Hugging Face's logo

KoichiYasuoka
/
roberta-base-japanese-luw-upos

Token Classification
Transformers
PyTorch
Japanese
roberta
japanese
pos
dependency-parsing
Inference Endpoints
Model card Files Community
KoichiYasuoka commited on
Commit
9ce5ff8
•
1 Parent(s): 812c493

model improved

Browse files
Files changed (2) hide show
  1. config.json +97 -96
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "RobertaForTokenClassification"
4
  ],
@@ -10,108 +11,108 @@
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
- "0": "B-NOUN",
14
- "1": "B-PART",
15
- "2": "B-PROPN",
16
- "3": "SYM",
17
- "4": "B-AUX",
18
- "5": "ADP",
19
- "6": "B-VERB",
20
- "7": "CCONJ",
21
- "8": "ADJ",
22
- "9": "I-PRON",
23
- "10": "B-CCONJ",
24
- "11": "B-NUM",
25
- "12": "NUM",
26
- "13": "I-X",
27
- "14": "I-NUM",
28
- "15": "I-PART",
29
- "16": "I-SCONJ",
30
- "17": "PROPN",
31
- "18": "PART",
32
- "19": "B-PRON",
33
- "20": "B-DET",
34
- "21": "I-SYM",
35
- "22": "I-PROPN",
36
- "23": "I-ADV",
37
- "24": "I-INTJ",
38
- "25": "B-SCONJ",
39
- "26": "I-DET",
40
- "27": "I-CCONJ",
41
- "28": "I-NOUN",
42
- "29": "PRON",
43
- "30": "B-ADJ",
44
- "31": "AUX",
45
- "32": "INTJ",
46
- "33": "ADV",
47
- "34": "X",
48
- "35": "PUNCT",
49
- "36": "I-VERB",
50
- "37": "B-SYM",
51
- "38": "B-INTJ",
52
- "39": "NOUN",
53
- "40": "B-X",
54
- "41": "I-ADP",
55
  "42": "VERB",
56
- "43": "I-AUX",
57
- "44": "B-ADP",
58
- "45": "I-ADJ",
59
- "46": "SCONJ",
60
- "47": "DET",
61
- "48": "B-ADV"
62
  },
63
  "initializer_range": 0.02,
64
  "intermediate_size": 3072,
65
  "label2id": {
66
- "ADJ": 8,
67
- "ADP": 5,
68
- "ADV": 33,
69
- "AUX": 31,
70
- "B-ADJ": 30,
71
- "B-ADP": 44,
72
- "B-ADV": 48,
73
- "B-AUX": 4,
74
- "B-CCONJ": 10,
75
- "B-DET": 20,
76
- "B-INTJ": 38,
77
- "B-NOUN": 0,
78
- "B-NUM": 11,
79
- "B-PART": 1,
80
- "B-PRON": 19,
81
- "B-PROPN": 2,
82
- "B-SCONJ": 25,
83
- "B-SYM": 37,
84
- "B-VERB": 6,
85
- "B-X": 40,
86
- "CCONJ": 7,
87
- "DET": 47,
88
- "I-ADJ": 45,
89
- "I-ADP": 41,
90
- "I-ADV": 23,
91
- "I-AUX": 43,
92
- "I-CCONJ": 27,
93
- "I-DET": 26,
94
- "I-INTJ": 24,
95
- "I-NOUN": 28,
96
- "I-NUM": 14,
97
- "I-PART": 15,
98
- "I-PRON": 9,
99
- "I-PROPN": 22,
100
- "I-SCONJ": 16,
101
- "I-SYM": 21,
102
- "I-VERB": 36,
103
- "I-X": 13,
104
- "INTJ": 32,
105
- "NOUN": 39,
106
- "NUM": 12,
107
- "PART": 18,
108
- "PRON": 29,
109
- "PROPN": 17,
110
- "PUNCT": 35,
111
- "SCONJ": 46,
112
- "SYM": 3,
113
  "VERB": 42,
114
- "X": 34
115
  },
116
  "layer_norm_eps": 1e-12,
117
  "max_position_embeddings": 512,
 
1
  {
2
+ "_name_or_path": "KoichiYasuoka/roberta-base-japanese-aozora",
3
  "architectures": [
4
  "RobertaForTokenClassification"
5
  ],
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
+ "0": "NUM",
15
+ "1": "ADP",
16
+ "2": "I-ADP",
17
+ "3": "B-PART",
18
+ "4": "I-NUM",
19
+ "5": "I-SCONJ",
20
+ "6": "X",
21
+ "7": "PART",
22
+ "8": "SYM",
23
+ "9": "I-PART",
24
+ "10": "B-PROPN",
25
+ "11": "I-VERB",
26
+ "12": "SCONJ",
27
+ "13": "ADV",
28
+ "14": "I-ADJ",
29
+ "15": "AUX",
30
+ "16": "B-SYM",
31
+ "17": "I-PRON",
32
+ "18": "PRON",
33
+ "19": "INTJ",
34
+ "20": "PROPN",
35
+ "21": "B-ADJ",
36
+ "22": "I-DET",
37
+ "23": "I-AUX",
38
+ "24": "I-PROPN",
39
+ "25": "B-DET",
40
+ "26": "B-AUX",
41
+ "27": "I-ADV",
42
+ "28": "CCONJ",
43
+ "29": "NOUN",
44
+ "30": "B-NUM",
45
+ "31": "B-X",
46
+ "32": "I-INTJ",
47
+ "33": "B-ADV",
48
+ "34": "I-NOUN",
49
+ "35": "I-SYM",
50
+ "36": "ADJ",
51
+ "37": "B-INTJ",
52
+ "38": "B-NOUN",
53
+ "39": "B-SCONJ",
54
+ "40": "I-X",
55
+ "41": "B-ADP",
56
  "42": "VERB",
57
+ "43": "PUNCT",
58
+ "44": "B-CCONJ",
59
+ "45": "I-CCONJ",
60
+ "46": "DET",
61
+ "47": "B-VERB",
62
+ "48": "B-PRON"
63
  },
64
  "initializer_range": 0.02,
65
  "intermediate_size": 3072,
66
  "label2id": {
67
+ "ADJ": 36,
68
+ "ADP": 1,
69
+ "ADV": 13,
70
+ "AUX": 15,
71
+ "B-ADJ": 21,
72
+ "B-ADP": 41,
73
+ "B-ADV": 33,
74
+ "B-AUX": 26,
75
+ "B-CCONJ": 44,
76
+ "B-DET": 25,
77
+ "B-INTJ": 37,
78
+ "B-NOUN": 38,
79
+ "B-NUM": 30,
80
+ "B-PART": 3,
81
+ "B-PRON": 48,
82
+ "B-PROPN": 10,
83
+ "B-SCONJ": 39,
84
+ "B-SYM": 16,
85
+ "B-VERB": 47,
86
+ "B-X": 31,
87
+ "CCONJ": 28,
88
+ "DET": 46,
89
+ "I-ADJ": 14,
90
+ "I-ADP": 2,
91
+ "I-ADV": 27,
92
+ "I-AUX": 23,
93
+ "I-CCONJ": 45,
94
+ "I-DET": 22,
95
+ "I-INTJ": 32,
96
+ "I-NOUN": 34,
97
+ "I-NUM": 4,
98
+ "I-PART": 9,
99
+ "I-PRON": 17,
100
+ "I-PROPN": 24,
101
+ "I-SCONJ": 5,
102
+ "I-SYM": 35,
103
+ "I-VERB": 11,
104
+ "I-X": 40,
105
+ "INTJ": 19,
106
+ "NOUN": 29,
107
+ "NUM": 0,
108
+ "PART": 7,
109
+ "PRON": 18,
110
+ "PROPN": 20,
111
+ "PUNCT": 43,
112
+ "SCONJ": 12,
113
+ "SYM": 8,
114
  "VERB": 42,
115
+ "X": 6
116
  },
117
  "layer_norm_eps": 1e-12,
118
  "max_position_embeddings": 512,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65ea9fd989d0944f84a7ccd4f610ce88e16cc2c0ea469025da25afead653f89e
3
- size 1111009234
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee4fabf9bac18da2b025643713bb091d4e2837537934732cfe3cf166d522ce0
3
+ size 1111009237