official
#1
by
mago18
- opened
- added_tokens.json +146 -0
- config.json +24 -0
- hparams.yaml +1 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +18 -0
- tokenizer_config.json +23 -0
added_tokens.json
ADDED
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s_Acceso>": 57533,
|
3 |
+
"</s_Avance_Obra>": 57593,
|
4 |
+
"</s_CP>": 57553,
|
5 |
+
"</s_Calle>": 57555,
|
6 |
+
"</s_Caracteristicas>": 57571,
|
7 |
+
"</s_Cedula_arqui_cont>": 57649,
|
8 |
+
"</s_Cedula_arqui_val>": 57641,
|
9 |
+
"</s_Cedula_cont>": 57651,
|
10 |
+
"</s_Cedula_val>": 57643,
|
11 |
+
"</s_Ciudad>": 57557,
|
12 |
+
"</s_Colonia>": 57559,
|
13 |
+
"</s_Construcion_M2>": 57573,
|
14 |
+
"</s_Consultora>": 57527,
|
15 |
+
"</s_Controlador>": 57647,
|
16 |
+
"</s_Costo_insta>": 57657,
|
17 |
+
"</s_Costo_neto_repo>": 57595,
|
18 |
+
"</s_Costo_neto_repo_dem>": 57597,
|
19 |
+
"</s_Costo_uni_neto_repo>": 57599,
|
20 |
+
"</s_Deterioro>": 57601,
|
21 |
+
"</s_Dis_val_com_homo>": 57611,
|
22 |
+
"</s_Dis_val_com_pre_homo>": 57613,
|
23 |
+
"</s_Edad_const>": 57575,
|
24 |
+
"</s_Enfoque>": 57609,
|
25 |
+
"</s_Equipo_Urbano>": 57637,
|
26 |
+
"</s_Escritura>": 57535,
|
27 |
+
"</s_Estado>": 57561,
|
28 |
+
"</s_Factor>": 57615,
|
29 |
+
"</s_Fecha_del_avaluo>": 57537,
|
30 |
+
"</s_Generales>": 57531,
|
31 |
+
"</s_Georeferencia>": 57563,
|
32 |
+
"</s_ID>": 57529,
|
33 |
+
"</s_Identiicador>": 57525,
|
34 |
+
"</s_Indice_fisico>": 57603,
|
35 |
+
"</s_Infraestructura>": 57633,
|
36 |
+
"</s_Interior>": 57655,
|
37 |
+
"</s_Lote>": 57565,
|
38 |
+
"</s_Manzana>": 57567,
|
39 |
+
"</s_Notas>": 57661,
|
40 |
+
"</s_Numero_de_avaluo>": 57539,
|
41 |
+
"</s_Numero_exterior>": 57569,
|
42 |
+
"</s_Ocupacion>": 57541,
|
43 |
+
"</s_Precio>": 57627,
|
44 |
+
"</s_Predial>": 57543,
|
45 |
+
"</s_Propietario>": 57545,
|
46 |
+
"</s_Proposito>": 57547,
|
47 |
+
"</s_Prototipo>": 57577,
|
48 |
+
"</s_Relacion_valor>": 57617,
|
49 |
+
"</s_SHF>": 57663,
|
50 |
+
"</s_Servicios_muni>": 57635,
|
51 |
+
"</s_Solicitante>": 57659,
|
52 |
+
"</s_Tipo_de_inmueble>": 57549,
|
53 |
+
"</s_Ubicacion>": 57551,
|
54 |
+
"</s_Val_comp_merc>": 57619,
|
55 |
+
"</s_Val_hip>": 57621,
|
56 |
+
"</s_Val_uni_con_dete>": 57623,
|
57 |
+
"</s_Val_uni_sin_dete>": 57625,
|
58 |
+
"</s_Valor_concluido>": 57629,
|
59 |
+
"</s_Valor_fisico>": 57605,
|
60 |
+
"</s_Valor_homo_M2>": 57607,
|
61 |
+
"</s_Valores_Calculados>": 57591,
|
62 |
+
"</s_Valuador>": 57639,
|
63 |
+
"</s_contro>": 57653,
|
64 |
+
"</s_letra>": 57631,
|
65 |
+
"</s_no_banos>": 57579,
|
66 |
+
"</s_no_estacionamiento>": 57581,
|
67 |
+
"</s_no_niv_UV>": 57583,
|
68 |
+
"</s_no_recamaras>": 57585,
|
69 |
+
"</s_terreno_M2>": 57587,
|
70 |
+
"</s_valu>": 57645,
|
71 |
+
"</s_vendible_M2>": 57589,
|
72 |
+
"<s_Acceso>": 57534,
|
73 |
+
"<s_Avance_Obra>": 57594,
|
74 |
+
"<s_CP>": 57554,
|
75 |
+
"<s_Calle>": 57556,
|
76 |
+
"<s_Caracteristicas>": 57572,
|
77 |
+
"<s_Cedula_arqui_cont>": 57650,
|
78 |
+
"<s_Cedula_arqui_val>": 57642,
|
79 |
+
"<s_Cedula_cont>": 57652,
|
80 |
+
"<s_Cedula_val>": 57644,
|
81 |
+
"<s_Ciudad>": 57558,
|
82 |
+
"<s_Colonia>": 57560,
|
83 |
+
"<s_Construcion_M2>": 57574,
|
84 |
+
"<s_Consultora>": 57528,
|
85 |
+
"<s_Controlador>": 57648,
|
86 |
+
"<s_Costo_insta>": 57658,
|
87 |
+
"<s_Costo_neto_repo>": 57596,
|
88 |
+
"<s_Costo_neto_repo_dem>": 57598,
|
89 |
+
"<s_Costo_uni_neto_repo>": 57600,
|
90 |
+
"<s_Deterioro>": 57602,
|
91 |
+
"<s_Dis_val_com_homo>": 57612,
|
92 |
+
"<s_Dis_val_com_pre_homo>": 57614,
|
93 |
+
"<s_Edad_const>": 57576,
|
94 |
+
"<s_Enfoque>": 57610,
|
95 |
+
"<s_Equipo_Urbano>": 57638,
|
96 |
+
"<s_Escritura>": 57536,
|
97 |
+
"<s_Estado>": 57562,
|
98 |
+
"<s_Factor>": 57616,
|
99 |
+
"<s_Fecha_del_avaluo>": 57538,
|
100 |
+
"<s_Generales>": 57532,
|
101 |
+
"<s_Georeferencia>": 57564,
|
102 |
+
"<s_ID>": 57530,
|
103 |
+
"<s_Identiicador>": 57526,
|
104 |
+
"<s_Indice_fisico>": 57604,
|
105 |
+
"<s_Infraestructura>": 57634,
|
106 |
+
"<s_Interior>": 57656,
|
107 |
+
"<s_Lote>": 57566,
|
108 |
+
"<s_Manzana>": 57568,
|
109 |
+
"<s_Notas>": 57662,
|
110 |
+
"<s_Numero_de_avaluo>": 57540,
|
111 |
+
"<s_Numero_exterior>": 57570,
|
112 |
+
"<s_Ocupacion>": 57542,
|
113 |
+
"<s_Precio>": 57628,
|
114 |
+
"<s_Predial>": 57544,
|
115 |
+
"<s_Propietario>": 57546,
|
116 |
+
"<s_Proposito>": 57548,
|
117 |
+
"<s_Prototipo>": 57578,
|
118 |
+
"<s_Relacion_valor>": 57618,
|
119 |
+
"<s_SHF>": 57664,
|
120 |
+
"<s_Servicios_muni>": 57636,
|
121 |
+
"<s_Solicitante>": 57660,
|
122 |
+
"<s_Tipo_de_inmueble>": 57550,
|
123 |
+
"<s_Ubicacion>": 57552,
|
124 |
+
"<s_Val_comp_merc>": 57620,
|
125 |
+
"<s_Val_hip>": 57622,
|
126 |
+
"<s_Val_uni_con_dete>": 57624,
|
127 |
+
"<s_Val_uni_sin_dete>": 57626,
|
128 |
+
"<s_Valor_concluido>": 57630,
|
129 |
+
"<s_Valor_fisico>": 57606,
|
130 |
+
"<s_Valor_homo_M2>": 57608,
|
131 |
+
"<s_Valores_Calculados>": 57592,
|
132 |
+
"<s_Valuador>": 57640,
|
133 |
+
"<s_avaluo>": 57665,
|
134 |
+
"<s_contro>": 57654,
|
135 |
+
"<s_iitcdip>": 57523,
|
136 |
+
"<s_letra>": 57632,
|
137 |
+
"<s_no_banos>": 57580,
|
138 |
+
"<s_no_estacionamiento>": 57582,
|
139 |
+
"<s_no_niv_UV>": 57584,
|
140 |
+
"<s_no_recamaras>": 57586,
|
141 |
+
"<s_synthdog>": 57524,
|
142 |
+
"<s_terreno_M2>": 57588,
|
143 |
+
"<s_valu>": 57646,
|
144 |
+
"<s_vendible_M2>": 57590,
|
145 |
+
"<sep/>": 57522
|
146 |
+
}
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "naver-clova-ix/donut-base",
|
3 |
+
"align_long_axis": false,
|
4 |
+
"architectures": [
|
5 |
+
"DonutModel"
|
6 |
+
],
|
7 |
+
"decoder_layer": 4,
|
8 |
+
"encoder_layer": [
|
9 |
+
2,
|
10 |
+
2,
|
11 |
+
14,
|
12 |
+
2
|
13 |
+
],
|
14 |
+
"input_size": [
|
15 |
+
2560,
|
16 |
+
1920
|
17 |
+
],
|
18 |
+
"max_length": 768,
|
19 |
+
"max_position_embeddings": 768,
|
20 |
+
"model_type": "donut",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.25.1",
|
23 |
+
"window_size": 10
|
24 |
+
}
|
hparams.yaml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b564894f9431e5266a10b5e218d75041b07668c571c10af05aabbebb2e59955c
|
3 |
+
size 1015863294
|
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 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s_avaluo>"
|
4 |
+
],
|
5 |
+
"bos_token": "<s>",
|
6 |
+
"cls_token": "<s>",
|
7 |
+
"eos_token": "</s>",
|
8 |
+
"mask_token": {
|
9 |
+
"content": "<mask>",
|
10 |
+
"lstrip": true,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"unk_token": "<unk>"
|
18 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"from_slow": true,
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 1000000000000000019884624838656,
|
15 |
+
"name_or_path": "naver-clova-ix/donut-base",
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"processor_class": "DonutProcessor",
|
18 |
+
"sep_token": "</s>",
|
19 |
+
"sp_model_kwargs": {},
|
20 |
+
"special_tokens_map_file": null,
|
21 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
22 |
+
"unk_token": "<unk>"
|
23 |
+
}
|