End of training
Browse files- README.md +6 -12
- added_tokens.json +0 -24
- generation_config.json +1 -1
- model.safetensors +1 -1
- runs/Nov22_05-47-12_a52fcfd27097/events.out.tfevents.1700632035.a52fcfd27097.47.1 +2 -2
- special_tokens_map.json +1 -169
- tokenizer.json +2 -220
- tokenizer_config.json +1 -217
README.md
CHANGED
@@ -3,8 +3,6 @@ license: mit
|
|
3 |
base_model: naver-clova-ix/donut-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
datasets:
|
7 |
-
- imagefolder
|
8 |
model-index:
|
9 |
- name: donut-base-sroie
|
10 |
results: []
|
@@ -15,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# donut-base-sroie
|
17 |
|
18 |
-
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,21 +33,17 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 2e-05
|
38 |
-
- train_batch_size:
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- num_epochs: 3
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
-
### Training results
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
### Framework versions
|
51 |
|
52 |
-
- Transformers 4.35.
|
53 |
-
- Pytorch 2.
|
54 |
- Datasets 2.15.0
|
55 |
-
- Tokenizers 0.
|
|
|
3 |
base_model: naver-clova-ix/donut-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: donut-base-sroie
|
8 |
results: []
|
|
|
13 |
|
14 |
# donut-base-sroie
|
15 |
|
16 |
+
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 2e-05
|
36 |
+
- train_batch_size: 4
|
37 |
+
- eval_batch_size: 16
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
- num_epochs: 3
|
42 |
- mixed_precision_training: Native AMP
|
43 |
|
|
|
|
|
|
|
|
|
44 |
### Framework versions
|
45 |
|
46 |
+
- Transformers 4.35.0
|
47 |
+
- Pytorch 2.0.0
|
48 |
- Datasets 2.15.0
|
49 |
+
- Tokenizers 0.14.1
|
added_tokens.json
CHANGED
@@ -1,29 +1,5 @@
|
|
1 |
{
|
2 |
-
"</s_charge_hours>": 57537,
|
3 |
-
"</s_charge_total>": 57536,
|
4 |
-
"</s_charge_type>": 57548,
|
5 |
-
"</s_charges>": 57527,
|
6 |
-
"</s_invoice_date>": 57528,
|
7 |
-
"</s_invoice_number>": 57533,
|
8 |
-
"</s_invoice_tax>": 57547,
|
9 |
-
"</s_invoice_total>": 57532,
|
10 |
-
"</s_part_description>": 57529,
|
11 |
-
"</s_part_number>": 57530,
|
12 |
-
"</s_service_date>": 57539,
|
13 |
-
"</s_service_number>": 57534,
|
14 |
-
"<s_charge_hours>": 57541,
|
15 |
-
"<s_charge_total>": 57544,
|
16 |
-
"<s_charge_type>": 57535,
|
17 |
-
"<s_charges>": 57540,
|
18 |
"<s_iitcdip>": 57523,
|
19 |
-
"<s_invoice_date>": 57543,
|
20 |
-
"<s_invoice_number>": 57526,
|
21 |
-
"<s_invoice_tax>": 57525,
|
22 |
-
"<s_invoice_total>": 57545,
|
23 |
-
"<s_part_description>": 57538,
|
24 |
-
"<s_part_number>": 57531,
|
25 |
-
"<s_service_date>": 57546,
|
26 |
-
"<s_service_number>": 57542,
|
27 |
"<s_synthdog>": 57524,
|
28 |
"<sep/>": 57522
|
29 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"<s_iitcdip>": 57523,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"<s_synthdog>": 57524,
|
4 |
"<sep/>": 57522
|
5 |
}
|
generation_config.json
CHANGED
@@ -4,5 +4,5 @@
|
|
4 |
"eos_token_id": 2,
|
5 |
"forced_eos_token_id": 2,
|
6 |
"pad_token_id": 1,
|
7 |
-
"transformers_version": "4.35.
|
8 |
}
|
|
|
4 |
"eos_token_id": 2,
|
5 |
"forced_eos_token_id": 2,
|
6 |
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.35.0"
|
8 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 809070744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d621e7b65e613c7545d32244610bfdbea1b977d362209eb9dae6d7e4cf5bd80
|
3 |
size 809070744
|
runs/Nov22_05-47-12_a52fcfd27097/events.out.tfevents.1700632035.a52fcfd27097.47.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1280a3b9a24d7754c11755ad9e7a541cce1dccfc5c4d423291c2e79c9ecb70f
|
3 |
+
size 9711
|
special_tokens_map.json
CHANGED
@@ -1,145 +1,5 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
{
|
4 |
-
"content": "<s_invoice_tax>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
{
|
11 |
-
"content": "<s_invoice_number>",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": false,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"content": "</s_charges>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"content": "</s_invoice_date>",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": false,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"content": "</s_part_description>",
|
33 |
-
"lstrip": false,
|
34 |
-
"normalized": false,
|
35 |
-
"rstrip": false,
|
36 |
-
"single_word": false
|
37 |
-
},
|
38 |
-
{
|
39 |
-
"content": "</s_part_number>",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false
|
44 |
-
},
|
45 |
-
{
|
46 |
-
"content": "<s_part_number>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"content": "</s_invoice_total>",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false
|
58 |
-
},
|
59 |
-
{
|
60 |
-
"content": "<s>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": false,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false
|
65 |
-
},
|
66 |
-
{
|
67 |
-
"content": "</s_invoice_number>",
|
68 |
-
"lstrip": false,
|
69 |
-
"normalized": false,
|
70 |
-
"rstrip": false,
|
71 |
-
"single_word": false
|
72 |
-
},
|
73 |
-
{
|
74 |
-
"content": "</s_service_number>",
|
75 |
-
"lstrip": false,
|
76 |
-
"normalized": false,
|
77 |
-
"rstrip": false,
|
78 |
-
"single_word": false
|
79 |
-
},
|
80 |
-
{
|
81 |
-
"content": "<s_charge_type>",
|
82 |
-
"lstrip": false,
|
83 |
-
"normalized": false,
|
84 |
-
"rstrip": false,
|
85 |
-
"single_word": false
|
86 |
-
},
|
87 |
-
{
|
88 |
-
"content": "</s_charge_total>",
|
89 |
-
"lstrip": false,
|
90 |
-
"normalized": false,
|
91 |
-
"rstrip": false,
|
92 |
-
"single_word": false
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"content": "</s_charge_hours>",
|
96 |
-
"lstrip": false,
|
97 |
-
"normalized": false,
|
98 |
-
"rstrip": false,
|
99 |
-
"single_word": false
|
100 |
-
},
|
101 |
-
{
|
102 |
-
"content": "<s_part_description>",
|
103 |
-
"lstrip": false,
|
104 |
-
"normalized": false,
|
105 |
-
"rstrip": false,
|
106 |
-
"single_word": false
|
107 |
-
},
|
108 |
-
{
|
109 |
-
"content": "</s_service_date>",
|
110 |
-
"lstrip": false,
|
111 |
-
"normalized": false,
|
112 |
-
"rstrip": false,
|
113 |
-
"single_word": false
|
114 |
-
},
|
115 |
-
{
|
116 |
-
"content": "<s_charges>",
|
117 |
-
"lstrip": false,
|
118 |
-
"normalized": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"single_word": false
|
121 |
-
},
|
122 |
-
{
|
123 |
-
"content": "<s_charge_hours>",
|
124 |
-
"lstrip": false,
|
125 |
-
"normalized": false,
|
126 |
-
"rstrip": false,
|
127 |
-
"single_word": false
|
128 |
-
},
|
129 |
-
{
|
130 |
-
"content": "<s_service_number>",
|
131 |
-
"lstrip": false,
|
132 |
-
"normalized": false,
|
133 |
-
"rstrip": false,
|
134 |
-
"single_word": false
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"content": "<s_invoice_date>",
|
138 |
-
"lstrip": false,
|
139 |
-
"normalized": false,
|
140 |
-
"rstrip": false,
|
141 |
-
"single_word": false
|
142 |
-
},
|
143 |
{
|
144 |
"content": "</s>",
|
145 |
"lstrip": false,
|
@@ -148,35 +8,7 @@
|
|
148 |
"single_word": false
|
149 |
},
|
150 |
{
|
151 |
-
"content": "<
|
152 |
-
"lstrip": false,
|
153 |
-
"normalized": false,
|
154 |
-
"rstrip": false,
|
155 |
-
"single_word": false
|
156 |
-
},
|
157 |
-
{
|
158 |
-
"content": "<s_invoice_total>",
|
159 |
-
"lstrip": false,
|
160 |
-
"normalized": false,
|
161 |
-
"rstrip": false,
|
162 |
-
"single_word": false
|
163 |
-
},
|
164 |
-
{
|
165 |
-
"content": "<s_service_date>",
|
166 |
-
"lstrip": false,
|
167 |
-
"normalized": false,
|
168 |
-
"rstrip": false,
|
169 |
-
"single_word": false
|
170 |
-
},
|
171 |
-
{
|
172 |
-
"content": "</s_invoice_tax>",
|
173 |
-
"lstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"rstrip": false,
|
176 |
-
"single_word": false
|
177 |
-
},
|
178 |
-
{
|
179 |
-
"content": "</s_charge_type>",
|
180 |
"lstrip": false,
|
181 |
"normalized": false,
|
182 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
{
|
4 |
"content": "</s>",
|
5 |
"lstrip": false,
|
|
|
8 |
"single_word": false
|
9 |
},
|
10 |
{
|
11 |
+
"content": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"lstrip": false,
|
13 |
"normalized": false,
|
14 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -88,222 +88,6 @@
|
|
88 |
"rstrip": false,
|
89 |
"normalized": false,
|
90 |
"special": true
|
91 |
-
},
|
92 |
-
{
|
93 |
-
"id": 57525,
|
94 |
-
"content": "<s_invoice_tax>",
|
95 |
-
"single_word": false,
|
96 |
-
"lstrip": false,
|
97 |
-
"rstrip": false,
|
98 |
-
"normalized": false,
|
99 |
-
"special": true
|
100 |
-
},
|
101 |
-
{
|
102 |
-
"id": 57526,
|
103 |
-
"content": "<s_invoice_number>",
|
104 |
-
"single_word": false,
|
105 |
-
"lstrip": false,
|
106 |
-
"rstrip": false,
|
107 |
-
"normalized": false,
|
108 |
-
"special": true
|
109 |
-
},
|
110 |
-
{
|
111 |
-
"id": 57527,
|
112 |
-
"content": "</s_charges>",
|
113 |
-
"single_word": false,
|
114 |
-
"lstrip": false,
|
115 |
-
"rstrip": false,
|
116 |
-
"normalized": false,
|
117 |
-
"special": true
|
118 |
-
},
|
119 |
-
{
|
120 |
-
"id": 57528,
|
121 |
-
"content": "</s_invoice_date>",
|
122 |
-
"single_word": false,
|
123 |
-
"lstrip": false,
|
124 |
-
"rstrip": false,
|
125 |
-
"normalized": false,
|
126 |
-
"special": true
|
127 |
-
},
|
128 |
-
{
|
129 |
-
"id": 57529,
|
130 |
-
"content": "</s_part_description>",
|
131 |
-
"single_word": false,
|
132 |
-
"lstrip": false,
|
133 |
-
"rstrip": false,
|
134 |
-
"normalized": false,
|
135 |
-
"special": true
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"id": 57530,
|
139 |
-
"content": "</s_part_number>",
|
140 |
-
"single_word": false,
|
141 |
-
"lstrip": false,
|
142 |
-
"rstrip": false,
|
143 |
-
"normalized": false,
|
144 |
-
"special": true
|
145 |
-
},
|
146 |
-
{
|
147 |
-
"id": 57531,
|
148 |
-
"content": "<s_part_number>",
|
149 |
-
"single_word": false,
|
150 |
-
"lstrip": false,
|
151 |
-
"rstrip": false,
|
152 |
-
"normalized": false,
|
153 |
-
"special": true
|
154 |
-
},
|
155 |
-
{
|
156 |
-
"id": 57532,
|
157 |
-
"content": "</s_invoice_total>",
|
158 |
-
"single_word": false,
|
159 |
-
"lstrip": false,
|
160 |
-
"rstrip": false,
|
161 |
-
"normalized": false,
|
162 |
-
"special": true
|
163 |
-
},
|
164 |
-
{
|
165 |
-
"id": 57533,
|
166 |
-
"content": "</s_invoice_number>",
|
167 |
-
"single_word": false,
|
168 |
-
"lstrip": false,
|
169 |
-
"rstrip": false,
|
170 |
-
"normalized": false,
|
171 |
-
"special": true
|
172 |
-
},
|
173 |
-
{
|
174 |
-
"id": 57534,
|
175 |
-
"content": "</s_service_number>",
|
176 |
-
"single_word": false,
|
177 |
-
"lstrip": false,
|
178 |
-
"rstrip": false,
|
179 |
-
"normalized": false,
|
180 |
-
"special": true
|
181 |
-
},
|
182 |
-
{
|
183 |
-
"id": 57535,
|
184 |
-
"content": "<s_charge_type>",
|
185 |
-
"single_word": false,
|
186 |
-
"lstrip": false,
|
187 |
-
"rstrip": false,
|
188 |
-
"normalized": false,
|
189 |
-
"special": true
|
190 |
-
},
|
191 |
-
{
|
192 |
-
"id": 57536,
|
193 |
-
"content": "</s_charge_total>",
|
194 |
-
"single_word": false,
|
195 |
-
"lstrip": false,
|
196 |
-
"rstrip": false,
|
197 |
-
"normalized": false,
|
198 |
-
"special": true
|
199 |
-
},
|
200 |
-
{
|
201 |
-
"id": 57537,
|
202 |
-
"content": "</s_charge_hours>",
|
203 |
-
"single_word": false,
|
204 |
-
"lstrip": false,
|
205 |
-
"rstrip": false,
|
206 |
-
"normalized": false,
|
207 |
-
"special": true
|
208 |
-
},
|
209 |
-
{
|
210 |
-
"id": 57538,
|
211 |
-
"content": "<s_part_description>",
|
212 |
-
"single_word": false,
|
213 |
-
"lstrip": false,
|
214 |
-
"rstrip": false,
|
215 |
-
"normalized": false,
|
216 |
-
"special": true
|
217 |
-
},
|
218 |
-
{
|
219 |
-
"id": 57539,
|
220 |
-
"content": "</s_service_date>",
|
221 |
-
"single_word": false,
|
222 |
-
"lstrip": false,
|
223 |
-
"rstrip": false,
|
224 |
-
"normalized": false,
|
225 |
-
"special": true
|
226 |
-
},
|
227 |
-
{
|
228 |
-
"id": 57540,
|
229 |
-
"content": "<s_charges>",
|
230 |
-
"single_word": false,
|
231 |
-
"lstrip": false,
|
232 |
-
"rstrip": false,
|
233 |
-
"normalized": false,
|
234 |
-
"special": true
|
235 |
-
},
|
236 |
-
{
|
237 |
-
"id": 57541,
|
238 |
-
"content": "<s_charge_hours>",
|
239 |
-
"single_word": false,
|
240 |
-
"lstrip": false,
|
241 |
-
"rstrip": false,
|
242 |
-
"normalized": false,
|
243 |
-
"special": true
|
244 |
-
},
|
245 |
-
{
|
246 |
-
"id": 57542,
|
247 |
-
"content": "<s_service_number>",
|
248 |
-
"single_word": false,
|
249 |
-
"lstrip": false,
|
250 |
-
"rstrip": false,
|
251 |
-
"normalized": false,
|
252 |
-
"special": true
|
253 |
-
},
|
254 |
-
{
|
255 |
-
"id": 57543,
|
256 |
-
"content": "<s_invoice_date>",
|
257 |
-
"single_word": false,
|
258 |
-
"lstrip": false,
|
259 |
-
"rstrip": false,
|
260 |
-
"normalized": false,
|
261 |
-
"special": true
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"id": 57544,
|
265 |
-
"content": "<s_charge_total>",
|
266 |
-
"single_word": false,
|
267 |
-
"lstrip": false,
|
268 |
-
"rstrip": false,
|
269 |
-
"normalized": false,
|
270 |
-
"special": true
|
271 |
-
},
|
272 |
-
{
|
273 |
-
"id": 57545,
|
274 |
-
"content": "<s_invoice_total>",
|
275 |
-
"single_word": false,
|
276 |
-
"lstrip": false,
|
277 |
-
"rstrip": false,
|
278 |
-
"normalized": false,
|
279 |
-
"special": true
|
280 |
-
},
|
281 |
-
{
|
282 |
-
"id": 57546,
|
283 |
-
"content": "<s_service_date>",
|
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_tax>",
|
293 |
-
"single_word": false,
|
294 |
-
"lstrip": false,
|
295 |
-
"rstrip": false,
|
296 |
-
"normalized": false,
|
297 |
-
"special": true
|
298 |
-
},
|
299 |
-
{
|
300 |
-
"id": 57548,
|
301 |
-
"content": "</s_charge_type>",
|
302 |
-
"single_word": false,
|
303 |
-
"lstrip": false,
|
304 |
-
"rstrip": false,
|
305 |
-
"normalized": false,
|
306 |
-
"special": true
|
307 |
}
|
308 |
],
|
309 |
"normalizer": {
|
@@ -325,8 +109,7 @@
|
|
325 |
"pre_tokenizer": {
|
326 |
"type": "Metaspace",
|
327 |
"replacement": "▁",
|
328 |
-
"add_prefix_space": true
|
329 |
-
"prepend_scheme": "always"
|
330 |
},
|
331 |
"post_processor": {
|
332 |
"type": "TemplateProcessing",
|
@@ -412,8 +195,7 @@
|
|
412 |
"decoder": {
|
413 |
"type": "Metaspace",
|
414 |
"replacement": "▁",
|
415 |
-
"add_prefix_space": true
|
416 |
-
"prepend_scheme": "always"
|
417 |
},
|
418 |
"model": {
|
419 |
"type": "Unigram",
|
|
|
88 |
"rstrip": false,
|
89 |
"normalized": false,
|
90 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
}
|
92 |
],
|
93 |
"normalizer": {
|
|
|
109 |
"pre_tokenizer": {
|
110 |
"type": "Metaspace",
|
111 |
"replacement": "▁",
|
112 |
+
"add_prefix_space": true
|
|
|
113 |
},
|
114 |
"post_processor": {
|
115 |
"type": "TemplateProcessing",
|
|
|
195 |
"decoder": {
|
196 |
"type": "Metaspace",
|
197 |
"replacement": "▁",
|
198 |
+
"add_prefix_space": true
|
|
|
199 |
},
|
200 |
"model": {
|
201 |
"type": "Unigram",
|
tokenizer_config.json
CHANGED
@@ -63,227 +63,11 @@
|
|
63 |
"rstrip": false,
|
64 |
"single_word": false,
|
65 |
"special": true
|
66 |
-
},
|
67 |
-
"57525": {
|
68 |
-
"content": "<s_invoice_tax>",
|
69 |
-
"lstrip": false,
|
70 |
-
"normalized": false,
|
71 |
-
"rstrip": false,
|
72 |
-
"single_word": false,
|
73 |
-
"special": true
|
74 |
-
},
|
75 |
-
"57526": {
|
76 |
-
"content": "<s_invoice_number>",
|
77 |
-
"lstrip": false,
|
78 |
-
"normalized": false,
|
79 |
