NAACL 2022 trained version
Browse files- config.json +166 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,166 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForTokenClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"directionality": "bidi",
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "ALT",
|
14 |
+
"2": "AND",
|
15 |
+
"3": "APP",
|
16 |
+
"4": "ART",
|
17 |
+
"5": "BUT",
|
18 |
+
"6": "COM",
|
19 |
+
"7": "CON",
|
20 |
+
"8": "COO",
|
21 |
+
"9": "DEC",
|
22 |
+
"10": "DEF",
|
23 |
+
"11": "DIS",
|
24 |
+
"12": "DOM",
|
25 |
+
"13": "DOW",
|
26 |
+
"14": "DST",
|
27 |
+
"15": "EFS",
|
28 |
+
"16": "EMP",
|
29 |
+
"17": "ENG",
|
30 |
+
"18": "ENS",
|
31 |
+
"19": "ENT",
|
32 |
+
"20": "EPG",
|
33 |
+
"21": "EPS",
|
34 |
+
"22": "EPT",
|
35 |
+
"23": "EQA",
|
36 |
+
"24": "ETG",
|
37 |
+
"25": "ETV",
|
38 |
+
"26": "EXC",
|
39 |
+
"27": "EXG",
|
40 |
+
"28": "EXN",
|
41 |
+
"29": "EXS",
|
42 |
+
"30": "EXT",
|
43 |
+
"31": "EXV",
|
44 |
+
"32": "FUT",
|
45 |
+
"33": "GPE",
|
46 |
+
"34": "HAP",
|
47 |
+
"35": "HAS",
|
48 |
+
"36": "IMP",
|
49 |
+
"37": "INT",
|
50 |
+
"38": "IST",
|
51 |
+
"39": "ITJ",
|
52 |
+
"40": "LES",
|
53 |
+
"41": "LOC",
|
54 |
+
"42": "MOR",
|
55 |
+
"43": "MOY",
|
56 |
+
"44": "NAT",
|
57 |
+
"45": "NEC",
|
58 |
+
"46": "NIL",
|
59 |
+
"47": "NOT",
|
60 |
+
"48": "NOW",
|
61 |
+
"49": "ORG",
|
62 |
+
"50": "PER",
|
63 |
+
"51": "POS",
|
64 |
+
"52": "PRO",
|
65 |
+
"53": "PRX",
|
66 |
+
"54": "PST",
|
67 |
+
"55": "QUA",
|
68 |
+
"56": "QUE",
|
69 |
+
"57": "REF",
|
70 |
+
"58": "REL",
|
71 |
+
"59": "RLI",
|
72 |
+
"60": "ROL",
|
73 |
+
"61": "SCO",
|
74 |
+
"62": "SUB",
|
75 |
+
"63": "TIM",
|
76 |
+
"64": "TOP",
|
77 |
+
"65": "UNK",
|
78 |
+
"66": "UOM",
|
79 |
+
"67": "YOC"
|
80 |
+
},
|
81 |
+
"initializer_range": 0.02,
|
82 |
+
"intermediate_size": 3072,
|
83 |
+
"label2id": {
|
84 |
+
"ALT": 1,
|
85 |
+
"AND": 2,
|
86 |
+
"APP": 3,
|
87 |
+
"ART": 4,
|
88 |
+
"BUT": 5,
|
89 |
+
"COM": 6,
|
90 |
+
"CON": 7,
|
91 |
+
"COO": 8,
|
92 |
+
"DEC": 9,
|
93 |
+
"DEF": 10,
|
94 |
+
"DIS": 11,
|
95 |
+
"DOM": 12,
|
96 |
+
"DOW": 13,
|
97 |
+
"DST": 14,
|
98 |
+
"EFS": 15,
|
99 |
+
"EMP": 16,
|
100 |
+
"ENG": 17,
|
101 |
+
"ENS": 18,
|
102 |
+
"ENT": 19,
|
103 |
+
"EPG": 20,
|
104 |
+
"EPS": 21,
|
105 |
+
"EPT": 22,
|
106 |
+
"EQA": 23,
|
107 |
+
"ETG": 24,
|
108 |
+
"ETV": 25,
|
109 |
+
"EXC": 26,
|
110 |
+
"EXG": 27,
|
111 |
+
"EXN": 28,
|
112 |
+
"EXS": 29,
|
113 |
+
"EXT": 30,
|
114 |
+
"EXV": 31,
|
115 |
+
"FUT": 32,
|
116 |
+
"GPE": 33,
|
117 |
+
"HAP": 34,
|
118 |
+
"HAS": 35,
|
119 |
+
"IMP": 36,
|
120 |
+
"INT": 37,
|
121 |
+
"IST": 38,
|
122 |
+
"ITJ": 39,
|
123 |
+
"LES": 40,
|
124 |
+
"LOC": 41,
|
125 |
+
"MOR": 42,
|
126 |
+
"MOY": 43,
|
127 |
+
"NAT": 44,
|
128 |
+
"NEC": 45,
|
129 |
+
"NIL": 46,
|
130 |
+
"NOT": 47,
|
131 |
+
"NOW": 48,
|
132 |
+
"O": 0,
|
133 |
+
"ORG": 49,
|
134 |
+
"PER": 50,
|
135 |
+
"POS": 51,
|
136 |
+
"PRO": 52,
|
137 |
+
"PRX": 53,
|
138 |
+
"PST": 54,
|
139 |
+
"QUA": 55,
|
140 |
+
"QUE": 56,
|
141 |
+
"REF": 57,
|
142 |
+
"REL": 58,
|
143 |
+
"RLI": 59,
|
144 |
+
"ROL": 60,
|
145 |
+
"SCO": 61,
|
146 |
+
"SUB": 62,
|
147 |
+
"TIM": 63,
|
148 |
+
"TOP": 64,
|
149 |
+
"UNK": 65,
|
150 |
+
"UOM": 66,
|
151 |
+
"YOC": 67
|
152 |
+
},
|
153 |
+
"layer_norm_eps": 1e-12,
|
154 |
+
"max_position_embeddings": 512,
|
155 |
+
"model_type": "bert",
|
156 |
+
"num_attention_heads": 12,
|
157 |
+
"num_hidden_layers": 12,
|
158 |
+
"pad_token_id": 0,
|
159 |
+
"pooler_fc_size": 768,
|
160 |
+
"pooler_num_attention_heads": 12,
|
161 |
+
"pooler_num_fc_layers": 3,
|
162 |
+
"pooler_size_per_head": 128,
|
163 |
+
"pooler_type": "first_token_transform",
|
164 |
+
"type_vocab_size": 2,
|
165 |
+
"vocab_size": 119547
|
166 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f494da40cffed443b45f50348e40837a305416074086ec9c6115b1dc9e84396
|
3 |
+
size 711677495
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "model_max_length": 512}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03bf56315fb86b9e1d29b0b83660c4aaa13223a0d5d107cefdad04bcf9988f8d
|
3 |
+
size 1289
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|