Luca Foppiano
commited on
Commit
·
ef5ded5
1
Parent(s):
54ac10e
add missing model
Browse files- software-type-BERT_CRF/config.json +38 -0
- software-type-BERT_CRF/model_weights.hdf5 +3 -0
- software-type-BERT_CRF/preprocessor.json +314 -0
- software-type-BERT_CRF/transformer-config.json +25 -0
- software-type-BERT_CRF/transformer-tokenizer/special_tokens_map.json +1 -0
- software-type-BERT_CRF/transformer-tokenizer/tokenizer.json +0 -0
- software-type-BERT_CRF/transformer-tokenizer/tokenizer_config.json +1 -0
- software-type-BERT_CRF/transformer-tokenizer/vocab.txt +0 -0
software-type-BERT_CRF/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_name": "software-type-BERT_CRF",
|
3 |
+
"architecture": "BERT_CRF",
|
4 |
+
"embeddings_name": null,
|
5 |
+
"char_vocab_size": 267,
|
6 |
+
"case_vocab_size": 8,
|
7 |
+
"char_embedding_size": 25,
|
8 |
+
"num_char_lstm_units": 25,
|
9 |
+
"max_char_length": 30,
|
10 |
+
"features_vocabulary_size": 12,
|
11 |
+
"features_indices": null,
|
12 |
+
"features_embedding_size": 4,
|
13 |
+
"features_lstm_units": 4,
|
14 |
+
"max_sequence_length": 512,
|
15 |
+
"word_embedding_size": 0,
|
16 |
+
"num_word_lstm_units": 100,
|
17 |
+
"case_embedding_size": 5,
|
18 |
+
"dropout": 0.5,
|
19 |
+
"recurrent_dropout": 0.5,
|
20 |
+
"use_crf": true,
|
21 |
+
"use_chain_crf": false,
|
22 |
+
"fold_number": 1,
|
23 |
+
"batch_size": 8,
|
24 |
+
"transformer_name": "michiyasunaga/LinkBERT-base",
|
25 |
+
"use_ELMo": false,
|
26 |
+
"labels": {
|
27 |
+
"<PAD>": 0,
|
28 |
+
"B-<component>": 1,
|
29 |
+
"B-<environment>": 2,
|
30 |
+
"B-<implicit>": 3,
|
31 |
+
"B-<language>": 4,
|
32 |
+
"I-<component>": 5,
|
33 |
+
"I-<environment>": 6,
|
34 |
+
"I-<implicit>": 7,
|
35 |
+
"I-<language>": 8,
|
36 |
+
"O": 9
|
37 |
+
}
|
38 |
+
}
|
software-type-BERT_CRF/model_weights.hdf5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:558257a4a1ce4c7d58dcd4ef3561b27322a188fef2d485a1288d6d9c770699cd
|
3 |
+
size 433545864
|
software-type-BERT_CRF/preprocessor.json
ADDED
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"padding": true,
|
3 |
+
"return_lengths": false,
|
4 |
+
"return_word_embeddings": false,
|
5 |
+
"return_casing": false,
|
6 |
+
"return_features": false,
|
7 |
+
"return_chars": false,
|
8 |
+
"return_bert_embeddings": true,
|
9 |
+
"vocab_char": {
|
10 |
+
"<PAD>": 0,
|
11 |
+
"<UNK>": 1,
|
12 |
+
"!": 2,
|
13 |
+
"\"": 3,
|
14 |
+
"#": 4,
|
15 |
+
"$": 5,
|
16 |
+
"%": 6,
|
17 |
+
"&": 7,
|
18 |
+
"'": 8,
|
19 |
+
"(": 9,
|
20 |
+
")": 10,
|
21 |
+
"*": 11,
|
22 |
+
"+": 12,
|
23 |
+
",": 13,
|
24 |
+
"-": 14,
|
25 |
+
".": 15,
|
26 |
+
"/": 16,
|
27 |
+
"0": 17,
|
28 |
+
"1": 18,
|
29 |
+
"2": 19,
|
30 |
+
"3": 20,
|
31 |
+
"4": 21,
|
32 |
+
"5": 22,
|
33 |
+
"6": 23,
|
34 |
+
"7": 24,
|
35 |
+
"8": 25,
|
36 |
+
"9": 26,
|
37 |
+
":": 27,
|
38 |
+
";": 28,
|
39 |
+
"<": 29,
|
40 |
+
"=": 30,
|
41 |
+
">": 31,
|
42 |
+
"?": 32,
|
43 |
+
"@": 33,
|
44 |
+
"A": 34,
|
45 |
+
"B": 35,
|
46 |
+
"C": 36,
|
47 |
+
"D": 37,
|
48 |
+
"E": 38,
|
49 |
+
"F": 39,
|
50 |
+
"G": 40,
|
51 |
+
"H": 41,
|
52 |
+
"I": 42,
|
53 |
+
"J": 43,
|
54 |
+
"K": 44,
|
55 |
+
"L": 45,
|
56 |
+
"M": 46,
|
57 |
+
"N": 47,
|
58 |
+
"O": 48,
|
59 |
+
"P": 49,
|
60 |
+
"Q": 50,
|
61 |
+
"R": 51,
|
62 |
+
"S": 52,
|
63 |
+
"T": 53,
|
64 |
+
"U": 54,
|
65 |
+
"V": 55,
|
66 |
+
"W": 56,
|
67 |
+
"X": 57,
|
68 |
+
"Y": 58,
|
69 |
+
"Z": 59,
|
70 |
+
"[": 60,
|
71 |
+
"]": 61,
|
72 |
+
"^": 62,
|
73 |
+
"_": 63,
|
74 |
+
"`": 64,
|
75 |
+
"a": 65,
|
76 |
+
"b": 66,
|
77 |
+
"c": 67,
|
78 |
+
"d": 68,
|
79 |
+
"e": 69,
|
80 |
+
"f": 70,
|
81 |
+
"g": 71,
|
82 |
+
"h": 72,
|
83 |
+
"i": 73,
|
84 |
+
"j": 74,
|
85 |
+
"k": 75,
|
86 |
+
"l": 76,
|
87 |
+
"m": 77,
|
88 |
+
"n": 78,
|
89 |
+
"o": 79,
|
90 |
+
"p": 80,
|
91 |
+
"q": 81,
|
92 |
+
"r": 82,
|
93 |
+
"s": 83,
|
94 |
+
"t": 84,
|
95 |
+
"u": 85,
|
96 |
+
"v": 86,
|
97 |
+
"w": 87,
|
98 |
+
"x": 88,
|
99 |
+
"y": 89,
|
100 |
+
"z": 90,
|
101 |
+
"{": 91,
|
102 |
+
"|": 92,
|
103 |
+
"}": 93,
|
104 |
+
"~": 94,
|
105 |
+
"\u00a1": 95,
|
106 |
+
"\u00a2": 96,
|
107 |
+
"\u00a3": 97,
|
108 |
+
"\u00a7": 98,
|
109 |
+
"\u00a8": 99,
|
110 |
+
"\u00a9": 100,
|
111 |
+
"\u00ae": 101,
|
112 |
+
"\u00b0": 102,
|
113 |
+
"\u00b1": 103,
|
114 |
+
"\u00b2": 104,
|
115 |
+
"\u00b4": 105,
|
116 |
+
"\u00b5": 106,
|
117 |
+
"\u00b7": 107,
|
118 |
+
"\u00ba": 108,
|
119 |
+
"\u00bb": 109,
|
120 |
+
"\u00bc": 110,
|
121 |
+
"\u00bd": 111,
|
122 |
+
"\u00c0": 112,
|
123 |
+
"\u00c1": 113,
|
124 |
+
"\u00c2": 114,
|
125 |
+
"\u00c3": 115,
|
126 |
+
"\u00c5": 116,
|
127 |
+
"\u00c9": 117,
|
128 |
+
"\u00d2": 118,
|
129 |
+
"\u00d4": 119,
|
130 |
+
"\u00d5": 120,
|
131 |
+
"\u00d7": 121,
|
132 |
+
"\u00dc": 122,
|
133 |
+
"\u00de": 123,
|
134 |
+
"\u00df": 124,
|
135 |
+
"\u00e1": 125,
|
136 |
+
"\u00e2": 126,
|
137 |
+
"\u00e3": 127,
|
138 |
+
"\u00e4": 128,
|
139 |
+
"\u00e5": 129,
|
140 |
+
"\u00e7": 130,
|
141 |
+
"\u00e8": 131,
|
142 |
+
"\u00e9": 132,
|
143 |
+
"\u00ea": 133,
|
144 |
+
"\u00ed": 134,
|
145 |
+
"\u00f0": 135,
|
146 |
+
"\u00f3": 136,
|
147 |
+
"\u00f6": 137,
|
148 |
+
"\u00f8": 138,
|
149 |
+
"\u00fa": 139,
|
150 |
+
"\u00fc": 140,
|
151 |
+
"\u00fe": 141,
|
152 |
+
"\u0107": 142,
|
153 |
+
"\u010d": 143,
|
154 |
+
"\u0117": 144,
|
155 |
+
"\u0131": 145,
|
156 |
+
"\u0144": 146,
|
157 |
+
"\u0160": 147,
|
158 |
+
"\u0177": 148,
|
159 |
+
"\u0192": 149,
|
160 |
+
"\u02c2": 150,
|
161 |
+
"\u02da": 151,
|
162 |
+
"\u02dc": 152,
|
163 |
+
"\u0357": 153,
|
164 |
+
"\u0358": 154,
|
165 |
+
"\u0374": 155,
|
166 |
+
"\u0394": 156,
|
167 |
+
"\u0397": 157,
|
168 |
+
"\u03a9": 158,
|
169 |
+
"\u03b1": 159,
|
170 |
+
"\u03b2": 160,
|
171 |
+
"\u03b3": 161,
|
172 |
+
"\u03b4": 162,
|
173 |
+
"\u03b5": 163,
|
174 |
+
"\u03b6": 164,
|
175 |
+
"\u03b7": 165,
|
176 |
+
"\u03b8": 166,
|
177 |
+
"\u03ba": 167,
|
178 |
+
"\u03bb": 168,
|
179 |
+
"\u03bc": 169,
|
180 |
+
"\u03bd": 170,
|
181 |
+
"\u03c0": 171,
|
182 |
+
"\u03c1": 172,
|
183 |
+
"\u03c3": 173,
|
184 |
+
"\u03c4": 174,
|
185 |
+
"\u03c5": 175,
|
186 |
+
"\u03c6": 176,
|
187 |
+
"\u03c7": 177,
|
188 |
+
"\u03c8": 178,
|
189 |
+
"\u03c9": 179,
|
190 |
+
"\u03d2": 180,
|
191 |
+
"\u03d5": 181,
|
192 |
+
"\u03e9": 182,
|
193 |
+
"\u03ea": 183,
|
194 |
+
"\u03eb": 184,
|
195 |
+
"\u03ed": 185,
|
196 |
+
"\u03ee": 186,
|
197 |
+
"\u03f3": 187,
|
198 |
+
"\u03fd": 188,
|
199 |
+
"\u03fe": 189,
|
200 |
+
"\u0408": 190,
|
201 |
+
"\u0412": 191,
|
202 |
+
"\u0545": 192,
|
203 |
+
"\u0546": 193,
|
204 |
+
"\u0609": 194,
|
205 |
+
"\u060a": 195,
|
206 |
+
"\u060e": 196,
|
207 |
+
"\u1e91": 197,
|
208 |
+
"\u2020": 198,
|
209 |
+
"\u2021": 199,
|
210 |
+
"\u2022": 200,
|
211 |
+
"\u2026": 201,
|
212 |
+
"\u2032": 202,
|
213 |
+
"\u2033": 203,
|
214 |
+
"\u2044": 204,
|
215 |
+
"\u20ac": 205,
|
216 |
+
"\u2103": 206,
|
217 |
+
"\u2122": 207,
|
218 |
+
"\u2150": 208,
|
219 |
+
"\u2192": 209,
|
220 |
+
"\u2206": 210,
|
221 |
+
"\u2208": 211,
|
222 |
+
"\u2212": 212,
|
223 |
+
"\u2215": 213,
|
224 |
+
"\u221e": 214,
|
225 |
+
"\u223c": 215,
|
226 |
+
"\u2248": 216,
|
227 |
+
"\u2260": 217,
|
228 |
+
"\u2264": 218,
|
229 |
+
"\u2265": 219,
|
230 |
+
"\u22c5": 220,
|
231 |
+
"\u232c": 221,
|
232 |
+
"\u233a": 222,
|
233 |
+
"\u233d": 223,
|
234 |
+
"\u2423": 224,
|
235 |
+
"\u2424": 225,
|
236 |
+
"\u2425": 226,
|
237 |
+
"\u24c7": 227,
|
238 |
+
"\u2500": 228,
|
239 |
+
"\u2502": 229,
|
240 |
+
"\u25b3": 230,
|
241 |
+
"\u25b8": 231,
|
242 |
+
"\u2a7e": 232,
|
243 |
+
"\ue024": 233,
|
244 |
+
"\ue02c": 234,
|
245 |
+
"\ue02e": 235,
|
246 |
+
"\ue032": 236,
|
247 |
+
"\ue039": 237,
|
248 |
+
"\ue061": 238,
|
249 |
+
"\ue062": 239,
|
250 |
+
"\ue067": 240,
|
251 |
+
"\ue06d": 241,
|
252 |
+
"\ue074": 242,
|
253 |
+
"\ue07a": 243,
|
254 |
+
"\uf062": 244,
|
255 |
+
"\uf06d": 245,
|
256 |
+
"\uf077": 246,
|
257 |
+
"\uf0a3": 247,
|
258 |
+
"\uf0b0": 248,
|
259 |
+
"\uf0b1": 249,
|
260 |
+
"\uf0b4": 250,
|
261 |
+
"\uf0b9": 251,
|
262 |
+
"\uf643": 252,
|
263 |
+
"\uf644": 253,
|
264 |
+
"\uf645": 254,
|
265 |
+
"\uf64b": 255,
|
266 |
+
"\uf64c": 256,
|
267 |
+
"\uf76d": 257,
|
268 |
+
"\uff1a": 258,
|
269 |
+
"\uff1c": 259,
|
270 |
+
"\uff1e": 260,
|
271 |
+
"\ufffd": 261,
|
272 |
+
"\ud835\udc56": 262,
|
273 |
+
"\ud835\udc57": 263,
|
274 |
+
"\ud835\udc61": 264,
|
275 |
+
"\ud835\udefc": 265,
|
276 |
+
"\ud835\udeff": 266
|
277 |
+
},
|
278 |
+
"vocab_tag": {
|
279 |
+
"<PAD>": 0,
|
280 |
+
"B-<component>": 1,
|
281 |
+
"B-<environment>": 2,
|
282 |
+
"B-<implicit>": 3,
|
283 |
+
"B-<language>": 4,
|
284 |
+
"I-<component>": 5,
|
285 |
+
"I-<environment>": 6,
|
286 |
+
"I-<implicit>": 7,
|
287 |
+
"I-<language>": 8,
|
288 |
+
"O": 9
|
289 |
+
},
|
290 |
+
"vocab_case": [
|
291 |
+
"<PAD>",
|
292 |
+
"numeric",
|
293 |
+
"allLower",
|
294 |
+
"allUpper",
|
295 |
+
"initialUpper",
|
296 |
+
"other",
|
297 |
+
"mainly_numeric",
|
298 |
+
"contains_digit"
|
299 |
+
],
|
300 |
+
"max_char_length": 30,
|
301 |
+
"feature_preprocessor": null,
|
302 |
+
"indice_tag": {
|
303 |
+
"0": "<PAD>",
|
304 |
+
"1": "B-<component>",
|
305 |
+
"2": "B-<environment>",
|
306 |
+
"3": "B-<implicit>",
|
307 |
+
"4": "B-<language>",
|
308 |
+
"5": "I-<component>",
|
309 |
+
"6": "I-<environment>",
|
310 |
+
"7": "I-<implicit>",
|
311 |
+
"8": "I-<language>",
|
312 |
+
"9": "O"
|
313 |
+
}
|
314 |
+
}
|
software-type-BERT_CRF/transformer-config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "michiyasunaga/LinkBERT-base",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"transformers_version": "4.15.0",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 28996
|
25 |
+
}
|
software-type-BERT_CRF/transformer-tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
software-type-BERT_CRF/transformer-tokenizer/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
software-type-BERT_CRF/transformer-tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "michiyasunaga/LinkBERT-base", "add_special_tokens": true, "max_length": 512, "add_prefix_space": true, "tokenizer_class": "BertTokenizer"}
|
software-type-BERT_CRF/transformer-tokenizer/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|