Date>": 57528,
|
4 |
"</s_Invoice>": 57526,
|
5 |
+
"</s_billing>": 57534,
|
6 |
"</s_num>": 57530,
|
7 |
+
"</s_shipping>": 57536,
|
8 |
+
"<s_Address>": 57531,
|
9 |
"<s_Date>": 57527,
|
10 |
"<s_Invoice>": 57525,
|
11 |
+
"<s_billing>": 57533,
|
12 |
"<s_iitcdip>": 57523,
|
13 |
"<s_num>": 57529,
|
14 |
+
"<s_shipping>": 57535,
|
15 |
"<s_synthdog>": 57524,
|
16 |
"<sep/>": 57522
|
17 |
}
|
tokenizer.json
CHANGED
@@ -142,6 +142,60 @@
|
|
142 |
"rstrip": false,
|
143 |
"normalized": true,
|
144 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
145 |
}
|
146 |
],
|
147 |
"normalizer": {
|
|
|
142 |
"rstrip": false,
|
143 |
"normalized": true,
|
144 |
"special": false
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"id": 57531,
|
148 |
+
"content": "<s_Address>",
|
149 |
+
"single_word": false,
|
150 |
+
"lstrip": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"normalized": true,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"id": 57532,
|
157 |
+
"content": "</s_Address>",
|
158 |
+
"single_word": false,
|
159 |
+
"lstrip": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"id": 57533,
|
166 |
+
"content": "<s_billing>",
|
167 |
+
"single_word": false,
|
168 |
+
"lstrip": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"normalized": true,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"id": 57534,
|
175 |
+
"content": "</s_billing>",
|
176 |
+
"single_word": false,
|
177 |
+
"lstrip": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"normalized": true,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"id": 57535,
|
184 |
+
"content": "<s_shipping>",
|
185 |
+
"single_word": false,
|
186 |
+
"lstrip": false,
|
187 |
+
"rstrip": false,
|
188 |
+
"normalized": true,
|
189 |
+
"special": false
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"id": 57536,
|
193 |
+
"content": "</s_shipping>",
|
194 |
+
"single_word": false,
|
195 |
+
"lstrip": false,
|
196 |
+
"rstrip": false,
|
197 |
+
"normalized": true,
|
198 |
+
"special": false
|
199 |
}
|
200 |
],
|
201 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -111,6 +111,54 @@
|
|
111 |
"rstrip": false,
|
112 |
"single_word": false,
|
113 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
}
|
115 |
},
|
116 |
"additional_special_tokens": [
|
|
|
111 |
"rstrip": false,
|
112 |
"single_word": false,
|
113 |
"special": false
|
114 |
+
},
|
115 |
+
"57531": {
|
116 |
+
"content": "<s_Address>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"57532": {
|
124 |
+
"content": "</s_Address>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"57533": {
|
132 |
+
"content": "<s_billing>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"57534": {
|
140 |
+
"content": "</s_billing>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"57535": {
|
148 |
+
"content": "<s_shipping>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"57536": {
|
156 |
+
"content": "</s_shipping>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
}
|
163 |
},
|
164 |
"additional_special_tokens": [
|