Hugging Face's logo

lst-nectec
/
HoogBERTa-NER-lst20

Token Classification
Transformers
PyTorch
Safetensors
Thai
roberta
Inference Endpoints
Model card Files Community
2
HoogBERTa-NER-lst20
File size: 2,495 Bytes 
13aa7fa
32a058e
13aa7fa
38a956f
13aa7fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
 
{
  "_name_or_path": "data/converted_model_ner_huggingface",
  "architectures": [
    "RobertaForTokenClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "<s>",
    "1": "<pad>",
    "2": "</s>",
    "3": "<unk>",
    "4": "O",
    "5": "B_ORG",
    "6": "B_PER",
    "7": "B_LOC",
    "8": "B_MEA",
    "9": "I_DTM",
    "10": "I_ORG",
    "11": "E_ORG",
    "12": "I_PER",
    "13": "B_TTL",
    "14": "E_PER",
    "15": "B_DES",
    "16": "E_LOC",
    "17": "B_DTM",
    "18": "B_NUM",
    "19": "I_MEA",
    "20": "E_DTM",
    "21": "E_MEA",
    "22": "I_LOC",
    "23": "I_DES",
    "24": "E_DES",
    "25": "I_NUM",
    "26": "B",
    "27": "E_NUM",
    "28": "B_TRM",
    "29": "B_BRN",
    "30": "I_TRM",
    "31": "E_TRM",
    "32": "I_TTL",
    "33": "I_BRN",
    "34": "E_BRN",
    "35": "E_TTL",
    "36": "B_NAME",
    "37": "__",
    "38": "DDEM",
    "39": "I",
    "40": "MEA_BI",
    "41": "OBRN_B",
    "42": "ORG_I",
    "43": "PER_I",
    "44": "madeupword0000",
    "45": "madeupword0001",
    "46": "madeupword0002",
    "47": "madeupword0003"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "</s>": 2,
    "<pad>": 1,
    "<s>": 0,
    "<unk>": 3,
    "B": 26,
    "B_BRN": 29,
    "B_DES": 15,
    "B_DTM": 17,
    "B_LOC": 7,
    "B_MEA": 8,
    "B_NAME": 36,
    "B_NUM": 18,
    "B_ORG": 5,
    "B_PER": 6,
    "B_TRM": 28,
    "B_TTL": 13,
    "DDEM": 38,
    "E_BRN": 34,
    "E_DES": 24,
    "E_DTM": 20,
    "E_LOC": 16,
    "E_MEA": 21,
    "E_NUM": 27,
    "E_ORG": 11,
    "E_PER": 14,
    "E_TRM": 31,
    "E_TTL": 35,
    "I": 39,
    "I_BRN": 33,
    "I_DES": 23,
    "I_DTM": 9,
    "I_LOC": 22,
    "I_MEA": 19,
    "I_NUM": 25,
    "I_ORG": 10,
    "I_PER": 12,
    "I_TRM": 30,
    "I_TTL": 32,
    "MEA_BI": 40,
    "O": 4,
    "OBRN_B": 41,
    "ORG_I": 42,
    "PER_I": 43,
    "__": 37,
    "madeupword0000": 44,
    "madeupword0001": 45,
    "madeupword0002": 46,
    "madeupword0003": 47
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.27.4",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 74905
}