novakat commited on
Commit
1b7adda
1 Parent(s): 90f27ac
config.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
3
+ "architectures": [
4
+ "TokenClassifier"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "finetuning_task": "nerkor_cars_ner",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27",
42
+ "28": "LABEL_28",
43
+ "29": "LABEL_29",
44
+ "30": "LABEL_30",
45
+ "31": "LABEL_31",
46
+ "32": "LABEL_32",
47
+ "33": "LABEL_33",
48
+ "34": "LABEL_34",
49
+ "35": "LABEL_35",
50
+ "36": "LABEL_36",
51
+ "37": "LABEL_37",
52
+ "38": "LABEL_38",
53
+ "39": "LABEL_39",
54
+ "40": "LABEL_40",
55
+ "41": "LABEL_41",
56
+ "42": "LABEL_42",
57
+ "43": "LABEL_43",
58
+ "44": "LABEL_44",
59
+ "45": "LABEL_45",
60
+ "46": "LABEL_46",
61
+ "47": "LABEL_47",
62
+ "48": "LABEL_48",
63
+ "49": "LABEL_49",
64
+ "50": "LABEL_50",
65
+ "51": "LABEL_51",
66
+ "52": "LABEL_52",
67
+ "53": "LABEL_53",
68
+ "54": "LABEL_54",
69
+ "55": "LABEL_55",
70
+ "56": "LABEL_56",
71
+ "57": "LABEL_57",
72
+ "58": "LABEL_58",
73
+ "59": "LABEL_59",
74
+ "60": "LABEL_60",
75
+ "61": "LABEL_61",
76
+ "62": "LABEL_62",
77
+ "63": "LABEL_63",
78
+ "64": "LABEL_64",
79
+ "65": "LABEL_65",
80
+ "66": "LABEL_66",
81
+ "67": "LABEL_67",
82
+ "68": "LABEL_68",
83
+ "69": "LABEL_69",
84
+ "70": "LABEL_70",
85
+ "71": "LABEL_71",
86
+ "72": "LABEL_72",
87
+ "73": "LABEL_73",
88
+ "74": "LABEL_74"
89
+ },
90
+ "initializer_range": 0.02,
91
+ "intermediate_size": 3072,
92
+ "label2id": {
93
+ "LABEL_0": 0,
94
+ "LABEL_1": 1,
95
+ "LABEL_10": 10,
96
+ "LABEL_11": 11,
97
+ "LABEL_12": 12,
98
+ "LABEL_13": 13,
99
+ "LABEL_14": 14,
100
+ "LABEL_15": 15,
101
+ "LABEL_16": 16,
102
+ "LABEL_17": 17,
103
+ "LABEL_18": 18,
104
+ "LABEL_19": 19,
105
+ "LABEL_2": 2,
106
+ "LABEL_20": 20,
107
+ "LABEL_21": 21,
108
+ "LABEL_22": 22,
109
+ "LABEL_23": 23,
110
+ "LABEL_24": 24,
111
+ "LABEL_25": 25,
112
+ "LABEL_26": 26,
113
+ "LABEL_27": 27,
114
+ "LABEL_28": 28,
115
+ "LABEL_29": 29,
116
+ "LABEL_3": 3,
117
+ "LABEL_30": 30,
118
+ "LABEL_31": 31,
119
+ "LABEL_32": 32,
120
+ "LABEL_33": 33,
121
+ "LABEL_34": 34,
122
+ "LABEL_35": 35,
123
+ "LABEL_36": 36,
124
+ "LABEL_37": 37,
125
+ "LABEL_38": 38,
126
+ "LABEL_39": 39,
127
+ "LABEL_4": 4,
128
+ "LABEL_40": 40,
129
+ "LABEL_41": 41,
130
+ "LABEL_42": 42,
131
+ "LABEL_43": 43,
132
+ "LABEL_44": 44,
133
+ "LABEL_45": 45,
134
+ "LABEL_46": 46,
135
+ "LABEL_47": 47,
136
+ "LABEL_48": 48,
137
+ "LABEL_49": 49,
138
+ "LABEL_5": 5,
139
+ "LABEL_50": 50,
140
+ "LABEL_51": 51,
141
+ "LABEL_52": 52,
142
+ "LABEL_53": 53,
143
+ "LABEL_54": 54,
144
+ "LABEL_55": 55,
145
+ "LABEL_56": 56,
146
+ "LABEL_57": 57,
147
+ "LABEL_58": 58,
148
+ "LABEL_59": 59,
149
+ "LABEL_6": 6,
150
+ "LABEL_60": 60,
151
+ "LABEL_61": 61,
152
+ "LABEL_62": 62,
153
+ "LABEL_63": 63,
154
+ "LABEL_64": 64,
155
+ "LABEL_65": 65,
156
+ "LABEL_66": 66,
157
+ "LABEL_67": 67,
158
+ "LABEL_68": 68,
159
+ "LABEL_69": 69,
160
+ "LABEL_7": 7,
161
+ "LABEL_70": 70,
162
+ "LABEL_71": 71,
163
+ "LABEL_72": 72,
164
+ "LABEL_73": 73,
165
+ "LABEL_74": 74,
166
+ "LABEL_8": 8,
167
+ "LABEL_9": 9
168
+ },
169
+ "layer_norm_eps": 1e-12,
170
+ "max_position_embeddings": 512,
171
+ "model_type": "bert",
172
+ "num_attention_heads": 12,
173
+ "num_hidden_layers": 12,
174
+ "pad_token_id": 0,
175
+ "position_embedding_type": "absolute",
176
+ "torch_dtype": "float32",
177
+ "transformers_version": "4.12.2",
178
+ "type_vocab_size": 2,
179
+ "use_cache": true,
180
+ "vocab_size": 32001
181
+ }
model_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bert_model": "SZTAKI-HLT/hubert-base-cc", "do_lower": false, "max_seq_length": 448, "num_labels": 75, "labels": ["O", "B-AGE", "B-AWARD", "B-CAR", "B-CARDINAL", "B-DATE", "B-DUR", "B-EVENT", "B-FAC", "B-FRQ", "B-GPE", "B-ID", "B-LANGUAGE", "B-LAW", "B-LOC", "B-MEDIA", "B-MISC", "B-MISC-LOC", "B-MISC-ORG", "B-MONEY", "B-NORP", "B-ORDINAL", "B-ORG", "B-PER", "B-PERCENT", "B-PERS", "B-PROD", "B-PROJ", "B-QUANTITY", "B-SCORE", "B-SEC", "B-SMEDIA", "B-STX", "B-TEL", "B-TIME", "B-URL", "B-VRN", "B-WORK_OF_ART", "B-ZIP", "B-[DATE", "I-AGE", "I-AWARD", "I-CAR", "I-CARDINAL", "I-DATE", "I-DUR", "I-EVENT", "I-FAC", "I-FRQ", "I-GPE", "I-ID", "I-LAW", "I-LOC", "I-MEDIA", "I-MISC", "I-MISC-ORG", "I-MONEY", "I-NORP", "I-ORG", "I-PER", "I-PERCENT", "I-PROD", "I-PROJ", "I-QUANTITY", "I-SCORE", "I-SEC", "I-SMEDIA", "I-STX", "I-TIME", "I-VRN", "I-WORK_OF_ART", "I-[DATE", "[CLS]", "[SEP]"]}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e33cd4f1f0990fd04f67d21428f25e80efec7080468249ac59f3469cbfe4ef8
3
+ size 440424177
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "do_basic_tokenize": false, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "tokenizer_file": null, "name_or_path": "SZTAKI-HLT/hubert-base-cc", "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff