boltuix commited on
Commit
2ed5136
·
verified ·
1 Parent(s): f587310

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "return_dict": true,
3
+ "output_hidden_states": false,
4
+ "output_attentions": false,
5
+ "torchscript": false,
6
+ "torch_dtype": "float32",
7
+ "use_bfloat16": false,
8
+ "tf_legacy_loss": false,
9
+ "pruned_heads": {},
10
+ "tie_word_embeddings": true,
11
+ "chunk_size_feed_forward": 0,
12
+ "is_encoder_decoder": false,
13
+ "is_decoder": false,
14
+ "cross_attention_hidden_size": null,
15
+ "add_cross_attention": false,
16
+ "tie_encoder_decoder": false,
17
+ "max_length": 20,
18
+ "min_length": 0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "num_beams": 1,
22
+ "num_beam_groups": 1,
23
+ "diversity_penalty": 0.0,
24
+ "temperature": 1.0,
25
+ "top_k": 50,
26
+ "top_p": 1.0,
27
+ "typical_p": 1.0,
28
+ "repetition_penalty": 1.0,
29
+ "length_penalty": 1.0,
30
+ "no_repeat_ngram_size": 0,
31
+ "encoder_no_repeat_ngram_size": 0,
32
+ "bad_words_ids": null,
33
+ "num_return_sequences": 1,
34
+ "output_scores": false,
35
+ "return_dict_in_generate": false,
36
+ "forced_bos_token_id": null,
37
+ "forced_eos_token_id": null,
38
+ "remove_invalid_values": false,
39
+ "exponential_decay_length_penalty": null,
40
+ "suppress_tokens": null,
41
+ "begin_suppress_tokens": null,
42
+ "architectures": [
43
+ "BertForTokenClassification"
44
+ ],
45
+ "finetuning_task": null,
46
+ "id2label": {
47
+ "0": "O",
48
+ "1": "B-fromloc.city_name",
49
+ "2": "I-fromloc.city_name",
50
+ "3": "B-toloc.city_name",
51
+ "4": "I-toloc.city_name",
52
+ "5": "B-transportation_mode",
53
+ "6": "I-transportation_mode",
54
+ "7": "B-person",
55
+ "8": "I-person",
56
+ "9": "B-organization",
57
+ "10": "I-organization",
58
+ "11": "B-city",
59
+ "12": "I-city",
60
+ "13": "B-state",
61
+ "14": "I-state",
62
+ "15": "B-email",
63
+ "16": "I-email",
64
+ "17": "B-phone_number",
65
+ "18": "I-phone_number",
66
+ "19": "B-url",
67
+ "20": "I-url",
68
+ "21": "B-date",
69
+ "22": "I-date",
70
+ "23": "B-time",
71
+ "24": "I-time",
72
+ "25": "B-job_title",
73
+ "26": "I-job_title",
74
+ "27": "B-country",
75
+ "28": "I-country"
76
+ },
77
+ "label2id": {
78
+ "O": 0,
79
+ "B-fromloc.city_name": 1,
80
+ "I-fromloc.city_name": 2,
81
+ "B-toloc.city_name": 3,
82
+ "I-toloc.city_name": 4,
83
+ "B-transportation_mode": 5,
84
+ "I-transportation_mode": 6,
85
+ "B-person": 7,
86
+ "I-person": 8,
87
+ "B-organization": 9,
88
+ "I-organization": 10,
89
+ "B-city": 11,
90
+ "I-city": 12,
91
+ "B-state": 13,
92
+ "I-state": 14,
93
+ "B-email": 15,
94
+ "I-email": 16,
95
+ "B-phone_number": 17,
96
+ "I-phone_number": 18,
97
+ "B-url": 19,
98
+ "I-url": 20,
99
+ "B-date": 21,
100
+ "I-date": 22,
101
+ "B-time": 23,
102
+ "I-time": 24,
103
+ "B-job_title": 25,
104
+ "I-job_title": 26,
105
+ "B-country": 27,
106
+ "I-country": 28
107
+ },
108
+ "tokenizer_class": null,
109
+ "prefix": null,
110
+ "bos_token_id": null,
111
+ "pad_token_id": 0,
112
+ "eos_token_id": null,
113
+ "sep_token_id": null,
114
+ "decoder_start_token_id": null,
115
+ "task_specific_params": null,
116
+ "problem_type": null,
117
+ "_name_or_path": "boltuix/bert-mini",
118
+ "transformers_version": "4.52.4",
119
+ "model_type": "bert",
120
+ "vocab_size": 30522,
121
+ "hidden_size": 128,
122
+ "num_hidden_layers": 4,
123
+ "num_attention_heads": 2,
124
+ "hidden_act": "gelu",
125
+ "intermediate_size": 512,
126
+ "hidden_dropout_prob": 0.1,
127
+ "attention_probs_dropout_prob": 0.1,
128
+ "max_position_embeddings": 512,
129
+ "type_vocab_size": 2,
130
+ "initializer_range": 0.02,
131
+ "layer_norm_eps": 1e-12,
132
+ "position_embedding_type": "absolute",
133
+ "use_cache": true,
134
+ "classifier_dropout": null
135
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b023aa177c17af540fade6293a969e08eb18a9b926f116870af2a8e862031f9a
3
+ size 19086884
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff