stefan-it commited on
Commit
a239043
1 Parent(s): dc9624d

model/tokenizer: add initial version

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<end>": 32001,
3
+ "<start>": 32000
4
+ }
config.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpanMarkerModel"
4
+ ],
5
+ "encoder": {
6
+ "_name_or_path": "gwlms/bert-base-token-dropping-dewiki-v1",
7
+ "add_cross_attention": false,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "gelu",
29
+ "hidden_dropout_prob": 0.1,
30
+ "hidden_size": 768,
31
+ "id2label": {
32
+ "0": "O",
33
+ "1": "B-LOC",
34
+ "2": "I-LOC",
35
+ "3": "B-LOCderiv",
36
+ "4": "I-LOCderiv",
37
+ "5": "B-LOCpart",
38
+ "6": "I-LOCpart",
39
+ "7": "B-ORG",
40
+ "8": "I-ORG",
41
+ "9": "B-ORGderiv",
42
+ "10": "I-ORGderiv",
43
+ "11": "B-ORGpart",
44
+ "12": "I-ORGpart",
45
+ "13": "B-OTH",
46
+ "14": "I-OTH",
47
+ "15": "B-OTHderiv",
48
+ "16": "I-OTHderiv",
49
+ "17": "B-OTHpart",
50
+ "18": "I-OTHpart",
51
+ "19": "B-PER",
52
+ "20": "I-PER",
53
+ "21": "B-PERderiv",
54
+ "22": "I-PERderiv",
55
+ "23": "B-PERpart",
56
+ "24": "I-PERpart"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "is_decoder": false,
61
+ "is_encoder_decoder": false,
62
+ "label2id": {
63
+ "B-LOC": 1,
64
+ "B-LOCderiv": 3,
65
+ "B-LOCpart": 5,
66
+ "B-ORG": 7,
67
+ "B-ORGderiv": 9,
68
+ "B-ORGpart": 11,
69
+ "B-OTH": 13,
70
+ "B-OTHderiv": 15,
71
+ "B-OTHpart": 17,
72
+ "B-PER": 19,
73
+ "B-PERderiv": 21,
74
+ "B-PERpart": 23,
75
+ "I-LOC": 2,
76
+ "I-LOCderiv": 4,
77
+ "I-LOCpart": 6,
78
+ "I-ORG": 8,
79
+ "I-ORGderiv": 10,
80
+ "I-ORGpart": 12,
81
+ "I-OTH": 14,
82
+ "I-OTHderiv": 16,
83
+ "I-OTHpart": 18,
84
+ "I-PER": 20,
85
+ "I-PERderiv": 22,
86
+ "I-PERpart": 24,
87
+ "O": 0
88
+ },
89
+ "layer_norm_eps": 1e-12,
90
+ "length_penalty": 1.0,
91
+ "max_length": 20,
92
+ "max_position_embeddings": 512,
93
+ "min_length": 0,
94
+ "model_type": "bert",
95
+ "no_repeat_ngram_size": 0,
96
+ "num_attention_heads": 12,
97
+ "num_beam_groups": 1,
98
+ "num_beams": 1,
99
+ "num_hidden_layers": 12,
100
+ "num_return_sequences": 1,
101
+ "output_attentions": false,
102
+ "output_hidden_states": false,
103
+ "output_scores": false,
104
+ "pad_token_id": 0,
105
+ "position_embedding_type": "absolute",
106
+ "prefix": null,
107
+ "problem_type": null,
108
+ "pruned_heads": {},
109
+ "remove_invalid_values": false,
110
+ "repetition_penalty": 1.0,
111
+ "return_dict": true,
112
+ "return_dict_in_generate": false,
113
+ "sep_token_id": null,
114
+ "suppress_tokens": null,
115
+ "task_specific_params": null,
116
+ "temperature": 1.0,
117
+ "tf_legacy_loss": false,
118
+ "tie_encoder_decoder": false,
119
+ "tie_word_embeddings": true,
120
+ "tokenizer_class": null,
121
+ "top_k": 50,
122
+ "top_p": 1.0,
123
+ "torch_dtype": "float32",
124
+ "torchscript": false,
125
+ "transformers_version": "4.31.0",
126
+ "type_vocab_size": 2,
127
+ "typical_p": 1.0,
128
+ "use_bfloat16": false,
129
+ "use_cache": true,
130
+ "vocab_size": 32002
131
+ },
132
+ "entity_max_length": 8,
133
+ "id2label": {
134
+ "0": "O",
135
+ "1": "LOC",
136
+ "2": "LOCderiv",
137
+ "3": "LOCpart",
138
+ "4": "ORG",
139
+ "5": "ORGderiv",
140
+ "6": "ORGpart",
141
+ "7": "OTH",
142
+ "8": "OTHderiv",
143
+ "9": "OTHpart",
144
+ "10": "PER",
145
+ "11": "PERderiv",
146
+ "12": "PERpart"
147
+ },
148
+ "id2reduced_id": {
149
+ "0": 0,
150
+ "1": 1,
151
+ "2": 1,
152
+ "3": 2,
153
+ "4": 2,
154
+ "5": 3,
155
+ "6": 3,
156
+ "7": 4,
157
+ "8": 4,
158
+ "9": 5,
159
+ "10": 5,
160
+ "11": 6,
161
+ "12": 6,
162
+ "13": 7,
163
+ "14": 7,
164
+ "15": 8,
165
+ "16": 8,
166
+ "17": 9,
167
+ "18": 9,
168
+ "19": 10,
169
+ "20": 10,
170
+ "21": 11,
171
+ "22": 11,
172
+ "23": 12,
173
+ "24": 12
174
+ },
175
+ "label2id": {
176
+ "LOC": 1,
177
+ "LOCderiv": 2,
178
+ "LOCpart": 3,
179
+ "O": 0,
180
+ "ORG": 4,
181
+ "ORGderiv": 5,
182
+ "ORGpart": 6,
183
+ "OTH": 7,
184
+ "OTHderiv": 8,
185
+ "OTHpart": 9,
186
+ "PER": 10,
187
+ "PERderiv": 11,
188
+ "PERpart": 12
189
+ },
190
+ "marker_max_length": 128,
191
+ "max_next_context": null,
192
+ "max_prev_context": null,
193
+ "model_max_length": 256,
194
+ "model_max_length_default": 512,
195
+ "model_type": "span-marker",
196
+ "span_marker_version": "1.2.4",
197
+ "torch_dtype": "float32",
198
+ "trained_with_document_context": false,
199
+ "transformers_version": "4.31.0",
200
+ "vocab_size": 32002
201
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf7dc06b0030ba189c4a7be870526a35571197b5df837874b639d05648d74c3
3
+ size 442624369
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 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_basic_tokenize": true,
6
+ "do_lower_case": false,
7
+ "entity_max_length": 8,
8
+ "marker_max_length": 128,
9
+ "mask_token": "[MASK]",
10
+ "max_len": 512,
11
+ "model_max_length": 256,
12
+ "never_split": null,
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "strip_accents": null,
16
+ "tokenize_chinese_chars": true,
17
+ "tokenizer_class": "BertTokenizer",
18
+ "unk_token": "[UNK]"
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dddf22281c1338cb0f85ea73d4271dd95a38127b1321957f0f10e4153d1c152
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff