Training done
Browse files- added_tokens.json +22 -0
- preprocessor_config.json +26 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +55 -0
- tokenizer.json +0 -0
- tokenizer_config.json +220 -0
added_tokens.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s_address>": 57540,
|
3 |
+
"</s_company>": 57538,
|
4 |
+
"</s_date>": 57536,
|
5 |
+
"</s_item_desc>": 57534,
|
6 |
+
"</s_item_price>": 57532,
|
7 |
+
"</s_item_qty>": 57530,
|
8 |
+
"</s_items>": 57528,
|
9 |
+
"</s_total_paid>": 57526,
|
10 |
+
"<s_address>": 57539,
|
11 |
+
"<s_company>": 57537,
|
12 |
+
"<s_date>": 57535,
|
13 |
+
"<s_iitcdip>": 57523,
|
14 |
+
"<s_item_desc>": 57533,
|
15 |
+
"<s_item_price>": 57531,
|
16 |
+
"<s_item_qty>": 57529,
|
17 |
+
"<s_items>": 57527,
|
18 |
+
"<s_receipts>": 57541,
|
19 |
+
"<s_synthdog>": 57524,
|
20 |
+
"<s_total_paid>": 57525,
|
21 |
+
"<sep/>": 57522
|
22 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_align_long_axis": false,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pad": true,
|
5 |
+
"do_rescale": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"do_thumbnail": true,
|
8 |
+
"image_mean": [
|
9 |
+
0.5,
|
10 |
+
0.5,
|
11 |
+
0.5
|
12 |
+
],
|
13 |
+
"image_processor_type": "DonutImageProcessor",
|
14 |
+
"image_std": [
|
15 |
+
0.5,
|
16 |
+
0.5,
|
17 |
+
0.5
|
18 |
+
],
|
19 |
+
"processor_class": "DonutProcessor",
|
20 |
+
"resample": 2,
|
21 |
+
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": [
|
23 |
+
960,
|
24 |
+
1280
|
25 |
+
]
|
26 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
|
3 |
+
size 1296245
|
special_tokens_map.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s_iitcdip>",
|
4 |
+
"<s_synthdog>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<s>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"cls_token": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"mask_token": {
|
28 |
+
"content": "<mask>",
|
29 |
+
"lstrip": true,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
},
|
34 |
+
"pad_token": {
|
35 |
+
"content": "<pad>",
|
36 |
+
"lstrip": false,
|
37 |
+
"normalized": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"single_word": false
|
40 |
+
},
|
41 |
+
"sep_token": {
|
42 |
+
"content": "</s>",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": false,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"unk_token": {
|
49 |
+
"content": "<unk>",
|
50 |
+
"lstrip": false,
|
51 |
+
"normalized": false,
|
52 |
+
"rstrip": false,
|
53 |
+
"single_word": false
|
54 |
+
}
|
55 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_total_paid>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"57526": {
|
76 |
+
"content": "</s_total_paid>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"57527": {
|
84 |
+
"content": "<s_items>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"57528": {
|
92 |
+
"content": "</s_items>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"57529": {
|
100 |
+
"content": "<s_item_qty>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"57530": {
|
108 |
+
"content": "</s_item_qty>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"57531": {
|
116 |
+
"content": "<s_item_price>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"57532": {
|
124 |
+
"content": "</s_item_price>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"57533": {
|
132 |
+
"content": "<s_item_desc>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"57534": {
|
140 |
+
"content": "</s_item_desc>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"57535": {
|
148 |
+
"content": "<s_date>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"57536": {
|
156 |
+
"content": "</s_date>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"57537": {
|
164 |
+
"content": "<s_company>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"57538": {
|
172 |
+
"content": "</s_company>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"57539": {
|
180 |
+
"content": "<s_address>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"57540": {
|
188 |
+
"content": "</s_address>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"57541": {
|
196 |
+
"content": "<s_receipts>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
}
|
203 |
+
},
|
204 |
+
"additional_special_tokens": [
|
205 |
+
"<s_iitcdip>",
|
206 |
+
"<s_synthdog>"
|
207 |
+
],
|
208 |
+
"bos_token": "<s>",
|
209 |
+
"clean_up_tokenization_spaces": true,
|
210 |
+
"cls_token": "<s>",
|
211 |
+
"eos_token": "</s>",
|
212 |
+
"mask_token": "<mask>",
|
213 |
+
"model_max_length": 1000000000000000019884624838656,
|
214 |
+
"pad_token": "<pad>",
|
215 |
+
"processor_class": "DonutProcessor",
|
216 |
+
"sep_token": "</s>",
|
217 |
+
"sp_model_kwargs": {},
|
218 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
219 |
+
"unk_token": "<unk>"
|
220 |
+
}
|