KoichiYasuoka commited on
Commit
97a10b5
1 Parent(s): 4587d90

model improved

Browse files
Files changed (4) hide show
  1. config.json +81 -81
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. vocab.txt +0 -0
config.json CHANGED
@@ -11,92 +11,92 @@
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
- "0": "B-NUM",
15
- "1": "I-NUM",
16
- "2": "PART",
17
- "3": "B-NOUN",
18
- "4": "B-DET",
19
- "5": "PROPN",
20
  "6": "ADJ",
21
- "7": "I-ADP",
22
- "8": "B-VERB",
23
- "9": "I-ADV",
24
- "10": "PRON",
25
- "11": "I-AUX",
26
- "12": "I-PROPN",
27
- "13": "B-CCONJ",
28
- "14": "DET",
29
- "15": "B-ADP",
30
- "16": "SYM",
31
- "17": "I-DET",
32
- "18": "B-AUX",
33
- "19": "AUX",
34
- "20": "VERB",
35
- "21": "I-VERB",
36
- "22": "I-PART",
37
- "23": "B-PROPN",
38
- "24": "I-PUNCT",
39
- "25": "I-PRON",
40
- "26": "CCONJ",
41
- "27": "ADV",
42
- "28": "NUM",
43
- "29": "SCONJ",
44
- "30": "PUNCT",
45
- "31": "NOUN",
46
- "32": "I-ADJ",
47
- "33": "B-PRON",
48
- "34": "B-ADJ",
49
- "35": "B-PART",
50
- "36": "B-ADV",
51
- "37": "I-NOUN",
52
- "38": "ADP",
53
- "39": "B-PUNCT",
54
- "40": "I-CCONJ"
55
  },
56
  "initializer_range": 0.02,
57
  "intermediate_size": 3072,
58
  "label2id": {
59
  "ADJ": 6,
60
- "ADP": 38,
61
- "ADV": 27,
62
- "AUX": 19,
63
- "B-ADJ": 34,
64
- "B-ADP": 15,
65
- "B-ADV": 36,
66
- "B-AUX": 18,
67
- "B-CCONJ": 13,
68
- "B-DET": 4,
69
- "B-NOUN": 3,
70
- "B-NUM": 0,
71
- "B-PART": 35,
72
- "B-PRON": 33,
73
- "B-PROPN": 23,
74
- "B-PUNCT": 39,
75
- "B-VERB": 8,
76
- "CCONJ": 26,
77
- "DET": 14,
78
- "I-ADJ": 32,
79
- "I-ADP": 7,
80
- "I-ADV": 9,
81
- "I-AUX": 11,
82
- "I-CCONJ": 40,
83
- "I-DET": 17,
84
- "I-NOUN": 37,
85
- "I-NUM": 1,
86
- "I-PART": 22,
87
- "I-PRON": 25,
88
- "I-PROPN": 12,
89
- "I-PUNCT": 24,
90
- "I-VERB": 21,
91
- "NOUN": 31,
92
- "NUM": 28,
93
- "PART": 2,
94
- "PRON": 10,
95
- "PROPN": 5,
96
- "PUNCT": 30,
97
- "SCONJ": 29,
98
- "SYM": 16,
99
- "VERB": 20
100
  },
101
  "layer_norm_eps": 1e-05,
102
  "mask_token_id": 4,
@@ -112,5 +112,5 @@
112
  "type_vocab_size": 1,
113
  "unk_token_id": 3,
114
  "use_cache": true,
115
- "vocab_size": 33144
116
  }
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
+ "0": "I-PART",
15
+ "1": "I-PROPN",
16
+ "2": "B-PROPN",
17
+ "3": "I-PUNCT",
18
+ "4": "B-CCONJ",
19
+ "5": "B-PRON",
20
  "6": "ADJ",
21
+ "7": "CCONJ",
22
+ "8": "VERB",
23
+ "9": "B-NUM",
24
+ "10": "B-AUX",
25
+ "11": "I-ADP",
26
+ "12": "NOUN",
27
+ "13": "SCONJ",
28
+ "14": "I-AUX",
29
+ "15": "B-DET",
30
+ "16": "B-PUNCT",
31
+ "17": "B-VERB",
32
+ "18": "PART",
33
+ "19": "B-ADP",
34
+ "20": "I-NOUN",
35
+ "21": "ADV",
36
+ "22": "DET",
37
+ "23": "B-ADJ",
38
+ "24": "B-ADV",
39
+ "25": "I-NUM",
40
+ "26": "PUNCT",
41
+ "27": "PROPN",
42
+ "28": "I-CCONJ",
43
+ "29": "I-DET",
44
+ "30": "ADP",
45
+ "31": "I-ADJ",
46
+ "32": "PRON",
47
+ "33": "I-PRON",
48
+ "34": "NUM",
49
+ "35": "I-ADV",
50
+ "36": "B-NOUN",
51
+ "37": "SYM",
52
+ "38": "I-VERB",
53
+ "39": "AUX",
54
+ "40": "B-PART"
55
  },
56
  "initializer_range": 0.02,
57
  "intermediate_size": 3072,
58
  "label2id": {
59
  "ADJ": 6,
60
+ "ADP": 30,
61
+ "ADV": 21,
62
+ "AUX": 39,
63
+ "B-ADJ": 23,
64
+ "B-ADP": 19,
65
+ "B-ADV": 24,
66
+ "B-AUX": 10,
67
+ "B-CCONJ": 4,
68
+ "B-DET": 15,
69
+ "B-NOUN": 36,
70
+ "B-NUM": 9,
71
+ "B-PART": 40,
72
+ "B-PRON": 5,
73
+ "B-PROPN": 2,
74
+ "B-PUNCT": 16,
75
+ "B-VERB": 17,
76
+ "CCONJ": 7,
77
+ "DET": 22,
78
+ "I-ADJ": 31,
79
+ "I-ADP": 11,
80
+ "I-ADV": 35,
81
+ "I-AUX": 14,
82
+ "I-CCONJ": 28,
83
+ "I-DET": 29,
84
+ "I-NOUN": 20,
85
+ "I-NUM": 25,
86
+ "I-PART": 0,
87
+ "I-PRON": 33,
88
+ "I-PROPN": 1,
89
+ "I-PUNCT": 3,
90
+ "I-VERB": 38,
91
+ "NOUN": 12,
92
+ "NUM": 34,
93
+ "PART": 18,
94
+ "PRON": 32,
95
+ "PROPN": 27,
96
+ "PUNCT": 26,
97
+ "SCONJ": 13,
98
+ "SYM": 37,
99
+ "VERB": 8
100
  },
101
  "layer_norm_eps": 1e-05,
102
  "mask_token_id": 4,
 
112
  "type_vocab_size": 1,
113
  "unk_token_id": 3,
114
  "use_cache": true,
115
+ "vocab_size": 16582
116
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4860ad4ef9b423ca8a89f032a9b835d23ecbc82ae21dac6e9a6c8279241959c
3
- size 443838354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d026f658cc7f72ce7f02981de69586c562efea5868afc741c08b1d4dd820707
3
+ size 392959889
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff