permutans commited on
Commit
2641f46
·
verified ·
1 Parent(s): 578b83f

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. config.json +324 -0
  2. model.safetensors +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +14 -0
config.json ADDED
@@ -0,0 +1,324 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-literate_abstract_noun",
18
+ "2": "B-literate_additive_formal",
19
+ "3": "B-literate_agent_demoted",
20
+ "4": "B-literate_agentless_passive",
21
+ "5": "B-literate_aside",
22
+ "6": "B-literate_categorical_statement",
23
+ "7": "B-literate_causal_chain",
24
+ "8": "B-literate_causal_explicit",
25
+ "9": "B-literate_citation",
26
+ "10": "B-literate_conceptual_metaphor",
27
+ "11": "B-literate_concessive",
28
+ "12": "B-literate_concessive_connector",
29
+ "13": "B-literate_conditional",
30
+ "14": "B-literate_contrastive",
31
+ "15": "B-literate_cross_reference",
32
+ "16": "B-literate_definitional_move",
33
+ "17": "B-literate_enumeration",
34
+ "18": "B-literate_epistemic_hedge",
35
+ "19": "B-literate_evidential",
36
+ "20": "B-literate_footnote_reference",
37
+ "21": "B-literate_institutional_subject",
38
+ "22": "B-literate_list_structure",
39
+ "23": "B-literate_metadiscourse",
40
+ "24": "B-literate_methodological_framing",
41
+ "25": "B-literate_nested_clauses",
42
+ "26": "B-literate_nominalization",
43
+ "27": "B-literate_objectifying_stance",
44
+ "28": "B-literate_paradox",
45
+ "29": "B-literate_probability",
46
+ "30": "B-literate_qualified_assertion",
47
+ "31": "B-literate_relative_chain",
48
+ "32": "B-literate_technical_abbreviation",
49
+ "33": "B-literate_technical_term",
50
+ "34": "B-literate_temporal_embedding",
51
+ "35": "B-literate_third_person_reference",
52
+ "36": "B-oral_alliteration",
53
+ "37": "B-oral_anaphora",
54
+ "38": "B-oral_asyndeton",
55
+ "39": "B-oral_audience_response",
56
+ "40": "B-oral_binomial_expression",
57
+ "41": "B-oral_conflict_frame",
58
+ "42": "B-oral_discourse_formula",
59
+ "43": "B-oral_dramatic_pause",
60
+ "44": "B-oral_embodied_action",
61
+ "45": "B-oral_epistrophe",
62
+ "46": "B-oral_epithet",
63
+ "47": "B-oral_everyday_example",
64
+ "48": "B-oral_first_person",
65
+ "49": "B-oral_imperative",
66
+ "50": "B-oral_inclusive_we",
67
+ "51": "B-oral_intensifier_doubling",
68
+ "52": "B-oral_lexical_repetition",
69
+ "53": "B-oral_named_individual",
70
+ "54": "B-oral_paradox",
71
+ "55": "B-oral_parallelism",
72
+ "56": "B-oral_phatic_check",
73
+ "57": "B-oral_phatic_filler",
74
+ "58": "B-oral_polysyndeton",
75
+ "59": "B-oral_proverb",
76
+ "60": "B-oral_refrain",
77
+ "61": "B-oral_religious_formula",
78
+ "62": "B-oral_rhetorical_question",
79
+ "63": "B-oral_rhythm",
80
+ "64": "B-oral_second_person",
81
+ "65": "B-oral_self_correction",
82
+ "66": "B-oral_sensory_detail",
83
+ "67": "B-oral_simple_conjunction",
84
+ "68": "B-oral_specific_place",
85
+ "69": "B-oral_temporal_anchor",
86
+ "70": "B-oral_tricolon",
87
+ "71": "B-oral_us_them",
88
+ "72": "B-oral_vocative",
89
+ "73": "I-literate_abstract_noun",
90
+ "74": "I-literate_additive_formal",
91
+ "75": "I-literate_agent_demoted",
92
+ "76": "I-literate_agentless_passive",
93
+ "77": "I-literate_aside",
94
+ "78": "I-literate_categorical_statement",
95
+ "79": "I-literate_causal_chain",
96
+ "80": "I-literate_causal_explicit",
97
+ "81": "I-literate_citation",
98
+ "82": "I-literate_conceptual_metaphor",
99
+ "83": "I-literate_concessive",
100
+ "84": "I-literate_concessive_connector",
101
+ "85": "I-literate_conditional",
102
+ "86": "I-literate_contrastive",
103
+ "87": "I-literate_cross_reference",
104
+ "88": "I-literate_definitional_move",
105
+ "89": "I-literate_enumeration",
106
+ "90": "I-literate_epistemic_hedge",
107
+ "91": "I-literate_evidential",
108
+ "92": "I-literate_footnote_reference",
109
+ "93": "I-literate_institutional_subject",
110
+ "94": "I-literate_list_structure",
111
+ "95": "I-literate_metadiscourse",
112
+ "96": "I-literate_methodological_framing",
113
+ "97": "I-literate_nested_clauses",
114
+ "98": "I-literate_nominalization",
115
+ "99": "I-literate_objectifying_stance",
116
+ "100": "I-literate_paradox",
117
+ "101": "I-literate_probability",
118
+ "102": "I-literate_qualified_assertion",
119
+ "103": "I-literate_relative_chain",
120
+ "104": "I-literate_technical_abbreviation",
121
+ "105": "I-literate_technical_term",
122
+ "106": "I-literate_temporal_embedding",
123
+ "107": "I-literate_third_person_reference",
124
+ "108": "I-oral_alliteration",
125
+ "109": "I-oral_anaphora",
126
+ "110": "I-oral_asyndeton",
127
+ "111": "I-oral_audience_response",
128
+ "112": "I-oral_binomial_expression",
129
+ "113": "I-oral_conflict_frame",
130
+ "114": "I-oral_discourse_formula",
131
+ "115": "I-oral_dramatic_pause",
132
+ "116": "I-oral_embodied_action",
133
+ "117": "I-oral_epistrophe",
134
+ "118": "I-oral_epithet",
135
+ "119": "I-oral_everyday_example",
136
+ "120": "I-oral_first_person",
137
+ "121": "I-oral_imperative",
138
+ "122": "I-oral_inclusive_we",
139
+ "123": "I-oral_intensifier_doubling",
140
+ "124": "I-oral_lexical_repetition",
141
+ "125": "I-oral_named_individual",
142
+ "126": "I-oral_paradox",
143
+ "127": "I-oral_parallelism",
144
+ "128": "I-oral_phatic_check",
145
+ "129": "I-oral_phatic_filler",
146
+ "130": "I-oral_polysyndeton",
147
+ "131": "I-oral_proverb",
148
+ "132": "I-oral_refrain",
149
+ "133": "I-oral_religious_formula",
150
+ "134": "I-oral_rhetorical_question",
151
+ "135": "I-oral_rhythm",
152
+ "136": "I-oral_second_person",
153
+ "137": "I-oral_self_correction",
154
+ "138": "I-oral_sensory_detail",
155
+ "139": "I-oral_simple_conjunction",
156
+ "140": "I-oral_specific_place",
157
+ "141": "I-oral_temporal_anchor",
158
+ "142": "I-oral_tricolon",
159
+ "143": "I-oral_us_them",
160
+ "144": "I-oral_vocative"
161
+ },
162
+ "initializer_range": 0.02,
163
+ "intermediate_size": 3072,
164
+ "is_decoder": false,
165
+ "label2id": {
166
+ "B-literate_abstract_noun": 1,
167
+ "B-literate_additive_formal": 2,
168
+ "B-literate_agent_demoted": 3,
169
+ "B-literate_agentless_passive": 4,
170
+ "B-literate_aside": 5,
171
+ "B-literate_categorical_statement": 6,
172
+ "B-literate_causal_chain": 7,
173
+ "B-literate_causal_explicit": 8,
174
+ "B-literate_citation": 9,
175
+ "B-literate_conceptual_metaphor": 10,
176
+ "B-literate_concessive": 11,
177
+ "B-literate_concessive_connector": 12,
178
+ "B-literate_conditional": 13,
179
+ "B-literate_contrastive": 14,
180
+ "B-literate_cross_reference": 15,
181
+ "B-literate_definitional_move": 16,
182
+ "B-literate_enumeration": 17,
183
+ "B-literate_epistemic_hedge": 18,
184
+ "B-literate_evidential": 19,
185
+ "B-literate_footnote_reference": 20,
186
+ "B-literate_institutional_subject": 21,
187
+ "B-literate_list_structure": 22,
188
+ "B-literate_metadiscourse": 23,
189
+ "B-literate_methodological_framing": 24,
190
+ "B-literate_nested_clauses": 25,
191
+ "B-literate_nominalization": 26,
192
+ "B-literate_objectifying_stance": 27,
193
+ "B-literate_paradox": 28,
194
+ "B-literate_probability": 29,
195
+ "B-literate_qualified_assertion": 30,
196
+ "B-literate_relative_chain": 31,
197
+ "B-literate_technical_abbreviation": 32,
198
+ "B-literate_technical_term": 33,
199
+ "B-literate_temporal_embedding": 34,
200
+ "B-literate_third_person_reference": 35,
201
+ "B-oral_alliteration": 36,
202
+ "B-oral_anaphora": 37,
203
+ "B-oral_asyndeton": 38,
204
+ "B-oral_audience_response": 39,
205
+ "B-oral_binomial_expression": 40,
206
+ "B-oral_conflict_frame": 41,
207
+ "B-oral_discourse_formula": 42,
208
+ "B-oral_dramatic_pause": 43,
209
+ "B-oral_embodied_action": 44,
210
+ "B-oral_epistrophe": 45,
211
+ "B-oral_epithet": 46,
212
+ "B-oral_everyday_example": 47,
213
+ "B-oral_first_person": 48,
214
+ "B-oral_imperative": 49,
215
+ "B-oral_inclusive_we": 50,
216
+ "B-oral_intensifier_doubling": 51,
217
+ "B-oral_lexical_repetition": 52,
218
+ "B-oral_named_individual": 53,
219
+ "B-oral_paradox": 54,
220
+ "B-oral_parallelism": 55,
221
+ "B-oral_phatic_check": 56,
222
+ "B-oral_phatic_filler": 57,
223
+ "B-oral_polysyndeton": 58,
224
+ "B-oral_proverb": 59,
225
+ "B-oral_refrain": 60,
226
+ "B-oral_religious_formula": 61,
227
+ "B-oral_rhetorical_question": 62,
228
+ "B-oral_rhythm": 63,
229
+ "B-oral_second_person": 64,
230
+ "B-oral_self_correction": 65,
231
+ "B-oral_sensory_detail": 66,
232
+ "B-oral_simple_conjunction": 67,
233
+ "B-oral_specific_place": 68,
234
+ "B-oral_temporal_anchor": 69,
235
+ "B-oral_tricolon": 70,
236
+ "B-oral_us_them": 71,
237
+ "B-oral_vocative": 72,
238
+ "I-literate_abstract_noun": 73,
239
+ "I-literate_additive_formal": 74,
240
+ "I-literate_agent_demoted": 75,
241
+ "I-literate_agentless_passive": 76,
242
+ "I-literate_aside": 77,
243
+ "I-literate_categorical_statement": 78,
244
+ "I-literate_causal_chain": 79,
245
+ "I-literate_causal_explicit": 80,
246
+ "I-literate_citation": 81,
247
+ "I-literate_conceptual_metaphor": 82,
248
+ "I-literate_concessive": 83,
249
+ "I-literate_concessive_connector": 84,
250
+ "I-literate_conditional": 85,
251
+ "I-literate_contrastive": 86,
252
+ "I-literate_cross_reference": 87,
253
+ "I-literate_definitional_move": 88,
254
+ "I-literate_enumeration": 89,
255
+ "I-literate_epistemic_hedge": 90,
256
+ "I-literate_evidential": 91,
257
+ "I-literate_footnote_reference": 92,
258
+ "I-literate_institutional_subject": 93,
259
+ "I-literate_list_structure": 94,
260
+ "I-literate_metadiscourse": 95,
261
+ "I-literate_methodological_framing": 96,
262
+ "I-literate_nested_clauses": 97,
263
+ "I-literate_nominalization": 98,
264
+ "I-literate_objectifying_stance": 99,
265
+ "I-literate_paradox": 100,
266
+ "I-literate_probability": 101,
267
+ "I-literate_qualified_assertion": 102,
268
+ "I-literate_relative_chain": 103,
269
+ "I-literate_technical_abbreviation": 104,
270
+ "I-literate_technical_term": 105,
271
+ "I-literate_temporal_embedding": 106,
272
+ "I-literate_third_person_reference": 107,
273
+ "I-oral_alliteration": 108,
274
+ "I-oral_anaphora": 109,
275
+ "I-oral_asyndeton": 110,
276
+ "I-oral_audience_response": 111,
277
+ "I-oral_binomial_expression": 112,
278
+ "I-oral_conflict_frame": 113,
279
+ "I-oral_discourse_formula": 114,
280
+ "I-oral_dramatic_pause": 115,
281
+ "I-oral_embodied_action": 116,
282
+ "I-oral_epistrophe": 117,
283
+ "I-oral_epithet": 118,
284
+ "I-oral_everyday_example": 119,
285
+ "I-oral_first_person": 120,
286
+ "I-oral_imperative": 121,
287
+ "I-oral_inclusive_we": 122,
288
+ "I-oral_intensifier_doubling": 123,
289
+ "I-oral_lexical_repetition": 124,
290
+ "I-oral_named_individual": 125,
291
+ "I-oral_paradox": 126,
292
+ "I-oral_parallelism": 127,
293
+ "I-oral_phatic_check": 128,
294
+ "I-oral_phatic_filler": 129,
295
+ "I-oral_polysyndeton": 130,
296
+ "I-oral_proverb": 131,
297
+ "I-oral_refrain": 132,
298
+ "I-oral_religious_formula": 133,
299
+ "I-oral_rhetorical_question": 134,
300
+ "I-oral_rhythm": 135,
301
+ "I-oral_second_person": 136,
302
+ "I-oral_self_correction": 137,
303
+ "I-oral_sensory_detail": 138,
304
+ "I-oral_simple_conjunction": 139,
305
+ "I-oral_specific_place": 140,
306
+ "I-oral_temporal_anchor": 141,
307
+ "I-oral_tricolon": 142,
308
+ "I-oral_us_them": 143,
309
+ "I-oral_vocative": 144,
310
+ "O": 0
311
+ },
312
+ "layer_norm_eps": 1e-12,
313
+ "max_position_embeddings": 512,
314
+ "model_type": "bert",
315
+ "num_attention_heads": 12,
316
+ "num_hidden_layers": 12,
317
+ "pad_token_id": 0,
318
+ "position_embedding_type": "absolute",
319
+ "tie_word_embeddings": true,
320
+ "transformers_version": "5.0.0",
321
+ "type_vocab_size": 2,
322
+ "use_cache": true,
323
+ "vocab_size": 30522
324
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e641fcf77a44c588e4adbf53f11be6c4d285e3f0ecabe20e112660a0febaba1
3
+ size 436035932
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }