Model save
Browse files- README.md +479 -0
- config.json +188 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +946 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,479 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: answerdotai/ModernBERT-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: ModernBERT-base-iob2-20241223160124
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# ModernBERT-base-iob2-20241223160124
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- eval_loss: 4.5330
|
20 |
+
- eval_model_preparation_time: 0.0027
|
21 |
+
- eval_overall_strict_precision: 0.0014
|
22 |
+
- eval_overall_strict_recall: 0.0001
|
23 |
+
- eval_overall_strict_f1: 0.0001
|
24 |
+
- eval_overall_ent_type_precision: 0.0057
|
25 |
+
- eval_overall_ent_type_recall: 0.0003
|
26 |
+
- eval_overall_ent_type_f1: 0.0005
|
27 |
+
- eval_overall_partial_precision: 0.2577
|
28 |
+
- eval_overall_partial_recall: 0.0130
|
29 |
+
- eval_overall_partial_f1: 0.0247
|
30 |
+
- eval_overall_exact_precision: 0.1638
|
31 |
+
- eval_overall_exact_recall: 0.0082
|
32 |
+
- eval_overall_exact_f1: 0.0157
|
33 |
+
- eval_checkOut_strict_precision: 0.0
|
34 |
+
- eval_checkOut_strict_recall: 0.0
|
35 |
+
- eval_checkOut_strict_f1: 0
|
36 |
+
- eval_checkOut_ent_type_precision: 0.0
|
37 |
+
- eval_checkOut_ent_type_recall: 0.0
|
38 |
+
- eval_checkOut_ent_type_f1: 0
|
39 |
+
- eval_checkOut_partial_precision: 0.0030
|
40 |
+
- eval_checkOut_partial_recall: 0.0031
|
41 |
+
- eval_checkOut_partial_f1: 0.0030
|
42 |
+
- eval_checkOut_exact_precision: 0.0022
|
43 |
+
- eval_checkOut_exact_recall: 0.0023
|
44 |
+
- eval_checkOut_exact_f1: 0.0023
|
45 |
+
- eval_bookingNumber_strict_precision: 0.0
|
46 |
+
- eval_bookingNumber_strict_recall: 0.0
|
47 |
+
- eval_bookingNumber_strict_f1: 0
|
48 |
+
- eval_bookingNumber_ent_type_precision: 0.0
|
49 |
+
- eval_bookingNumber_ent_type_recall: 0.0
|
50 |
+
- eval_bookingNumber_ent_type_f1: 0
|
51 |
+
- eval_bookingNumber_partial_precision: 0.0015
|
52 |
+
- eval_bookingNumber_partial_recall: 0.0067
|
53 |
+
- eval_bookingNumber_partial_f1: 0.0024
|
54 |
+
- eval_bookingNumber_exact_precision: 0.0014
|
55 |
+
- eval_bookingNumber_exact_recall: 0.0063
|
56 |
+
- eval_bookingNumber_exact_f1: 0.0023
|
57 |
+
- eval_documentType_strict_precision: 0.0
|
58 |
+
- eval_documentType_strict_recall: 0.0
|
59 |
+
- eval_documentType_strict_f1: 0
|
60 |
+
- eval_documentType_ent_type_precision: 0.0006
|
61 |
+
- eval_documentType_ent_type_recall: 0.0001
|
62 |
+
- eval_documentType_ent_type_f1: 0.0001
|
63 |
+
- eval_documentType_partial_precision: 0.1126
|
64 |
+
- eval_documentType_partial_recall: 0.0171
|
65 |
+
- eval_documentType_partial_f1: 0.0297
|
66 |
+
- eval_documentType_exact_precision: 0.0816
|
67 |
+
- eval_documentType_exact_recall: 0.0124
|
68 |
+
- eval_documentType_exact_f1: 0.0215
|
69 |
+
- eval_companyCountry_strict_precision: 0.0010
|
70 |
+
- eval_companyCountry_strict_recall: 0.0003
|
71 |
+
- eval_companyCountry_strict_f1: 0.0005
|
72 |
+
- eval_companyCountry_ent_type_precision: 0.0014
|
73 |
+
- eval_companyCountry_ent_type_recall: 0.0005
|
74 |
+
- eval_companyCountry_ent_type_f1: 0.0008
|
75 |
+
- eval_companyCountry_partial_precision: 0.0455
|
76 |
+
- eval_companyCountry_partial_recall: 0.0167
|
77 |
+
- eval_companyCountry_partial_f1: 0.0245
|
78 |
+
- eval_companyCountry_exact_precision: 0.0204
|
79 |
+
- eval_companyCountry_exact_recall: 0.0075
|
80 |
+
- eval_companyCountry_exact_f1: 0.0110
|
81 |
+
- eval_hotelName_strict_precision: 0.0
|
82 |
+
- eval_hotelName_strict_recall: 0.0
|
83 |
+
- eval_hotelName_strict_f1: 0
|
84 |
+
- eval_hotelName_ent_type_precision: 0.0
|
85 |
+
- eval_hotelName_ent_type_recall: 0.0
|
86 |
+
- eval_hotelName_ent_type_f1: 0
|
87 |
+
- eval_hotelName_partial_precision: 0.0003
|
88 |
+
- eval_hotelName_partial_recall: 0.0016
|
89 |
+
- eval_hotelName_partial_f1: 0.0005
|
90 |
+
- eval_hotelName_exact_precision: 0.0003
|
91 |
+
- eval_hotelName_exact_recall: 0.0014
|
92 |
+
- eval_hotelName_exact_f1: 0.0005
|
93 |
+
- eval_hotelBankAccount_strict_precision: 0.0
|
94 |
+
- eval_hotelBankAccount_strict_recall: 0.0
|
95 |
+
- eval_hotelBankAccount_strict_f1: 0
|
96 |
+
- eval_hotelBankAccount_ent_type_precision: 0.0
|
97 |
+
- eval_hotelBankAccount_ent_type_recall: 0.0
|
98 |
+
- eval_hotelBankAccount_ent_type_f1: 0
|
99 |
+
- eval_hotelBankAccount_partial_precision: 0.0
|
100 |
+
- eval_hotelBankAccount_partial_recall: 0.0
|
101 |
+
- eval_hotelBankAccount_partial_f1: 0
|
102 |
+
- eval_hotelBankAccount_exact_precision: 0.0
|
103 |
+
- eval_hotelBankAccount_exact_recall: 0.0
|
104 |
+
- eval_hotelBankAccount_exact_f1: 0
|
105 |
+
- eval_hotelAddress_strict_precision: 0.0
|
106 |
+
- eval_hotelAddress_strict_recall: 0.0
|
107 |
+
- eval_hotelAddress_strict_f1: 0
|
108 |
+
- eval_hotelAddress_ent_type_precision: 0.0
|
109 |
+
- eval_hotelAddress_ent_type_recall: 0.0
|
110 |
+
- eval_hotelAddress_ent_type_f1: 0
|
111 |
+
- eval_hotelAddress_partial_precision: 0.0
|
112 |
+
- eval_hotelAddress_partial_recall: 0.0
|
113 |
+
- eval_hotelAddress_partial_f1: 0
|
114 |
+
- eval_hotelAddress_exact_precision: 0.0
|
115 |
+
- eval_hotelAddress_exact_recall: 0.0
|
116 |
+
- eval_hotelAddress_exact_f1: 0
|
117 |
+
- eval_companyZipcode_strict_precision: 0.0
|
118 |
+
- eval_companyZipcode_strict_recall: 0.0
|
119 |
+
- eval_companyZipcode_strict_f1: 0
|
120 |
+
- eval_companyZipcode_ent_type_precision: 0.0
|
121 |
+
- eval_companyZipcode_ent_type_recall: 0.0
|
122 |
+
- eval_companyZipcode_ent_type_f1: 0
|
123 |
+
- eval_companyZipcode_partial_precision: 0.0005
|
124 |
+
- eval_companyZipcode_partial_recall: 0.0028
|
125 |
+
- eval_companyZipcode_partial_f1: 0.0008
|
126 |
+
- eval_companyZipcode_exact_precision: 0.0004
|
127 |
+
- eval_companyZipcode_exact_recall: 0.0026
|
128 |
+
- eval_companyZipcode_exact_f1: 0.0007
|
129 |
+
- eval_companyAddress_strict_precision: 0.0
|
130 |
+
- eval_companyAddress_strict_recall: 0.0
|
131 |
+
- eval_companyAddress_strict_f1: 0
|
132 |
+
- eval_companyAddress_ent_type_precision: 0.0
|
133 |
+
- eval_companyAddress_ent_type_recall: 0.0
|
134 |
+
- eval_companyAddress_ent_type_f1: 0
|
135 |
+
- eval_companyAddress_partial_precision: 0.0001
|
136 |
+
- eval_companyAddress_partial_recall: 0.0038
|
137 |
+
- eval_companyAddress_partial_f1: 0.0001
|
138 |
+
- eval_companyAddress_exact_precision: 0.0001
|
139 |
+
- eval_companyAddress_exact_recall: 0.0038
|
140 |
+
- eval_companyAddress_exact_f1: 0.0001
|
141 |
+
- eval_netAmount_strict_precision: 0.0
|
142 |
+
- eval_netAmount_strict_recall: 0.0
|
143 |
+
- eval_netAmount_strict_f1: 0
|
144 |
+
- eval_netAmount_ent_type_precision: 0.0
|
145 |
+
- eval_netAmount_ent_type_recall: 0.0
|
146 |
+
- eval_netAmount_ent_type_f1: 0
|
147 |
+
- eval_netAmount_partial_precision: 0.0117
|
148 |
+
- eval_netAmount_partial_recall: 0.0036
|
149 |
+
- eval_netAmount_partial_f1: 0.0055
|
150 |
+
- eval_netAmount_exact_precision: 0.0048
|
151 |
+
- eval_netAmount_exact_recall: 0.0015
|
152 |
+
- eval_netAmount_exact_f1: 0.0023
|
153 |
+
- eval_hotelCountry_strict_precision: 0.0
|
154 |
+
- eval_hotelCountry_strict_recall: 0.0
|
155 |
+
- eval_hotelCountry_strict_f1: 0
|
156 |
+
- eval_hotelCountry_ent_type_precision: 0.0
|
157 |
+
- eval_hotelCountry_ent_type_recall: 0.0
|
158 |
+
- eval_hotelCountry_ent_type_f1: 0
|
159 |
+
- eval_hotelCountry_partial_precision: 0.0015
|
160 |
+
- eval_hotelCountry_partial_recall: 0.0017
|
161 |
+
- eval_hotelCountry_partial_f1: 0.0016
|
162 |
+
- eval_hotelCountry_exact_precision: 0.0015
|
163 |
+
- eval_hotelCountry_exact_recall: 0.0017
|
164 |
+
- eval_hotelCountry_exact_f1: 0.0016
|
165 |
+
- eval_cardNumber_strict_precision: 0.0
|
166 |
+
- eval_cardNumber_strict_recall: 0.0
|
167 |
+
- eval_cardNumber_strict_f1: 0
|
168 |
+
- eval_cardNumber_ent_type_precision: 0.0
|
169 |
+
- eval_cardNumber_ent_type_recall: 0.0
|
170 |
+
- eval_cardNumber_ent_type_f1: 0
|
171 |
+
- eval_cardNumber_partial_precision: 0.0020
|
172 |
+
- eval_cardNumber_partial_recall: 0.0010
|
173 |
+
- eval_cardNumber_partial_f1: 0.0013
|
174 |
+
- eval_cardNumber_exact_precision: 0.0020
|
175 |
+
- eval_cardNumber_exact_recall: 0.0010
|
176 |
+
- eval_cardNumber_exact_f1: 0.0013
|
177 |
+
- eval_cardType_strict_precision: 0.0
|
178 |
+
- eval_cardType_strict_recall: 0.0
|
179 |
+
- eval_cardType_strict_f1: 0
|
180 |
+
- eval_cardType_ent_type_precision: 0.0001
|
181 |
+
- eval_cardType_ent_type_recall: 0.0007
|
182 |
+
- eval_cardType_ent_type_f1: 0.0002
|
183 |
+
- eval_cardType_partial_precision: 0.0008
|
184 |
+
- eval_cardType_partial_recall: 0.0050
|
185 |
+
- eval_cardType_partial_f1: 0.0014
|
186 |
+
- eval_cardType_exact_precision: 0.0005
|
187 |
+
- eval_cardType_exact_recall: 0.0032
|
188 |
+
- eval_cardType_exact_f1: 0.0009
|
189 |
+
- eval_grossAmount_strict_precision: 0.0
|
190 |
+
- eval_grossAmount_strict_recall: 0.0
|
191 |
+
- eval_grossAmount_strict_f1: 0
|
192 |
+
- eval_grossAmount_ent_type_precision: 0.0
|
193 |
+
- eval_grossAmount_ent_type_recall: 0.0
|
194 |
+
- eval_grossAmount_ent_type_f1: 0
|
195 |
+
- eval_grossAmount_partial_precision: 0.0001
|
196 |
+
- eval_grossAmount_partial_recall: 0.0014
|
197 |
+
- eval_grossAmount_partial_f1: 0.0001
|
198 |
+
- eval_grossAmount_exact_precision: 0.0001
|
199 |
+
- eval_grossAmount_exact_recall: 0.0014
|
200 |
+
- eval_grossAmount_exact_f1: 0.0001
|
201 |
+
- eval_reservationNumber_strict_precision: 0.0
|
202 |
+
- eval_reservationNumber_strict_recall: 0.0
|
203 |
+
- eval_reservationNumber_strict_f1: 0
|
204 |
+
- eval_reservationNumber_ent_type_precision: 0.0
|
205 |
+
- eval_reservationNumber_ent_type_recall: 0.0
|
206 |
+
- eval_reservationNumber_ent_type_f1: 0
|
207 |
+
- eval_reservationNumber_partial_precision: 0.0008
|
208 |
+
- eval_reservationNumber_partial_recall: 0.0045
|
209 |
+
- eval_reservationNumber_partial_f1: 0.0014
|
210 |
+
- eval_reservationNumber_exact_precision: 0.0008
|
211 |
+
- eval_reservationNumber_exact_recall: 0.0045
|
212 |
+
- eval_reservationNumber_exact_f1: 0.0014
|
213 |
+
- eval_invoiceNumber_strict_precision: 0.0007
|
214 |
+
- eval_invoiceNumber_strict_recall: 0.0002
|
215 |
+
- eval_invoiceNumber_strict_f1: 0.0003
|
216 |
+
- eval_invoiceNumber_ent_type_precision: 0.0011
|
217 |
+
- eval_invoiceNumber_ent_type_recall: 0.0003
|
218 |
+
- eval_invoiceNumber_ent_type_f1: 0.0005
|
219 |
+
- eval_invoiceNumber_partial_precision: 0.0461
|
220 |
+
- eval_invoiceNumber_partial_recall: 0.0135
|
221 |
+
- eval_invoiceNumber_partial_f1: 0.0209
|
222 |
+
- eval_invoiceNumber_exact_precision: 0.0118
|
223 |
+
- eval_invoiceNumber_exact_recall: 0.0035
|
224 |
+
- eval_invoiceNumber_exact_f1: 0.0054
|
225 |
+
- eval_hotelVATNumber_strict_precision: 0.0001
|
226 |
+
- eval_hotelVATNumber_strict_recall: 0.0005
|
227 |
+
- eval_hotelVATNumber_strict_f1: 0.0001
|
228 |
+
- eval_hotelVATNumber_ent_type_precision: 0.0001
|
229 |
+
- eval_hotelVATNumber_ent_type_recall: 0.0005
|
230 |
+
- eval_hotelVATNumber_ent_type_f1: 0.0001
|
231 |
+
- eval_hotelVATNumber_partial_precision: 0.0004
|
232 |
+
- eval_hotelVATNumber_partial_recall: 0.0035
|
233 |
+
- eval_hotelVATNumber_partial_f1: 0.0008
|
234 |
+
- eval_hotelVATNumber_exact_precision: 0.0004
|
235 |
+
- eval_hotelVATNumber_exact_recall: 0.0035
|
236 |
+
- eval_hotelVATNumber_exact_f1: 0.0008
|
237 |
+
- eval_externalReservationNumber_strict_precision: 0.0
|
238 |
+
- eval_externalReservationNumber_strict_recall: 0.0
|
239 |
+
- eval_externalReservationNumber_strict_f1: 0
|
240 |
+
- eval_externalReservationNumber_ent_type_precision: 0.0
|
241 |
+
- eval_externalReservationNumber_ent_type_recall: 0.0
|
242 |
+
- eval_externalReservationNumber_ent_type_f1: 0
|
243 |
+
- eval_externalReservationNumber_partial_precision: 0.0000
|
244 |
+
- eval_externalReservationNumber_partial_recall: 0.0012
|
245 |
+
- eval_externalReservationNumber_partial_f1: 0.0001
|
246 |
+
- eval_externalReservationNumber_exact_precision: 0.0
|
247 |
+
- eval_externalReservationNumber_exact_recall: 0.0
|
248 |
+
- eval_externalReservationNumber_exact_f1: 0
|
249 |
+
- eval_hotelFaxNumber_strict_precision: 0.0
|
250 |
+
- eval_hotelFaxNumber_strict_recall: 0.0
|
251 |
+
- eval_hotelFaxNumber_strict_f1: 0
|
252 |
+
- eval_hotelFaxNumber_ent_type_precision: 0.0
|
253 |
+
- eval_hotelFaxNumber_ent_type_recall: 0.0
|
254 |
+
- eval_hotelFaxNumber_ent_type_f1: 0
|
255 |
+
- eval_hotelFaxNumber_partial_precision: 0.0001
|
256 |
+
- eval_hotelFaxNumber_partial_recall: 0.0031
|
257 |
+
- eval_hotelFaxNumber_partial_f1: 0.0001
|
258 |
+
- eval_hotelFaxNumber_exact_precision: 0.0
|
259 |
+
- eval_hotelFaxNumber_exact_recall: 0.0
|
260 |
+
- eval_hotelFaxNumber_exact_f1: 0
|
261 |
+
- eval_roomNo_strict_precision: 0.0001
|
262 |
+
- eval_roomNo_strict_recall: 0.0017
|
263 |
+
- eval_roomNo_strict_f1: 0.0001
|
264 |
+
- eval_roomNo_ent_type_precision: 0.0001
|
265 |
+
- eval_roomNo_ent_type_recall: 0.0017
|
266 |
+
- eval_roomNo_ent_type_f1: 0.0001
|
267 |
+
- eval_roomNo_partial_precision: 0.0001
|
268 |
+
- eval_roomNo_partial_recall: 0.0025
|
269 |
+
- eval_roomNo_partial_f1: 0.0002
|
270 |
+
- eval_roomNo_exact_precision: 0.0001
|
271 |
+
- eval_roomNo_exact_recall: 0.0017
|
272 |
+
- eval_roomNo_exact_f1: 0.0001
|
273 |
+
- eval_companyName_strict_precision: 0.0002
|
274 |
+
- eval_companyName_strict_recall: 0.0001
|
275 |
+
- eval_companyName_strict_f1: 0.0001
|
276 |
+
- eval_companyName_ent_type_precision: 0.0040
|
277 |
+
- eval_companyName_ent_type_recall: 0.0017
|
278 |
+
- eval_companyName_ent_type_f1: 0.0024
|
279 |
+
- eval_companyName_partial_precision: 0.0422
|
280 |
+
- eval_companyName_partial_recall: 0.0179
|
281 |
+
- eval_companyName_partial_f1: 0.0252
|
282 |
+
- eval_companyName_exact_precision: 0.0244
|
283 |
+
- eval_companyName_exact_recall: 0.0104
|
284 |
+
- eval_companyName_exact_f1: 0.0145
|
285 |
+
- eval_hotelEmail_strict_precision: 0.0
|
286 |
+
- eval_hotelEmail_strict_recall: 0.0
|
287 |
+
- eval_hotelEmail_strict_f1: 0
|
288 |
+
- eval_hotelEmail_ent_type_precision: 0.0
|
289 |
+
- eval_hotelEmail_ent_type_recall: 0.0
|
290 |
+
- eval_hotelEmail_ent_type_f1: 0
|
291 |
+
- eval_hotelEmail_partial_precision: 0.0024
|
292 |
+
- eval_hotelEmail_partial_recall: 0.0199
|
293 |
+
- eval_hotelEmail_partial_f1: 0.0043
|
294 |
+
- eval_hotelEmail_exact_precision: 0.0024
|
295 |
+
- eval_hotelEmail_exact_recall: 0.0199
|
296 |
+
- eval_hotelEmail_exact_f1: 0.0043
|
297 |
+
- eval_companyVATNumber_strict_precision: 0.0
|
298 |
+
- eval_companyVATNumber_strict_recall: 0.0
|
299 |
+
- eval_companyVATNumber_strict_f1: 0
|
300 |
+
- eval_companyVATNumber_ent_type_precision: 0.0
|
301 |
+
- eval_companyVATNumber_ent_type_recall: 0.0
|
302 |
+
- eval_companyVATNumber_ent_type_f1: 0
|
303 |
+
- eval_companyVATNumber_partial_precision: 0.0020
|
304 |
+
- eval_companyVATNumber_partial_recall: 0.0020
|
305 |
+
- eval_companyVATNumber_partial_f1: 0.0020
|
306 |
+
- eval_companyVATNumber_exact_precision: 0.0018
|
307 |
+
- eval_companyVATNumber_exact_recall: 0.0017
|
308 |
+
- eval_companyVATNumber_exact_f1: 0.0018
|
309 |
+
- eval_invoiceDate_strict_precision: 0.0
|
310 |
+
- eval_invoiceDate_strict_recall: 0.0
|
311 |
+
- eval_invoiceDate_strict_f1: 0
|
312 |
+
- eval_invoiceDate_ent_type_precision: 0.0
|
313 |
+
- eval_invoiceDate_ent_type_recall: 0.0
|
314 |
+
- eval_invoiceDate_ent_type_f1: 0
|
315 |
+
- eval_invoiceDate_partial_precision: 0.0058
|
316 |
+
- eval_invoiceDate_partial_recall: 0.0127
|
317 |
+
- eval_invoiceDate_partial_f1: 0.0080
|
318 |
+
- eval_invoiceDate_exact_precision: 0.0035
|
319 |
+
- eval_invoiceDate_exact_recall: 0.0077
|
320 |
+
- eval_invoiceDate_exact_f1: 0.0048
|
321 |
+
- eval_companyCity_strict_precision: 0.0
|
322 |
+
- eval_companyCity_strict_recall: 0.0
|
323 |
+
- eval_companyCity_strict_f1: 0
|
324 |
+
- eval_companyCity_ent_type_precision: 0.0
|
325 |
+
- eval_companyCity_ent_type_recall: 0.0
|
326 |
+
- eval_companyCity_ent_type_f1: 0
|
327 |
+
- eval_companyCity_partial_precision: 0.0012
|
328 |
+
- eval_companyCity_partial_recall: 0.0053
|
329 |
+
- eval_companyCity_partial_f1: 0.0020
|
330 |
+
- eval_companyCity_exact_precision: 0.0010
|
331 |
+
- eval_companyCity_exact_recall: 0.0044
|
332 |
+
- eval_companyCity_exact_f1: 0.0017
|
333 |
+
- eval_hotelPhoneNumber_strict_precision: 0.0
|
334 |
+
- eval_hotelPhoneNumber_strict_recall: 0.0
|
335 |
+
- eval_hotelPhoneNumber_strict_f1: 0
|
336 |
+
- eval_hotelPhoneNumber_ent_type_precision: 0.0
|
337 |
+
- eval_hotelPhoneNumber_ent_type_recall: 0.0
|
338 |
+
- eval_hotelPhoneNumber_ent_type_f1: 0
|
339 |
+
- eval_hotelPhoneNumber_partial_precision: 0.0006
|
340 |
+
- eval_hotelPhoneNumber_partial_recall: 0.0047
|
341 |
+
- eval_hotelPhoneNumber_partial_f1: 0.0011
|
342 |
+
- eval_hotelPhoneNumber_exact_precision: 0.0004
|
343 |
+
- eval_hotelPhoneNumber_exact_recall: 0.0031
|
344 |
+
- eval_hotelPhoneNumber_exact_f1: 0.0007
|
345 |
+
- eval_hotelTaxCode_strict_precision: 0.0
|
346 |
+
- eval_hotelTaxCode_strict_recall: 0.0
|
347 |
+
- eval_hotelTaxCode_strict_f1: 0
|
348 |
+
- eval_hotelTaxCode_ent_type_precision: 0.0
|
349 |
+
- eval_hotelTaxCode_ent_type_recall: 0.0
|
350 |
+
- eval_hotelTaxCode_ent_type_f1: 0
|
351 |
+
- eval_hotelTaxCode_partial_precision: 0.0007
|
352 |
+
- eval_hotelTaxCode_partial_recall: 0.0019
|
353 |
+
- eval_hotelTaxCode_partial_f1: 0.0010
|
354 |
+
- eval_hotelTaxCode_exact_precision: 0.0007
|
355 |
+
- eval_hotelTaxCode_exact_recall: 0.0019
|
356 |
+
- eval_hotelTaxCode_exact_f1: 0.0010
|
357 |
+
- eval_travellerName_strict_precision: 0.0
|
358 |
+
- eval_travellerName_strict_recall: 0.0
|
359 |
+
- eval_travellerName_strict_f1: 0
|
360 |
+
- eval_travellerName_ent_type_precision: 0.0
|
361 |
+
- eval_travellerName_ent_type_recall: 0.0
|
362 |
+
- eval_travellerName_ent_type_f1: 0
|
363 |
+
- eval_travellerName_partial_precision: 0.0010
|
364 |
+
- eval_travellerName_partial_recall: 0.0157
|
365 |
+
- eval_travellerName_partial_f1: 0.0019
|
366 |
+
- eval_travellerName_exact_precision: 0.0010
|
367 |
+
- eval_travellerName_exact_recall: 0.0157
|
368 |
+
- eval_travellerName_exact_f1: 0.0019
|
369 |
+
- eval_hotelCity_strict_precision: 0.0
|
370 |
+
- eval_hotelCity_strict_recall: 0.0
|
371 |
+
- eval_hotelCity_strict_f1: 0
|
372 |
+
- eval_hotelCity_ent_type_precision: 0.0001
|
373 |
+
- eval_hotelCity_ent_type_recall: 0.0002
|
374 |
+
- eval_hotelCity_ent_type_f1: 0.0001
|
375 |
+
- eval_hotelCity_partial_precision: 0.0044
|
376 |
+
- eval_hotelCity_partial_recall: 0.0140
|
377 |
+
- eval_hotelCity_partial_f1: 0.0067
|
378 |
+
- eval_hotelCity_exact_precision: 0.0035
|
379 |
+
- eval_hotelCity_exact_recall: 0.0111
|
380 |
+
- eval_hotelCity_exact_f1: 0.0053
|
381 |
+
- eval_checkIn_strict_precision: 0.0
|
382 |
+
- eval_checkIn_strict_recall: 0.0
|
383 |
+
- eval_checkIn_strict_f1: 0
|
384 |
+
- eval_checkIn_ent_type_precision: 0.0
|
385 |
+
- eval_checkIn_ent_type_recall: 0.0
|
386 |
+
- eval_checkIn_ent_type_f1: 0
|
387 |
+
- eval_checkIn_partial_precision: 0.0002
|
388 |
+
- eval_checkIn_partial_recall: 0.0009
|
389 |
+
- eval_checkIn_partial_f1: 0.0003
|
390 |
+
- eval_checkIn_exact_precision: 0.0001
|
391 |
+
- eval_checkIn_exact_recall: 0.0004
|
392 |
+
- eval_checkIn_exact_f1: 0.0001
|
393 |
+
- eval_currencyCode_strict_precision: 0.0
|
394 |
+
- eval_currencyCode_strict_recall: 0.0
|
395 |
+
- eval_currencyCode_strict_f1: 0
|
396 |
+
- eval_currencyCode_ent_type_precision: 0.0
|
397 |
+
- eval_currencyCode_ent_type_recall: 0.0
|
398 |
+
- eval_currencyCode_ent_type_f1: 0
|
399 |
+
- eval_currencyCode_partial_precision: 0.0001
|
400 |
+
- eval_currencyCode_partial_recall: 0.0018
|
401 |
+
- eval_currencyCode_partial_f1: 0.0002
|
402 |
+
- eval_currencyCode_exact_precision: 0.0
|
403 |
+
- eval_currencyCode_exact_recall: 0.0
|
404 |
+
- eval_currencyCode_exact_f1: 0
|
405 |
+
- eval_pageNumber_strict_precision: 0.0
|
406 |
+
- eval_pageNumber_strict_recall: 0.0
|
407 |
+
- eval_pageNumber_strict_f1: 0
|
408 |
+
- eval_pageNumber_ent_type_precision: 0.0
|
409 |
+
- eval_pageNumber_ent_type_recall: 0.0
|
410 |
+
- eval_pageNumber_ent_type_f1: 0
|
411 |
+
- eval_pageNumber_partial_precision: 0.0005
|
412 |
+
- eval_pageNumber_partial_recall: 0.0070
|
413 |
+
- eval_pageNumber_partial_f1: 0.0009
|
414 |
+
- eval_pageNumber_exact_precision: 0.0005
|
415 |
+
- eval_pageNumber_exact_recall: 0.0070
|
416 |
+
- eval_pageNumber_exact_f1: 0.0009
|
417 |
+
- eval_hotelZipCode_strict_precision: 0.0
|
418 |
+
- eval_hotelZipCode_strict_recall: 0.0
|
419 |
+
- eval_hotelZipCode_strict_f1: 0
|
420 |
+
- eval_hotelZipCode_ent_type_precision: 0.0
|
421 |
+
- eval_hotelZipCode_ent_type_recall: 0.0
|
422 |
+
- eval_hotelZipCode_ent_type_f1: 0
|
423 |
+
- eval_hotelZipCode_partial_precision: 0.0008
|
424 |
+
- eval_hotelZipCode_partial_recall: 0.0039
|
425 |
+
- eval_hotelZipCode_partial_f1: 0.0013
|
426 |
+
- eval_hotelZipCode_exact_precision: 0.0006
|
427 |
+
- eval_hotelZipCode_exact_recall: 0.0031
|
428 |
+
- eval_hotelZipCode_exact_f1: 0.0010
|
429 |
+
- eval_taxAmount_strict_precision: 0.0
|
430 |
+
- eval_taxAmount_strict_recall: 0.0
|
431 |
+
- eval_taxAmount_strict_f1: 0
|
432 |
+
- eval_taxAmount_ent_type_precision: 0.0008
|
433 |
+
- eval_taxAmount_ent_type_recall: 0.0004
|
434 |
+
- eval_taxAmount_ent_type_f1: 0.0005
|
435 |
+
- eval_taxAmount_partial_precision: 0.0723
|
436 |
+
- eval_taxAmount_partial_recall: 0.0353
|
437 |
+
- eval_taxAmount_partial_f1: 0.0474
|
438 |
+
- eval_taxAmount_exact_precision: 0.0608
|
439 |
+
- eval_taxAmount_exact_recall: 0.0296
|
440 |
+
- eval_taxAmount_exact_f1: 0.0399
|
441 |
+
- eval_runtime: 24.6705
|
442 |
+
- eval_samples_per_second: 40.413
|
443 |
+
- eval_steps_per_second: 1.297
|
444 |
+
- step: 0
|
445 |
+
|
446 |
+
## Model description
|
447 |
+
|
448 |
+
More information needed
|
449 |
+
|
450 |
+
## Intended uses & limitations
|
451 |
+
|
452 |
+
More information needed
|
453 |
+
|
454 |
+
## Training and evaluation data
|
455 |
+
|
456 |
+
More information needed
|
457 |
+
|
458 |
+
## Training procedure
|
459 |
+
|
460 |
+
### Training hyperparameters
|
461 |
+
|
462 |
+
The following hyperparameters were used during training:
|
463 |
+
- learning_rate: 2e-05
|
464 |
+
- train_batch_size: 32
|
465 |
+
- eval_batch_size: 32
|
466 |
+
- seed: 42
|
467 |
+
- gradient_accumulation_steps: 16
|
468 |
+
- total_train_batch_size: 512
|
469 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
470 |
+
- lr_scheduler_type: linear
|
471 |
+
- lr_scheduler_warmup_ratio: 0.5
|
472 |
+
- num_epochs: 8
|
473 |
+
|
474 |
+
### Framework versions
|
475 |
+
|
476 |
+
- Transformers 4.48.0.dev0
|
477 |
+
- Pytorch 2.3.1
|
478 |
+
- Datasets 3.2.0
|
479 |
+
- Tokenizers 0.21.0
|
config.json
ADDED
@@ -0,0 +1,188 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "answerdotai/ModernBERT-base",
|
3 |
+
"architectures": [
|
4 |
+
"ModernBertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 50281,
|
9 |
+
"classifier_activation": "gelu",
|
10 |
+
"classifier_bias": false,
|
11 |
+
"classifier_dropout": 0.0,
|
12 |
+
"classifier_pooling": "mean",
|
13 |
+
"cls_token_id": 50281,
|
14 |
+
"decoder_bias": true,
|
15 |
+
"deterministic_flash_attn": false,
|
16 |
+
"embedding_dropout": 0.0,
|
17 |
+
"eos_token_id": 50282,
|
18 |
+
"global_attn_every_n_layers": 3,
|
19 |
+
"global_rope_theta": 160000.0,
|
20 |
+
"gradient_checkpointing": false,
|
21 |
+
"hidden_activation": "gelu",
|
22 |
+
"hidden_size": 768,
|
23 |
+
"id2label": {
|
24 |
+
"0": "O",
|
25 |
+
"1": "B-bookingNumber",
|
26 |
+
"2": "I-bookingNumber",
|
27 |
+
"3": "B-cardNumber",
|
28 |
+
"4": "I-cardNumber",
|
29 |
+
"5": "B-cardType",
|
30 |
+
"6": "I-cardType",
|
31 |
+
"7": "B-checkIn",
|
32 |
+
"8": "I-checkIn",
|
33 |
+
"9": "B-checkOut",
|
34 |
+
"10": "I-checkOut",
|
35 |
+
"11": "B-companyAddress",
|
36 |
+
"12": "I-companyAddress",
|
37 |
+
"13": "B-companyCity",
|
38 |
+
"14": "I-companyCity",
|
39 |
+
"15": "B-companyCountry",
|
40 |
+
"16": "I-companyCountry",
|
41 |
+
"17": "B-companyName",
|
42 |
+
"18": "I-companyName",
|
43 |
+
"19": "B-companyVATNumber",
|
44 |
+
"20": "I-companyVATNumber",
|
45 |
+
"21": "B-companyZipcode",
|
46 |
+
"22": "I-companyZipcode",
|
47 |
+
"23": "B-currencyCode",
|
48 |
+
"24": "I-currencyCode",
|
49 |
+
"25": "B-documentType",
|
50 |
+
"26": "I-documentType",
|
51 |
+
"27": "B-externalReservationNumber",
|
52 |
+
"28": "I-externalReservationNumber",
|
53 |
+
"29": "B-grossAmount",
|
54 |
+
"30": "I-grossAmount",
|
55 |
+
"31": "B-hotelAddress",
|
56 |
+
"32": "I-hotelAddress",
|
57 |
+
"33": "B-hotelBankAccount",
|
58 |
+
"34": "I-hotelBankAccount",
|
59 |
+
"35": "B-hotelCity",
|
60 |
+
"36": "I-hotelCity",
|
61 |
+
"37": "B-hotelCountry",
|
62 |
+
"38": "I-hotelCountry",
|
63 |
+
"39": "B-hotelEmail",
|
64 |
+
"40": "I-hotelEmail",
|
65 |
+
"41": "B-hotelFaxNumber",
|
66 |
+
"42": "I-hotelFaxNumber",
|
67 |
+
"43": "B-hotelName",
|
68 |
+
"44": "I-hotelName",
|
69 |
+
"45": "B-hotelPhoneNumber",
|
70 |
+
"46": "I-hotelPhoneNumber",
|
71 |
+
"47": "B-hotelTaxCode",
|
72 |
+
"48": "I-hotelTaxCode",
|
73 |
+
"49": "B-hotelVATNumber",
|
74 |
+
"50": "I-hotelVATNumber",
|
75 |
+
"51": "B-hotelZipCode",
|
76 |
+
"52": "I-hotelZipCode",
|
77 |
+
"53": "B-invoiceDate",
|
78 |
+
"54": "I-invoiceDate",
|
79 |
+
"55": "B-invoiceNumber",
|
80 |
+
"56": "I-invoiceNumber",
|
81 |
+
"57": "B-netAmount",
|
82 |
+
"58": "I-netAmount",
|
83 |
+
"59": "B-pageNumber",
|
84 |
+
"60": "I-pageNumber",
|
85 |
+
"61": "B-reservationNumber",
|
86 |
+
"62": "I-reservationNumber",
|
87 |
+
"63": "B-roomNo",
|
88 |
+
"64": "I-roomNo",
|
89 |
+
"65": "B-taxAmount",
|
90 |
+
"66": "I-taxAmount",
|
91 |
+
"67": "B-travellerName",
|
92 |
+
"68": "I-travellerName"
|
93 |
+
},
|
94 |
+
"initializer_cutoff_factor": 2.0,
|
95 |
+
"initializer_range": 0.02,
|
96 |
+
"intermediate_size": 1152,
|
97 |
+
"label2id": {
|
98 |
+
"B-bookingNumber": 1,
|
99 |
+
"B-cardNumber": 3,
|
100 |
+
"B-cardType": 5,
|
101 |
+
"B-checkIn": 7,
|
102 |
+
"B-checkOut": 9,
|
103 |
+
"B-companyAddress": 11,
|
104 |
+
"B-companyCity": 13,
|
105 |
+
"B-companyCountry": 15,
|
106 |
+
"B-companyName": 17,
|
107 |
+
"B-companyVATNumber": 19,
|
108 |
+
"B-companyZipcode": 21,
|
109 |
+
"B-currencyCode": 23,
|
110 |
+
"B-documentType": 25,
|
111 |
+
"B-externalReservationNumber": 27,
|
112 |
+
"B-grossAmount": 29,
|
113 |
+
"B-hotelAddress": 31,
|
114 |
+
"B-hotelBankAccount": 33,
|
115 |
+
"B-hotelCity": 35,
|
116 |
+
"B-hotelCountry": 37,
|
117 |
+
"B-hotelEmail": 39,
|
118 |
+
"B-hotelFaxNumber": 41,
|
119 |
+
"B-hotelName": 43,
|
120 |
+
"B-hotelPhoneNumber": 45,
|
121 |
+
"B-hotelTaxCode": 47,
|
122 |
+
"B-hotelVATNumber": 49,
|
123 |
+
"B-hotelZipCode": 51,
|
124 |
+
"B-invoiceDate": 53,
|
125 |
+
"B-invoiceNumber": 55,
|
126 |
+
"B-netAmount": 57,
|
127 |
+
"B-pageNumber": 59,
|
128 |
+
"B-reservationNumber": 61,
|
129 |
+
"B-roomNo": 63,
|
130 |
+
"B-taxAmount": 65,
|
131 |
+
"B-travellerName": 67,
|
132 |
+
"I-bookingNumber": 2,
|
133 |
+
"I-cardNumber": 4,
|
134 |
+
"I-cardType": 6,
|
135 |
+
"I-checkIn": 8,
|
136 |
+
"I-checkOut": 10,
|
137 |
+
"I-companyAddress": 12,
|
138 |
+
"I-companyCity": 14,
|
139 |
+
"I-companyCountry": 16,
|
140 |
+
"I-companyName": 18,
|
141 |
+
"I-companyVATNumber": 20,
|
142 |
+
"I-companyZipcode": 22,
|
143 |
+
"I-currencyCode": 24,
|
144 |
+
"I-documentType": 26,
|
145 |
+
"I-externalReservationNumber": 28,
|
146 |
+
"I-grossAmount": 30,
|
147 |
+
"I-hotelAddress": 32,
|
148 |
+
"I-hotelBankAccount": 34,
|
149 |
+
"I-hotelCity": 36,
|
150 |
+
"I-hotelCountry": 38,
|
151 |
+
"I-hotelEmail": 40,
|
152 |
+
"I-hotelFaxNumber": 42,
|
153 |
+
"I-hotelName": 44,
|
154 |
+
"I-hotelPhoneNumber": 46,
|
155 |
+
"I-hotelTaxCode": 48,
|
156 |
+
"I-hotelVATNumber": 50,
|
157 |
+
"I-hotelZipCode": 52,
|
158 |
+
"I-invoiceDate": 54,
|
159 |
+
"I-invoiceNumber": 56,
|
160 |
+
"I-netAmount": 58,
|
161 |
+
"I-pageNumber": 60,
|
162 |
+
"I-reservationNumber": 62,
|
163 |
+
"I-roomNo": 64,
|
164 |
+
"I-taxAmount": 66,
|
165 |
+
"I-travellerName": 68,
|
166 |
+
"O": 0
|
167 |
+
},
|
168 |
+
"layer_norm_eps": 1e-05,
|
169 |
+
"local_attention": 128,
|
170 |
+
"local_rope_theta": 10000.0,
|
171 |
+
"max_position_embeddings": 8192,
|
172 |
+
"mlp_bias": false,
|
173 |
+
"mlp_dropout": 0.0,
|
174 |
+
"model_type": "modernbert",
|
175 |
+
"norm_bias": false,
|
176 |
+
"norm_eps": 1e-05,
|
177 |
+
"num_attention_heads": 12,
|
178 |
+
"num_hidden_layers": 22,
|
179 |
+
"pad_token_id": 50283,
|
180 |
+
"position_embedding_type": "absolute",
|
181 |
+
"reference_compile": false,
|
182 |
+
"sep_token_id": 50282,
|
183 |
+
"sparse_pred_ignore_index": -100,
|
184 |
+
"sparse_prediction": false,
|
185 |
+
"torch_dtype": "bfloat16",
|
186 |
+
"transformers_version": "4.48.0.dev0",
|
187 |
+
"vocab_size": 50368
|
188 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c37faf916a3302280d02d444eb70f66f6f45896c7e7a06e0f3478186ad6cbdb
|
3 |
+
size 299330146
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,946 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "|||IP_ADDRESS|||",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": false
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<|padding|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"50254": {
|
21 |
+
"content": " ",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"50255": {
|
29 |
+
"content": " ",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"50256": {
|
37 |
+
"content": " ",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"50257": {
|
45 |
+
"content": " ",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"50258": {
|
53 |
+
"content": " ",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"50259": {
|
61 |
+
"content": " ",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"50260": {
|
69 |
+
"content": " ",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"50261": {
|
77 |
+
"content": " ",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"50262": {
|
85 |
+
"content": " ",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"50263": {
|
93 |
+
"content": " ",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"50264": {
|
101 |
+
"content": " ",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"50265": {
|
109 |
+
"content": " ",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"50266": {
|
117 |
+
"content": " ",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"50267": {
|
125 |
+
"content": " ",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"50268": {
|
133 |
+
"content": " ",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"50269": {
|
141 |
+
"content": " ",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"50270": {
|
149 |
+
"content": " ",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"50271": {
|
157 |
+
"content": " ",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"50272": {
|
165 |
+
"content": " ",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"50273": {
|
173 |
+
"content": " ",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"50274": {
|
181 |
+
"content": " ",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"50275": {
|
189 |
+
"content": " ",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"50276": {
|
197 |
+
"content": " ",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"50277": {
|
205 |
+
"content": "|||EMAIL_ADDRESS|||",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": true,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
},
|
212 |
+
"50278": {
|
213 |
+
"content": "|||PHONE_NUMBER|||",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": true,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"50279": {
|
221 |
+
"content": "<|endoftext|>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"50280": {
|
229 |
+
"content": "[UNK]",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"50281": {
|
237 |
+
"content": "[CLS]",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"50282": {
|
245 |
+
"content": "[SEP]",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"50283": {
|
253 |
+
"content": "[PAD]",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"50284": {
|
261 |
+
"content": "[MASK]",
|
262 |
+
"lstrip": true,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"50285": {
|
269 |
+
"content": "[unused0]",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": true,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
"50286": {
|
277 |
+
"content": "[unused1]",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": true,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": false
|
283 |
+
},
|
284 |
+
"50287": {
|
285 |
+
"content": "[unused2]",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": true,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": false
|
291 |
+
},
|
292 |
+
"50288": {
|
293 |
+
"content": "[unused3]",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": true,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": false
|
299 |
+
},
|
300 |
+
"50289": {
|
301 |
+
"content": "[unused4]",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": true,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
"50290": {
|
309 |
+
"content": "[unused5]",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": true,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": false
|
315 |
+
},
|
316 |
+
"50291": {
|
317 |
+
"content": "[unused6]",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": true,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": false
|
323 |
+
},
|
324 |
+
"50292": {
|
325 |
+
"content": "[unused7]",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": true,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": false
|
331 |
+
},
|
332 |
+
"50293": {
|
333 |
+
"content": "[unused8]",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": true,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": false
|
339 |
+
},
|
340 |
+
"50294": {
|
341 |
+
"content": "[unused9]",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": true,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": false
|
347 |
+
},
|
348 |
+
"50295": {
|
349 |
+
"content": "[unused10]",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": true,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": false
|
355 |
+
},
|
356 |
+
"50296": {
|
357 |
+
"content": "[unused11]",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": true,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": false
|
363 |
+
},
|
364 |
+
"50297": {
|
365 |
+
"content": "[unused12]",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": true,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": false
|
371 |
+
},
|
372 |
+
"50298": {
|
373 |
+
"content": "[unused13]",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": true,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": false
|
379 |
+
},
|
380 |
+
"50299": {
|
381 |
+
"content": "[unused14]",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": true,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": false
|
387 |
+
},
|
388 |
+
"50300": {
|
389 |
+
"content": "[unused15]",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": true,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": false
|
395 |
+
},
|
396 |
+
"50301": {
|
397 |
+
"content": "[unused16]",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": true,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": false
|
403 |
+
},
|
404 |
+
"50302": {
|
405 |
+
"content": "[unused17]",
|
406 |
+
"lstrip": false,
|
407 |
+
"normalized": true,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": false
|
411 |
+
},
|
412 |
+
"50303": {
|
413 |
+
"content": "[unused18]",
|
414 |
+
"lstrip": false,
|
415 |
+
"normalized": true,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": false
|
419 |
+
},
|
420 |
+
"50304": {
|
421 |
+
"content": "[unused19]",
|
422 |
+
"lstrip": false,
|
423 |
+
"normalized": true,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": false
|
427 |
+
},
|
428 |
+
"50305": {
|
429 |
+
"content": "[unused20]",
|
430 |
+
"lstrip": false,
|
431 |
+
"normalized": true,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": false
|
435 |
+
},
|
436 |
+
"50306": {
|
437 |
+
"content": "[unused21]",
|
438 |
+
"lstrip": false,
|
439 |
+
"normalized": true,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": false
|
443 |
+
},
|
444 |
+
"50307": {
|
445 |
+
"content": "[unused22]",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": true,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": false
|
451 |
+
},
|
452 |
+
"50308": {
|
453 |
+
"content": "[unused23]",
|
454 |
+
"lstrip": false,
|
455 |
+
"normalized": true,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": false
|
459 |
+
},
|
460 |
+
"50309": {
|
461 |
+
"content": "[unused24]",
|
462 |
+
"lstrip": false,
|
463 |
+
"normalized": true,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": false
|
467 |
+
},
|
468 |
+
"50310": {
|
469 |
+
"content": "[unused25]",
|
470 |
+
"lstrip": false,
|
471 |
+
"normalized": true,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": false
|
475 |
+
},
|
476 |
+
"50311": {
|
477 |
+
"content": "[unused26]",
|
478 |
+
"lstrip": false,
|
479 |
+
"normalized": true,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": false
|
483 |
+
},
|
484 |
+
"50312": {
|
485 |
+
"content": "[unused27]",
|
486 |
+
"lstrip": false,
|
487 |
+
"normalized": true,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": false
|
491 |
+
},
|
492 |
+
"50313": {
|
493 |
+
"content": "[unused28]",
|
494 |
+
"lstrip": false,
|
495 |
+
"normalized": true,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": false
|
499 |
+
},
|
500 |
+
"50314": {
|
501 |
+
"content": "[unused29]",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": true,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": false
|
507 |
+
},
|
508 |
+
"50315": {
|
509 |
+
"content": "[unused30]",
|
510 |
+
"lstrip": false,
|
511 |
+
"normalized": true,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": false
|
515 |
+
},
|
516 |
+
"50316": {
|
517 |
+
"content": "[unused31]",
|
518 |
+
"lstrip": false,
|
519 |
+
"normalized": true,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": false
|
523 |
+
},
|
524 |
+
"50317": {
|
525 |
+
"content": "[unused32]",
|
526 |
+
"lstrip": false,
|
527 |
+
"normalized": true,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": false
|
531 |
+
},
|
532 |
+
"50318": {
|
533 |
+
"content": "[unused33]",
|
534 |
+
"lstrip": false,
|
535 |
+
"normalized": true,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": false
|
539 |
+
},
|
540 |
+
"50319": {
|
541 |
+
"content": "[unused34]",
|
542 |
+
"lstrip": false,
|
543 |
+
"normalized": true,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": false
|
547 |
+
},
|
548 |
+
"50320": {
|
549 |
+
"content": "[unused35]",
|
550 |
+
"lstrip": false,
|
551 |
+
"normalized": true,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": false
|
555 |
+
},
|
556 |
+
"50321": {
|
557 |
+
"content": "[unused36]",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": true,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": false
|
563 |
+
},
|
564 |
+
"50322": {
|
565 |
+
"content": "[unused37]",
|
566 |
+
"lstrip": false,
|
567 |
+
"normalized": true,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": false
|
571 |
+
},
|
572 |
+
"50323": {
|
573 |
+
"content": "[unused38]",
|
574 |
+
"lstrip": false,
|
575 |
+
"normalized": true,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": false
|
579 |
+
},
|
580 |
+
"50324": {
|
581 |
+
"content": "[unused39]",
|
582 |
+
"lstrip": false,
|
583 |
+
"normalized": true,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": false
|
587 |
+
},
|
588 |
+
"50325": {
|
589 |
+
"content": "[unused40]",
|
590 |
+
"lstrip": false,
|
591 |
+
"normalized": true,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": false
|
595 |
+
},
|
596 |
+
"50326": {
|
597 |
+
"content": "[unused41]",
|
598 |
+
"lstrip": false,
|
599 |
+
"normalized": true,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": false
|
603 |
+
},
|
604 |
+
"50327": {
|
605 |
+
"content": "[unused42]",
|
606 |
+
"lstrip": false,
|
607 |
+
"normalized": true,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": false
|
611 |
+
},
|
612 |
+
"50328": {
|
613 |
+
"content": "[unused43]",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": true,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": false
|
619 |
+
},
|
620 |
+
"50329": {
|
621 |
+
"content": "[unused44]",
|
622 |
+
"lstrip": false,
|
623 |
+
"normalized": true,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": false
|
627 |
+
},
|
628 |
+
"50330": {
|
629 |
+
"content": "[unused45]",
|
630 |
+
"lstrip": false,
|
631 |
+
"normalized": true,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": false
|
635 |
+
},
|
636 |
+
"50331": {
|
637 |
+
"content": "[unused46]",
|
638 |
+
"lstrip": false,
|
639 |
+
"normalized": true,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": false
|
643 |
+
},
|
644 |
+
"50332": {
|
645 |
+
"content": "[unused47]",
|
646 |
+
"lstrip": false,
|
647 |
+
"normalized": true,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": false
|
651 |
+
},
|
652 |
+
"50333": {
|
653 |
+
"content": "[unused48]",
|
654 |
+
"lstrip": false,
|
655 |
+
"normalized": true,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": false
|
659 |
+
},
|
660 |
+
"50334": {
|
661 |
+
"content": "[unused49]",
|
662 |
+
"lstrip": false,
|
663 |
+
"normalized": true,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": false
|
667 |
+
},
|
668 |
+
"50335": {
|
669 |
+
"content": "[unused50]",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": true,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": false
|
675 |
+
},
|
676 |
+
"50336": {
|
677 |
+
"content": "[unused51]",
|
678 |
+
"lstrip": false,
|
679 |
+
"normalized": true,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": false
|
683 |
+
},
|
684 |
+
"50337": {
|
685 |
+
"content": "[unused52]",
|
686 |
+
"lstrip": false,
|
687 |
+
"normalized": true,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": false
|
691 |
+
},
|
692 |
+
"50338": {
|
693 |
+
"content": "[unused53]",
|
694 |
+
"lstrip": false,
|
695 |
+
"normalized": true,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": false
|
699 |
+
},
|
700 |
+
"50339": {
|
701 |
+
"content": "[unused54]",
|
702 |
+
"lstrip": false,
|
703 |
+
"normalized": true,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": false
|
707 |
+
},
|
708 |
+
"50340": {
|
709 |
+
"content": "[unused55]",
|
710 |
+
"lstrip": false,
|
711 |
+
"normalized": true,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": false
|
715 |
+
},
|
716 |
+
"50341": {
|
717 |
+
"content": "[unused56]",
|
718 |
+
"lstrip": false,
|
719 |
+
"normalized": true,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": false
|
723 |
+
},
|
724 |
+
"50342": {
|
725 |
+
"content": "[unused57]",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": true,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": false
|
731 |
+
},
|
732 |
+
"50343": {
|
733 |
+
"content": "[unused58]",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": true,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": false
|
739 |
+
},
|
740 |
+
"50344": {
|
741 |
+
"content": "[unused59]",
|
742 |
+
"lstrip": false,
|
743 |
+
"normalized": true,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": false
|
747 |
+
},
|
748 |
+
"50345": {
|
749 |
+
"content": "[unused60]",
|
750 |
+
"lstrip": false,
|
751 |
+
"normalized": true,
|
752 |
+
"rstrip": false,
|
753 |
+
"single_word": false,
|
754 |
+
"special": false
|
755 |
+
},
|
756 |
+
"50346": {
|
757 |
+
"content": "[unused61]",
|
758 |
+
"lstrip": false,
|
759 |
+
"normalized": true,
|
760 |
+
"rstrip": false,
|
761 |
+
"single_word": false,
|
762 |
+
"special": false
|
763 |
+
},
|
764 |
+
"50347": {
|
765 |
+
"content": "[unused62]",
|
766 |
+
"lstrip": false,
|
767 |
+
"normalized": true,
|
768 |
+
"rstrip": false,
|
769 |
+
"single_word": false,
|
770 |
+
"special": false
|
771 |
+
},
|
772 |
+
"50348": {
|
773 |
+
"content": "[unused63]",
|
774 |
+
"lstrip": false,
|
775 |
+
"normalized": true,
|
776 |
+
"rstrip": false,
|
777 |
+
"single_word": false,
|
778 |
+
"special": false
|
779 |
+
},
|
780 |
+
"50349": {
|
781 |
+
"content": "[unused64]",
|
782 |
+
"lstrip": false,
|
783 |
+
"normalized": true,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false,
|
786 |
+
"special": false
|
787 |
+
},
|
788 |
+
"50350": {
|
789 |
+
"content": "[unused65]",
|
790 |
+
"lstrip": false,
|
791 |
+
"normalized": true,
|
792 |
+
"rstrip": false,
|
793 |
+
"single_word": false,
|
794 |
+
"special": false
|
795 |
+
},
|
796 |
+
"50351": {
|
797 |
+
"content": "[unused66]",
|
798 |
+
"lstrip": false,
|
799 |
+
"normalized": true,
|
800 |
+
"rstrip": false,
|
801 |
+
"single_word": false,
|
802 |
+
"special": false
|
803 |
+
},
|
804 |
+
"50352": {
|
805 |
+
"content": "[unused67]",
|
806 |
+
"lstrip": false,
|
807 |
+
"normalized": true,
|
808 |
+
"rstrip": false,
|
809 |
+
"single_word": false,
|
810 |
+
"special": false
|
811 |
+
},
|
812 |
+
"50353": {
|
813 |
+
"content": "[unused68]",
|
814 |
+
"lstrip": false,
|
815 |
+
"normalized": true,
|
816 |
+
"rstrip": false,
|
817 |
+
"single_word": false,
|
818 |
+
"special": false
|
819 |
+
},
|
820 |
+
"50354": {
|
821 |
+
"content": "[unused69]",
|
822 |
+
"lstrip": false,
|
823 |
+
"normalized": true,
|
824 |
+
"rstrip": false,
|
825 |
+
"single_word": false,
|
826 |
+
"special": false
|
827 |
+
},
|
828 |
+
"50355": {
|
829 |
+
"content": "[unused70]",
|
830 |
+
"lstrip": false,
|
831 |
+
"normalized": true,
|
832 |
+
"rstrip": false,
|
833 |
+
"single_word": false,
|
834 |
+
"special": false
|
835 |
+
},
|
836 |
+
"50356": {
|
837 |
+
"content": "[unused71]",
|
838 |
+
"lstrip": false,
|
839 |
+
"normalized": true,
|
840 |
+
"rstrip": false,
|
841 |
+
"single_word": false,
|
842 |
+
"special": false
|
843 |
+
},
|
844 |
+
"50357": {
|
845 |
+
"content": "[unused72]",
|
846 |
+
"lstrip": false,
|
847 |
+
"normalized": true,
|
848 |
+
"rstrip": false,
|
849 |
+
"single_word": false,
|
850 |
+
"special": false
|
851 |
+
},
|
852 |
+
"50358": {
|
853 |
+
"content": "[unused73]",
|
854 |
+
"lstrip": false,
|
855 |
+
"normalized": true,
|
856 |
+
"rstrip": false,
|
857 |
+
"single_word": false,
|
858 |
+
"special": false
|
859 |
+
},
|
860 |
+
"50359": {
|
861 |
+
"content": "[unused74]",
|
862 |
+
"lstrip": false,
|
863 |
+
"normalized": true,
|
864 |
+
"rstrip": false,
|
865 |
+
"single_word": false,
|
866 |
+
"special": false
|
867 |
+
},
|
868 |
+
"50360": {
|
869 |
+
"content": "[unused75]",
|
870 |
+
"lstrip": false,
|
871 |
+
"normalized": true,
|
872 |
+
"rstrip": false,
|
873 |
+
"single_word": false,
|
874 |
+
"special": false
|
875 |
+
},
|
876 |
+
"50361": {
|
877 |
+
"content": "[unused76]",
|
878 |
+
"lstrip": false,
|
879 |
+
"normalized": true,
|
880 |
+
"rstrip": false,
|
881 |
+
"single_word": false,
|
882 |
+
"special": false
|
883 |
+
},
|
884 |
+
"50362": {
|
885 |
+
"content": "[unused77]",
|
886 |
+
"lstrip": false,
|
887 |
+
"normalized": true,
|
888 |
+
"rstrip": false,
|
889 |
+
"single_word": false,
|
890 |
+
"special": false
|
891 |
+
},
|
892 |
+
"50363": {
|
893 |
+
"content": "[unused78]",
|
894 |
+
"lstrip": false,
|
895 |
+
"normalized": true,
|
896 |
+
"rstrip": false,
|
897 |
+
"single_word": false,
|
898 |
+
"special": false
|
899 |
+
},
|
900 |
+
"50364": {
|
901 |
+
"content": "[unused79]",
|
902 |
+
"lstrip": false,
|
903 |
+
"normalized": true,
|
904 |
+
"rstrip": false,
|
905 |
+
"single_word": false,
|
906 |
+
"special": false
|
907 |
+
},
|
908 |
+
"50365": {
|
909 |
+
"content": "[unused80]",
|
910 |
+
"lstrip": false,
|
911 |
+
"normalized": true,
|
912 |
+
"rstrip": false,
|
913 |
+
"single_word": false,
|
914 |
+
"special": false
|
915 |
+
},
|
916 |
+
"50366": {
|
917 |
+
"content": "[unused81]",
|
918 |
+
"lstrip": false,
|
919 |
+
"normalized": true,
|
920 |
+
"rstrip": false,
|
921 |
+
"single_word": false,
|
922 |
+
"special": false
|
923 |
+
},
|
924 |
+
"50367": {
|
925 |
+
"content": "[unused82]",
|
926 |
+
"lstrip": false,
|
927 |
+
"normalized": true,
|
928 |
+
"rstrip": false,
|
929 |
+
"single_word": false,
|
930 |
+
"special": false
|
931 |
+
}
|
932 |
+
},
|
933 |
+
"clean_up_tokenization_spaces": true,
|
934 |
+
"cls_token": "[CLS]",
|
935 |
+
"extra_special_tokens": {},
|
936 |
+
"mask_token": "[MASK]",
|
937 |
+
"model_input_names": [
|
938 |
+
"input_ids",
|
939 |
+
"attention_mask"
|
940 |
+
],
|
941 |
+
"model_max_length": 1000000000000000019884624838656,
|
942 |
+
"pad_token": "[PAD]",
|
943 |
+
"sep_token": "[SEP]",
|
944 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
945 |
+
"unk_token": "[UNK]"
|
946 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:096aa2f0f2b3017cba4dce91bac4f3cebbceb94e2bd2c99dabe47b7c59762ed8
|
3 |
+
size 5432
|