Hugging Face's logo

CEIA-Ultimatum
/
ultimatum-ner-models

Transformers
Safetensors
SpanMarker
Model card Files
xet
 Community
gustavobarrosss commited on
Commit
06ece1a
·
verified ·
1 Parent(s): 8e1d93b

Upload model

Browse files
Files changed (7) hide show
  1. added_tokens.json +4 -0
  2. config.json +304 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +76 -0
  7. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<end>": 29795,
3
+ "<start>": 29794
4
+ }
config.json ADDED
@@ -0,0 +1,304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpanMarkerModel"
4
+ ],
5
+ "dtype": "float32",
6
+ "encoder": {
7
+ "_name_or_path": "neuralmind/bert-large-portuguese-cased",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "BertForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": null,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": null,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "directionality": "bidi",
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "dtype": null,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": null,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "gelu",
32
+ "hidden_dropout_prob": 0.1,
33
+ "hidden_size": 1024,
34
+ "id2label": {
35
+ "0": "O",
36
+ "1": "B-Advogado",
37
+ "2": "I-Advogado",
38
+ "3": "B-Artigo",
39
+ "4": "I-Artigo",
40
+ "5": "B-Assessor",
41
+ "6": "I-Assessor",
42
+ "7": "B-ClasseProcessual",
43
+ "8": "I-ClasseProcessual",
44
+ "9": "B-Encaminhamento",
45
+ "10": "I-Encaminhamento",
46
+ "11": "B-IdentificadorDeDocumento",
47
+ "12": "I-IdentificadorDeDocumento",
48
+ "13": "B-Jurisprudencia",
49
+ "14": "I-Jurisprudencia",
50
+ "15": "B-Magistrado",
51
+ "16": "I-Magistrado",
52
+ "17": "B-NumeroOAB",
53
+ "18": "I-NumeroOAB",
54
+ "19": "B-NumeroPeticao",
55
+ "20": "I-NumeroPeticao",
56
+ "21": "B-NumeroProcesso",
57
+ "22": "I-NumeroProcesso",
58
+ "23": "B-PessoaFisica_PoloAtivo",
59
+ "24": "I-PessoaFisica_PoloAtivo",
60
+ "25": "B-PessoaFisica_PoloIndeterminado",
61
+ "26": "I-PessoaFisica_PoloIndeterminado",
62
+ "27": "B-PessoaFisica_PoloPassivo",
63
+ "28": "I-PessoaFisica_PoloPassivo",
64
+ "29": "B-PessoaJuridica_PoloAtivo",
65
+ "30": "I-PessoaJuridica_PoloAtivo",
66
+ "31": "B-PessoaJuridica_PoloIndeterminado",
67
+ "32": "I-PessoaJuridica_PoloIndeterminado",
68
+ "33": "B-PessoaJuridica_PoloPassivo",
69
+ "34": "I-PessoaJuridica_PoloPassivo",
70
+ "35": "B-Prazo",
71
+ "36": "I-Prazo",
72
+ "37": "B-Pronunciamento_DecisaoDeInstanciaSuperior",
73
+ "38": "I-Pronunciamento_DecisaoDeInstanciaSuperior",
74
+ "39": "B-Pronunciamento_DecisaoInterlocutoria",
75
+ "40": "I-Pronunciamento_DecisaoInterlocutoria",
76
+ "41": "B-Pronunciamento_Despacho",
77
+ "42": "I-Pronunciamento_Despacho",
78
+ "43": "B-Pronunciamento_Sentenca",
79
+ "44": "I-Pronunciamento_Sentenca",
80
+ "45": "B-ReferenciaLegal",
81
+ "46": "I-ReferenciaLegal",
82
+ "47": "B-Servidor",
83
+ "48": "I-Servidor"
84
+ },
85
+ "initializer_range": 0.02,
86
+ "intermediate_size": 4096,
87
+ "is_decoder": false,
88
+ "is_encoder_decoder": false,
89
+ "label2id": {
90
+ "B-Advogado": 1,
91
+ "B-Artigo": 3,
92
+ "B-Assessor": 5,
93
+ "B-ClasseProcessual": 7,
94
+ "B-Encaminhamento": 9,
95
+ "B-IdentificadorDeDocumento": 11,
96
+ "B-Jurisprudencia": 13,
97
+ "B-Magistrado": 15,
98
+ "B-NumeroOAB": 17,
99
+ "B-NumeroPeticao": 19,
100
+ "B-NumeroProcesso": 21,
101
+ "B-PessoaFisica_PoloAtivo": 23,
102
+ "B-PessoaFisica_PoloIndeterminado": 25,
103
+ "B-PessoaFisica_PoloPassivo": 27,
104
+ "B-PessoaJuridica_PoloAtivo": 29,
105
+ "B-PessoaJuridica_PoloIndeterminado": 31,
106
+ "B-PessoaJuridica_PoloPassivo": 33,
107
+ "B-Prazo": 35,
108
+ "B-Pronunciamento_DecisaoDeInstanciaSuperior": 37,
109
+ "B-Pronunciamento_DecisaoInterlocutoria": 39,
110
+ "B-Pronunciamento_Despacho": 41,
111
+ "B-Pronunciamento_Sentenca": 43,
112
+ "B-ReferenciaLegal": 45,
113
+ "B-Servidor": 47,
114
+ "I-Advogado": 2,
115
+ "I-Artigo": 4,
116
+ "I-Assessor": 6,
117
+ "I-ClasseProcessual": 8,
118
+ "I-Encaminhamento": 10,
119
+ "I-IdentificadorDeDocumento": 12,
120
+ "I-Jurisprudencia": 14,
121
+ "I-Magistrado": 16,
122
+ "I-NumeroOAB": 18,
123
+ "I-NumeroPeticao": 20,
124
+ "I-NumeroProcesso": 22,
125
+ "I-PessoaFisica_PoloAtivo": 24,
126
+ "I-PessoaFisica_PoloIndeterminado": 26,
127
+ "I-PessoaFisica_PoloPassivo": 28,
128
+ "I-PessoaJuridica_PoloAtivo": 30,
129
+ "I-PessoaJuridica_PoloIndeterminado": 32,
130
+ "I-PessoaJuridica_PoloPassivo": 34,
131
+ "I-Prazo": 36,
132
+ "I-Pronunciamento_DecisaoDeInstanciaSuperior": 38,
133
+ "I-Pronunciamento_DecisaoInterlocutoria": 40,
134
+ "I-Pronunciamento_Despacho": 42,
135
+ "I-Pronunciamento_Sentenca": 44,
136
+ "I-ReferenciaLegal": 46,
137
+ "I-Servidor": 48,
138
+ "O": 0
139
+ },
140
+ "layer_norm_eps": 1e-12,
141
+ "length_penalty": 1.0,
142
+ "max_length": 20,
143
+ "max_position_embeddings": 512,
144
+ "min_length": 0,
145
+ "model_type": "bert",
146
+ "no_repeat_ngram_size": 0,
147
+ "num_attention_heads": 16,
148
+ "num_beam_groups": 1,
149
+ "num_beams": 1,
150
+ "num_hidden_layers": 24,
151
+ "num_return_sequences": 1,
152
+ "output_attentions": false,
153
+ "output_hidden_states": false,
154
+ "output_past": true,
155
+ "output_scores": false,
156
+ "pad_token_id": 0,
157
+ "pooler_fc_size": 768,
158
+ "pooler_num_attention_heads": 12,
159
+ "pooler_num_fc_layers": 3,
160
+ "pooler_size_per_head": 128,
161
+ "pooler_type": "first_token_transform",
162
+ "position_embedding_type": "absolute",
163
+ "prefix": null,
164
+ "problem_type": null,
165
+ "pruned_heads": {},
166
+ "remove_invalid_values": false,
167
+ "repetition_penalty": 1.0,
168
+ "return_dict": true,
169
+ "return_dict_in_generate": false,
170
+ "sep_token_id": null,
171
+ "suppress_tokens": null,
172
+ "task_specific_params": null,
173
+ "temperature": 1.0,
174
+ "tf_legacy_loss": false,
175
+ "tie_encoder_decoder": false,
176
+ "tie_word_embeddings": true,
177
+ "tokenizer_class": null,
178
+ "top_k": 50,
179
+ "top_p": 1.0,
180
+ "torchscript": false,
181
+ "transformers_version": "4.57.6",
182
+ "type_vocab_size": 2,
183
+ "typical_p": 1.0,
184
+ "use_bfloat16": false,
185
+ "use_cache": true,
186
+ "vocab_size": 29800
187
+ },
188
+ "entity_max_length": 20,
189
+ "id2label": {
190
+ "0": "O",
191
+ "1": "Advogado",
192
+ "2": "Artigo",
193
+ "3": "Assessor",
194
+ "4": "ClasseProcessual",
195
+ "5": "Encaminhamento",
196
+ "6": "IdentificadorDeDocumento",
197
+ "7": "Jurisprudencia",
198
+ "8": "Magistrado",
199
+ "9": "NumeroOAB",
200
+ "10": "NumeroPeticao",
201
+ "11": "NumeroProcesso",
202
+ "12": "PessoaFisica_PoloAtivo",
203
+ "13": "PessoaFisica_PoloIndeterminado",
204
+ "14": "PessoaFisica_PoloPassivo",
205
+ "15": "PessoaJuridica_PoloAtivo",
206
+ "16": "PessoaJuridica_PoloIndeterminado",
207
+ "17": "PessoaJuridica_PoloPassivo",
208
+ "18": "Prazo",
209
+ "19": "Pronunciamento_DecisaoDeInstanciaSuperior",
210
+ "20": "Pronunciamento_DecisaoInterlocutoria",
211
+ "21": "Pronunciamento_Despacho",
212
+ "22": "Pronunciamento_Sentenca",
213
+ "23": "ReferenciaLegal",
214
+ "24": "Servidor"
215
+ },
216
+ "id2reduced_id": {
217
+ "0": 0,
218
+ "1": 1,
219
+ "2": 1,
220
+ "3": 2,
221
+ "4": 2,
222
+ "5": 3,
223
+ "6": 3,
224
+ "7": 4,
225
+ "8": 4,
226
+ "9": 5,
227
+ "10": 5,
228
+ "11": 6,
229
+ "12": 6,
230
+ "13": 7,
231
+ "14": 7,
232
+ "15": 8,
233
+ "16": 8,
234
+ "17": 9,
235
+ "18": 9,
236
+ "19": 10,
237
+ "20": 10,
238
+ "21": 11,
239
+ "22": 11,
240
+ "23": 12,
241
+ "24": 12,
242
+ "25": 13,
243
+ "26": 13,
244
+ "27": 14,
245
+ "28": 14,
246
+ "29": 15,
247
+ "30": 15,
248
+ "31": 16,
249
+ "32": 16,
250
+ "33": 17,
251
+ "34": 17,
252
+ "35": 18,
253
+ "36": 18,
254
+ "37": 19,
255
+ "38": 19,
256
+ "39": 20,
257
+ "40": 20,
258
+ "41": 21,
259
+ "42": 21,
260
+ "43": 22,
261
+ "44": 22,
262
+ "45": 23,
263
+ "46": 23,
264
+ "47": 24,
265
+ "48": 24
266
+ },
267
+ "label2id": {
268
+ "Advogado": 1,
269
+ "Artigo": 2,
270
+ "Assessor": 3,
271
+ "ClasseProcessual": 4,
272
+ "Encaminhamento": 5,
273
+ "IdentificadorDeDocumento": 6,
274
+ "Jurisprudencia": 7,
275
+ "Magistrado": 8,
276
+ "NumeroOAB": 9,
277
+ "NumeroPeticao": 10,
278
+ "NumeroProcesso": 11,
279
+ "O": 0,
280
+ "PessoaFisica_PoloAtivo": 12,
281
+ "PessoaFisica_PoloIndeterminado": 13,
282
+ "PessoaFisica_PoloPassivo": 14,
283
+ "PessoaJuridica_PoloAtivo": 15,
284
+ "PessoaJuridica_PoloIndeterminado": 16,
285
+ "PessoaJuridica_PoloPassivo": 17,
286
+ "Prazo": 18,
287
+ "Pronunciamento_DecisaoDeInstanciaSuperior": 19,
288
+ "Pronunciamento_DecisaoInterlocutoria": 20,
289
+ "Pronunciamento_Despacho": 21,
290
+ "Pronunciamento_Sentenca": 22,
291
+ "ReferenciaLegal": 23,
292
+ "Servidor": 24
293
+ },
294
+ "marker_max_length": 128,
295
+ "max_next_context": null,
296
+ "max_prev_context": null,
297
+ "model_max_length": 256,
298
+ "model_max_length_default": 512,
299
+ "model_type": "span-marker",
300
+ "span_marker_version": "1.8.1",
301
+ "trained_with_document_context": false,
302
+ "transformers_version": "4.57.6",
303
+ "vocab_size": 29800
304
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25afa767647d62168dec4638c63e234ee98a023ad44e59901100c1357d46d19
3
+ size 1337863308
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "101": {
21
+ "content": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "102": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "103": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "29794": {
45
+ "content": "<start>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "29795": {
53
+ "content": "<end>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "clean_up_tokenization_spaces": true,
62
+ "cls_token": "[CLS]",
63
+ "do_basic_tokenize": true,
64
+ "do_lower_case": false,
65
+ "entity_max_length": 20,
66
+ "extra_special_tokens": {},
67
+ "mask_token": "[MASK]",
68
+ "model_max_length": 256,
69
+ "never_split": null,
70
+ "pad_token": "[PAD]",
71
+ "sep_token": "[SEP]",
72
+ "strip_accents": null,
73
+ "tokenize_chinese_chars": true,
74
+ "tokenizer_class": "BertTokenizer",
75
+ "unk_token": "[UNK]"
76
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff