Training done
Browse files- tokenizer.json +3 -18
- tokenizer_config.json +8 -239
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 768,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 768
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 1,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "<pad>"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
@@ -230478,7 +230464,6 @@
|
|
230478 |
"<mask>",
|
230479 |
0.0
|
230480 |
]
|
230481 |
-
]
|
230482 |
-
"byte_fallback": false
|
230483 |
}
|
230484 |
}
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
230464 |
"<mask>",
|
230465 |
0.0
|
230466 |
]
|
230467 |
+
]
|
|
|
230468 |
}
|
230469 |
}
|
tokenizer_config.json
CHANGED
@@ -1,247 +1,16 @@
|
|
1 |
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<pad>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "</s>",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"3": {
|
28 |
-
"content": "<unk>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"57521": {
|
36 |
-
"content": "<mask>",
|
37 |
-
"lstrip": true,
|
38 |
-
"normalized": true,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"57522": {
|
44 |
-
"content": "<sep/>",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": true,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": false
|
50 |
-
},
|
51 |
-
"57523": {
|
52 |
-
"content": "<s_iitcdip>",
|
53 |
-
"lstrip": false,
|
54 |
-
"normalized": false,
|
55 |
-
"rstrip": false,
|
56 |
-
"single_word": false,
|
57 |
-
"special": true
|
58 |
-
},
|
59 |
-
"57524": {
|
60 |
-
"content": "<s_synthdog>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": false,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false,
|
65 |
-
"special": true
|
66 |
-
},
|
67 |
-
"57525": {
|
68 |
-
"content": "<s_items>",
|
69 |
-
"lstrip": false,
|
70 |
-
"normalized": true,
|
71 |
-
"rstrip": false,
|
72 |
-
"single_word": false,
|
73 |
-
"special": false
|
74 |
-
},
|
75 |
-
"57526": {
|
76 |
-
"content": "</s_items>",
|
77 |
-
"lstrip": false,
|
78 |
-
"normalized": true,
|
79 |
-
"rstrip": false,
|
80 |
-
"single_word": false,
|
81 |
-
"special": false
|
82 |
-
},
|
83 |
-
"57527": {
|
84 |
-
"content": "<s_item_desc>",
|
85 |
-
"lstrip": false,
|
86 |
-
"normalized": true,
|
87 |
-
"rstrip": false,
|
88 |
-
"single_word": false,
|
89 |
-
"special": false
|
90 |
-
},
|
91 |
-
"57528": {
|
92 |
-
"content": "</s_item_desc>",
|
93 |
-
"lstrip": false,
|
94 |
-
"normalized": true,
|
95 |
-
"rstrip": false,
|
96 |
-
"single_word": false,
|
97 |
-
"special": false
|
98 |
-
},
|
99 |
-
"57529": {
|
100 |
-
"content": "<s_item_price>",
|
101 |
-
"lstrip": false,
|
102 |
-
"normalized": true,
|
103 |
-
"rstrip": false,
|
104 |
-
"single_word": false,
|
105 |
-
"special": false
|
106 |
-
},
|
107 |
-
"57530": {
|
108 |
-
"content": "</s_item_price>",
|
109 |
-
"lstrip": false,
|
110 |
-
"normalized": true,
|
111 |
-
"rstrip": false,
|
112 |
-
"single_word": false,
|
113 |
-
"special": false
|
114 |
-
},
|
115 |
-
"57531": {
|
116 |
-
"content": "<s_item_qty>",
|
117 |
-
"lstrip": false,
|
118 |
-
"normalized": true,
|
119 |
-
"rstrip": false,
|
120 |
-
"single_word": false,
|
121 |
-
"special": false
|
122 |
-
},
|
123 |
-
"57532": {
|
124 |
-
"content": "</s_item_qty>",
|
125 |
-
"lstrip": false,
|
126 |
-
"normalized": true,
|
127 |
-
"rstrip": false,
|
128 |
-
"single_word": false,
|
129 |
-
"special": false
|
130 |
-
},
|
131 |
-
"57533": {
|
132 |
-
"content": "<s_summary>",
|
133 |
-
"lstrip": false,
|
134 |
-
"normalized": true,
|
135 |
-
"rstrip": false,
|
136 |
-
"single_word": false,
|
137 |
-
"special": false
|
138 |
-
},
|
139 |
-
"57534": {
|
140 |
-
"content": "</s_summary>",
|
141 |
-
"lstrip": false,
|
142 |
-
"normalized": true,
|
143 |
-
"rstrip": false,
|
144 |
-
"single_word": false,
|
145 |
-
"special": false
|
146 |
-
},
|
147 |
-
"57535": {
|
148 |
-
"content": "<s_total_vat>",
|
149 |
-
"lstrip": false,
|
150 |
-
"normalized": true,
|
151 |
-
"rstrip": false,
|
152 |
-
"single_word": false,
|
153 |
-
"special": false
|
154 |
-
},
|
155 |
-
"57536": {
|
156 |
-
"content": "</s_total_vat>",
|
157 |
-
"lstrip": false,
|
158 |
-
"normalized": true,
|
159 |
-
"rstrip": false,
|
160 |
-
"single_word": false,
|
161 |
-
"special": false
|
162 |
-
},
|
163 |
-
"57537": {
|
164 |
-
"content": "<s_header>",
|
165 |
-
"lstrip": false,
|
166 |
-
"normalized": true,
|
167 |
-
"rstrip": false,
|
168 |
-
"single_word": false,
|
169 |
-
"special": false
|
170 |
-
},
|
171 |
-
"57538": {
|
172 |
-
"content": "</s_header>",
|
173 |
-
"lstrip": false,
|
174 |
-
"normalized": true,
|
175 |
-
"rstrip": false,
|
176 |
-
"single_word": 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,
|
231 |
-
"rstrip": false,
|
232 |
-
"single_word": false,
|
233 |
-
"special": false
|
234 |
-
}
|
235 |
-
},
|
236 |
-
"additional_special_tokens": [
|
237 |
-
"<s_iitcdip>",
|
238 |
-
"<s_synthdog>"
|
239 |
-
],
|
240 |
"bos_token": "<s>",
|
241 |
"clean_up_tokenization_spaces": true,
|
242 |
"cls_token": "<s>",
|
243 |
"eos_token": "</s>",
|
244 |
-
"mask_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
245 |
"model_max_length": 1000000000000000019884624838656,
|
246 |
"pad_token": "<pad>",
|
247 |
"processor_class": "DonutProcessor",
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "<s>",
|
5 |
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
"model_max_length": 1000000000000000019884624838656,
|
15 |
"pad_token": "<pad>",
|
16 |
"processor_class": "DonutProcessor",
|