-
"rstrip": false,
|
80 |
-
"single_word": false,
|
81 |
-
"special": true
|
82 |
-
},
|
83 |
-
"57527": {
|
84 |
-
"content": "</s_charges>",
|
85 |
-
"lstrip": false,
|
86 |
-
"normalized": false,
|
87 |
-
"rstrip": false,
|
88 |
-
"single_word": false,
|
89 |
-
"special": true
|
90 |
-
},
|
91 |
-
"57528": {
|
92 |
-
"content": "</s_invoice_date>",
|
93 |
-
"lstrip": false,
|
94 |
-
"normalized": false,
|
95 |
-
"rstrip": false,
|
96 |
-
"single_word": false,
|
97 |
-
"special": true
|
98 |
-
},
|
99 |
-
"57529": {
|
100 |
-
"content": "</s_part_description>",
|
101 |
-
"lstrip": false,
|
102 |
-
"normalized": false,
|
103 |
-
"rstrip": false,
|
104 |
-
"single_word": false,
|
105 |
-
"special": true
|
106 |
-
},
|
107 |
-
"57530": {
|
108 |
-
"content": "</s_part_number>",
|
109 |
-
"lstrip": false,
|
110 |
-
"normalized": false,
|
111 |
-
"rstrip": false,
|
112 |
-
"single_word": false,
|
113 |
-
"special": true
|
114 |
-
},
|
115 |
-
"57531": {
|
116 |
-
"content": "<s_part_number>",
|
117 |
-
"lstrip": false,
|
118 |
-
"normalized": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"single_word": false,
|
121 |
-
"special": true
|
122 |
-
},
|
123 |
-
"57532": {
|
124 |
-
"content": "</s_invoice_total>",
|
125 |
-
"lstrip": false,
|
126 |
-
"normalized": false,
|
127 |
-
"rstrip": false,
|
128 |
-
"single_word": false,
|
129 |
-
"special": true
|
130 |
-
},
|
131 |
-
"57533": {
|
132 |
-
"content": "</s_invoice_number>",
|
133 |
-
"lstrip": false,
|
134 |
-
"normalized": false,
|
135 |
-
"rstrip": false,
|
136 |
-
"single_word": false,
|
137 |
-
"special": true
|
138 |
-
},
|
139 |
-
"57534": {
|
140 |
-
"content": "</s_service_number>",
|
141 |
-
"lstrip": false,
|
142 |
-
"normalized": false,
|
143 |
-
"rstrip": false,
|
144 |
-
"single_word": false,
|
145 |
-
"special": true
|
146 |
-
},
|
147 |
-
"57535": {
|
148 |
-
"content": "<s_charge_type>",
|
149 |
-
"lstrip": false,
|
150 |
-
"normalized": false,
|
151 |
-
"rstrip": false,
|
152 |
-
"single_word": false,
|
153 |
-
"special": true
|
154 |
-
},
|
155 |
-
"57536": {
|
156 |
-
"content": "</s_charge_total>",
|
157 |
-
"lstrip": false,
|
158 |
-
"normalized": false,
|
159 |
-
"rstrip": false,
|
160 |
-
"single_word": false,
|
161 |
-
"special": true
|
162 |
-
},
|
163 |
-
"57537": {
|
164 |
-
"content": "</s_charge_hours>",
|
165 |
-
"lstrip": false,
|
166 |
-
"normalized": false,
|
167 |
-
"rstrip": false,
|
168 |
-
"single_word": false,
|
169 |
-
"special": true
|
170 |
-
},
|
171 |
-
"57538": {
|
172 |
-
"content": "<s_part_description>",
|
173 |
-
"lstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"rstrip": false,
|
176 |
-
"single_word": false,
|
177 |
-
"special": true
|
178 |
-
},
|
179 |
-
"57539": {
|
180 |
-
"content": "</s_service_date>",
|
181 |
-
"lstrip": false,
|
182 |
-
"normalized": false,
|
183 |
-
"rstrip": false,
|
184 |
-
"single_word": false,
|
185 |
-
"special": true
|
186 |
-
},
|
187 |
-
"57540": {
|
188 |
-
"content": "<s_charges>",
|
189 |
-
"lstrip": false,
|
190 |
-
"normalized": false,
|
191 |
-
"rstrip": false,
|
192 |
-
"single_word": false,
|
193 |
-
"special": true
|
194 |
-
},
|
195 |
-
"57541": {
|
196 |
-
"content": "<s_charge_hours>",
|
197 |
-
"lstrip": false,
|
198 |
-
"normalized": false,
|
199 |
-
"rstrip": false,
|
200 |
-
"single_word": false,
|
201 |
-
"special": true
|
202 |
-
},
|
203 |
-
"57542": {
|
204 |
-
"content": "<s_service_number>",
|
205 |
-
"lstrip": false,
|
206 |
-
"normalized": false,
|
207 |
-
"rstrip": false,
|
208 |
-
"single_word": false,
|
209 |
-
"special": true
|
210 |
-
},
|
211 |
-
"57543": {
|
212 |
-
"content": "<s_invoice_date>",
|
213 |
-
"lstrip": false,
|
214 |
-
"normalized": false,
|
215 |
-
"rstrip": false,
|
216 |
-
"single_word": false,
|
217 |
-
"special": true
|
218 |
-
},
|
219 |
-
"57544": {
|
220 |
-
"content": "<s_charge_total>",
|
221 |
-
"lstrip": false,
|
222 |
-
"normalized": false,
|
223 |
-
"rstrip": false,
|
224 |
-
"single_word": false,
|
225 |
-
"special": true
|
226 |
-
},
|
227 |
-
"57545": {
|
228 |
-
"content": "<s_invoice_total>",
|
229 |
-
"lstrip": false,
|
230 |
-
"normalized": false,
|
231 |
-
"rstrip": false,
|
232 |
-
"single_word": false,
|
233 |
-
"special": true
|
234 |
-
},
|
235 |
-
"57546": {
|
236 |
-
"content": "<s_service_date>",
|
237 |
-
"lstrip": false,
|
238 |
-
"normalized": false,
|
239 |
-
"rstrip": false,
|
240 |
-
"single_word": false,
|
241 |
-
"special": true
|
242 |
-
},
|
243 |
-
"57547": {
|
244 |
-
"content": "</s_invoice_tax>",
|
245 |
-
"lstrip": false,
|
246 |
-
"normalized": false,
|
247 |
-
"rstrip": false,
|
248 |
-
"single_word": false,
|
249 |
-
"special": true
|
250 |
-
},
|
251 |
-
"57548": {
|
252 |
-
"content": "</s_charge_type>",
|
253 |
-
"lstrip": false,
|
254 |
-
"normalized": false,
|
255 |
-
"rstrip": false,
|
256 |
-
"single_word": false,
|
257 |
-
"special": true
|
258 |
}
|
259 |
},
|
260 |
"additional_special_tokens": [
|
261 |
-
"<s_invoice_tax>",
|
262 |
-
"<s_invoice_number>",
|
263 |
-
"</s_charges>",
|
264 |
-
"</s_invoice_date>",
|
265 |
-
"</s_part_description>",
|
266 |
-
"</s_part_number>",
|
267 |
-
"<s_part_number>",
|
268 |
-
"</s_invoice_total>",
|
269 |
-
"<s>",
|
270 |
-
"</s_invoice_number>",
|
271 |
-
"</s_service_number>",
|
272 |
-
"<s_charge_type>",
|
273 |
-
"</s_charge_total>",
|
274 |
-
"</s_charge_hours>",
|
275 |
-
"<s_part_description>",
|
276 |
-
"</s_service_date>",
|
277 |
-
"<s_charges>",
|
278 |
-
"<s_charge_hours>",
|
279 |
-
"<s_service_number>",
|
280 |
-
"<s_invoice_date>",
|
281 |
"</s>",
|
282 |
-
"<
|
283 |
-
"<s_invoice_total>",
|
284 |
-
"<s_service_date>",
|
285 |
-
"</s_invoice_tax>",
|
286 |
-
"</s_charge_type>"
|
287 |
],
|
288 |
"bos_token": "<s>",
|
289 |
"clean_up_tokenization_spaces": true,
|
|
|
63 |
"rstrip": false,
|
64 |
"single_word": false,
|
65 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
}
|
67 |
},
|
68 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
"</s>",
|
70 |
+
"<s>"
|
|
|
|
|
|
|
|
|
71 |
],
|
72 |
"bos_token": "<s>",
|
73 |
"clean_up_tokenization_spaces": true,
|