Hugging Face's logo

KoichiYasuoka
/
roberta-base-thai-syllable-upos

Token Classification
Transformers
PyTorch
Thai
roberta
thai
pos
wikipedia
dependency-parsing
Inference Endpoints
Model card Files Community
1
roberta-base-thai-syllable-upos
File size: 2,268 Bytes 
4587d90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "architectures": [
    "RobertaForTokenClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "B-NUM",
    "1": "I-NUM",
    "2": "PART",
    "3": "B-NOUN",
    "4": "B-DET",
    "5": "PROPN",
    "6": "ADJ",
    "7": "I-ADP",
    "8": "B-VERB",
    "9": "I-ADV",
    "10": "PRON",
    "11": "I-AUX",
    "12": "I-PROPN",
    "13": "B-CCONJ",
    "14": "DET",
    "15": "B-ADP",
    "16": "SYM",
    "17": "I-DET",
    "18": "B-AUX",
    "19": "AUX",
    "20": "VERB",
    "21": "I-VERB",
    "22": "I-PART",
    "23": "B-PROPN",
    "24": "I-PUNCT",
    "25": "I-PRON",
    "26": "CCONJ",
    "27": "ADV",
    "28": "NUM",
    "29": "SCONJ",
    "30": "PUNCT",
    "31": "NOUN",
    "32": "I-ADJ",
    "33": "B-PRON",
    "34": "B-ADJ",
    "35": "B-PART",
    "36": "B-ADV",
    "37": "I-NOUN",
    "38": "ADP",
    "39": "B-PUNCT",
    "40": "I-CCONJ"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "ADJ": 6,
    "ADP": 38,
    "ADV": 27,
    "AUX": 19,
    "B-ADJ": 34,
    "B-ADP": 15,
    "B-ADV": 36,
    "B-AUX": 18,
    "B-CCONJ": 13,
    "B-DET": 4,
    "B-NOUN": 3,
    "B-NUM": 0,
    "B-PART": 35,
    "B-PRON": 33,
    "B-PROPN": 23,
    "B-PUNCT": 39,
    "B-VERB": 8,
    "CCONJ": 26,
    "DET": 14,
    "I-ADJ": 32,
    "I-ADP": 7,
    "I-ADV": 9,
    "I-AUX": 11,
    "I-CCONJ": 40,
    "I-DET": 17,
    "I-NOUN": 37,
    "I-NUM": 1,
    "I-PART": 22,
    "I-PRON": 25,
    "I-PROPN": 12,
    "I-PUNCT": 24,
    "I-VERB": 21,
    "NOUN": 31,
    "NUM": 28,
    "PART": 2,
    "PRON": 10,
    "PROPN": 5,
    "PUNCT": 30,
    "SCONJ": 29,
    "SYM": 16,
    "VERB": 20
  },
  "layer_norm_eps": 1e-05,
  "mask_token_id": 4,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "tokenizer_class": "BertTokenizerFast",
  "torch_dtype": "float32",
  "transformers_version": "4.10.0",
  "type_vocab_size": 1,
  "unk_token_id": 3,
  "use_cache": true,
  "vocab_size": 33144
}