Upload folder using huggingface_hub

#1
by lfoppiano - opened
Files changed (18) hide show
  1. grobid-reference-segmenter-BidLSTM_CRF_FEATURES-dev/config.json +156 -0
  2. grobid-reference-segmenter-BidLSTM_CRF_FEATURES-dev/model.safetensors +3 -0
  3. grobid-reference-segmenter-BidLSTM_CRF_FEATURES-dev/preprocessor.json +343 -0
  4. grobid-reference-segmenter-BidLSTM_CRF_FEATURES-glove_840B/config.json +5 -1
  5. grobid-reference-segmenter-BidLSTM_CRF_FEATURES-glove_840B/model.safetensors +3 -0
  6. grobid-reference-segmenter-BidLSTM_CRF_FEATURES-glove_840B/preprocessor.json +3 -1
  7. grobid-reference-segmenter-BidLSTM_CRF_FEATURES-no_embeddings/config.json +5 -1
  8. grobid-reference-segmenter-BidLSTM_CRF_FEATURES-no_embeddings/model.safetensors +3 -0
  9. grobid-reference-segmenter-BidLSTM_CRF_FEATURES-no_embeddings/preprocessor.json +3 -1
  10. grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-dev/config.json +156 -0
  11. grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-dev/model.safetensors +3 -0
  12. grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-dev/preprocessor.json +343 -0
  13. grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-glove_840B/config.json +5 -1
  14. grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-glove_840B/model.safetensors +3 -0
  15. grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-glove_840B/preprocessor.json +3 -1
  16. grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-no_embeddings/config.json +5 -1
  17. grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-no_embeddings/model.safetensors +3 -0
  18. grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-no_embeddings/preprocessor.json +3 -1
grobid-reference-segmenter-BidLSTM_CRF_FEATURES-dev/config.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "grobid-reference-segmenter-BidLSTM_CRF_FEATURES-dev",
3
+ "architecture": "BidLSTM_CRF_FEATURES",
4
+ "embeddings_name": "glove-840B",
5
+ "char_vocab_size": 172,
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": [
12
+ 9,
13
+ 10,
14
+ 11,
15
+ 12,
16
+ 13,
17
+ 14,
18
+ 15,
19
+ 16,
20
+ 17,
21
+ 18,
22
+ 19,
23
+ 20,
24
+ 21,
25
+ 22,
26
+ 23,
27
+ 24,
28
+ 25,
29
+ 26
30
+ ],
31
+ "features_embedding_size": 4,
32
+ "features_lstm_units": 4,
33
+ "continuous_features_indices": null,
34
+ "max_sequence_length": 3000,
35
+ "word_embedding_size": 300,
36
+ "num_word_lstm_units": 100,
37
+ "case_embedding_size": 5,
38
+ "dropout": 0.5,
39
+ "recurrent_dropout": 0.5,
40
+ "use_crf": false,
41
+ "use_chain_crf": false,
42
+ "fold_number": 1,
43
+ "batch_size": 5,
44
+ "transformer_name": null,
45
+ "window_stride": null,
46
+ "text_features_indices": null,
47
+ "contextual_embedding_settings": null,
48
+ "features_map_to_index": {
49
+ "9": {
50
+ "LINEEND": 1,
51
+ "LINEIN": 2,
52
+ "LINESTART": 3
53
+ },
54
+ "10": {
55
+ "ALIGNEDLEFT": 13,
56
+ "LINEINDENT": 14
57
+ },
58
+ "11": {
59
+ "ALLCAP": 25,
60
+ "INITCAP": 26,
61
+ "NOCAPS": 27
62
+ },
63
+ "12": {
64
+ "ALLDIGIT": 37,
65
+ "CONTAINSDIGITS": 38,
66
+ "NODIGIT": 39
67
+ },
68
+ "13": {
69
+ "0": 49,
70
+ "1": 50
71
+ },
72
+ "14": {
73
+ "0": 61,
74
+ "1": 62
75
+ },
76
+ "15": {
77
+ "0": 73,
78
+ "1": 74
79
+ },
80
+ "16": {
81
+ "0": 85
82
+ },
83
+ "17": {
84
+ "0": 97
85
+ },
86
+ "18": {
87
+ "0": 109,
88
+ "1": 110
89
+ },
90
+ "19": {
91
+ "0": 121,
92
+ "1": 122
93
+ },
94
+ "20": {
95
+ "0": 133,
96
+ "1": 134
97
+ },
98
+ "21": {
99
+ "COMMA": 145,
100
+ "DOT": 146,
101
+ "ENDBRACKET": 147,
102
+ "HYPHEN": 148,
103
+ "NOPUNCT": 149,
104
+ "OPENBRACKET": 150,
105
+ "PUNCT": 151,
106
+ "QUOTE": 152
107
+ },
108
+ "22": {
109
+ "0": 157,
110
+ "1": 158,
111
+ "10": 159,
112
+ "2": 160,
113
+ "3": 161,
114
+ "4": 162,
115
+ "5": 163,
116
+ "6": 164,
117
+ "7": 165,
118
+ "8": 166,
119
+ "9": 167
120
+ },
121
+ "23": {
122
+ "0": 169,
123
+ "1": 170,
124
+ "10": 171,
125
+ "2": 172,
126
+ "3": 173,
127
+ "4": 174,
128
+ "5": 175,
129
+ "6": 176,
130
+ "7": 177,
131
+ "8": 178,
132
+ "9": 179
133
+ },
134
+ "24": {
135
+ "BLOCKEND": 181,
136
+ "BLOCKIN": 182,
137
+ "BLOCKSTART": 183
138
+ },
139
+ "25": {
140
+ "1": 193,
141
+ "10": 194,
142
+ "2": 195,
143
+ "3": 196,
144
+ "4": 197,
145
+ "5": 198,
146
+ "6": 199,
147
+ "7": 200,
148
+ "8": 201,
149
+ "9": 202,
150
+ "no": 203
151
+ },
152
+ "26": {
153
+ "0": 205
154
+ }
155
+ }
156
+ }
grobid-reference-segmenter-BidLSTM_CRF_FEATURES-dev/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca1a323fd8ac64040c764765d2261473fc0baff120c3cf4f14cc375551b22b0b
3
+ size 1621648
grobid-reference-segmenter-BidLSTM_CRF_FEATURES-dev/preprocessor.json ADDED
@@ -0,0 +1,343 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "padding": true,
3
+ "return_lengths": false,
4
+ "return_word_embeddings": false,
5
+ "return_casing": false,
6
+ "return_features": true,
7
+ "return_chars": false,
8
+ "return_bert_embeddings": false,
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
+ "0": 16,
27
+ "1": 17,
28
+ "2": 18,
29
+ "3": 19,
30
+ "4": 20,
31
+ "5": 21,
32
+ "6": 22,
33
+ "7": 23,
34
+ "8": 24,
35
+ "9": 25,
36
+ ":": 26,
37
+ ";": 27,
38
+ "<": 28,
39
+ "=": 29,
40
+ ">": 30,
41
+ "?": 31,
42
+ "@": 32,
43
+ "A": 33,
44
+ "B": 34,
45
+ "C": 35,
46
+ "D": 36,
47
+ "E": 37,
48
+ "F": 38,
49
+ "G": 39,
50
+ "H": 40,
51
+ "I": 41,
52
+ "J": 42,
53
+ "K": 43,
54
+ "L": 44,
55
+ "M": 45,
56
+ "N": 46,
57
+ "O": 47,
58
+ "P": 48,
59
+ "Q": 49,
60
+ "R": 50,
61
+ "S": 51,
62
+ "T": 52,
63
+ "U": 53,
64
+ "V": 54,
65
+ "W": 55,
66
+ "X": 56,
67
+ "Y": 57,
68
+ "Z": 58,
69
+ "[": 59,
70
+ "]": 60,
71
+ "_": 61,
72
+ "`": 62,
73
+ "a": 63,
74
+ "b": 64,
75
+ "c": 65,
76
+ "d": 66,
77
+ "e": 67,
78
+ "f": 68,
79
+ "g": 69,
80
+ "h": 70,
81
+ "i": 71,
82
+ "j": 72,
83
+ "k": 73,
84
+ "l": 74,
85
+ "m": 75,
86
+ "n": 76,
87
+ "o": 77,
88
+ "p": 78,
89
+ "q": 79,
90
+ "r": 80,
91
+ "s": 81,
92
+ "t": 82,
93
+ "u": 83,
94
+ "v": 84,
95
+ "w": 85,
96
+ "x": 86,
97
+ "y": 87,
98
+ "z": 88,
99
+ "{": 89,
100
+ "|": 90,
101
+ "}": 91,
102
+ "~": 92,
103
+ "\u00a8": 93,
104
+ "\u00b1": 94,
105
+ "\u00b4": 95,
106
+ "\u00b8": 96,
107
+ "\u00c1": 97,
108
+ "\u00c3": 98,
109
+ "\u00c9": 99,
110
+ "\u00d6": 100,
111
+ "\u00d7": 101,
112
+ "\u00d8": 102,
113
+ "\u00df": 103,
114
+ "\u00e0": 104,
115
+ "\u00e1": 105,
116
+ "\u00e2": 106,
117
+ "\u00e3": 107,
118
+ "\u00e4": 108,
119
+ "\u00e5": 109,
120
+ "\u00e7": 110,
121
+ "\u00e8": 111,
122
+ "\u00e9": 112,
123
+ "\u00ea": 113,
124
+ "\u00ec": 114,
125
+ "\u00ed": 115,
126
+ "\u00ee": 116,
127
+ "\u00f1": 117,
128
+ "\u00f2": 118,
129
+ "\u00f3": 119,
130
+ "\u00f4": 120,
131
+ "\u00f6": 121,
132
+ "\u00f8": 122,
133
+ "\u00fa": 123,
134
+ "\u00fc": 124,
135
+ "\u00fd": 125,
136
+ "\u00ff": 126,
137
+ "\u0102": 127,
138
+ "\u0107": 128,
139
+ "\u010d": 129,
140
+ "\u011f": 130,
141
+ "\u0130": 131,
142
+ "\u0131": 132,
143
+ "\u0132": 133,
144
+ "\u013e": 134,
145
+ "\u0142": 135,
146
+ "\u0144": 136,
147
+ "\u0148": 137,
148
+ "\u0159": 138,
149
+ "\u015f": 139,
150
+ "\u0161": 140,
151
+ "\u016f": 141,
152
+ "\u0179": 142,
153
+ "\u017e": 143,
154
+ "\u02c6": 144,
155
+ "\u02dc": 145,
156
+ "\u039b": 146,
157
+ "\u03b2": 147,
158
+ "\u03b3": 148,
159
+ "\u03c0": 149,
160
+ "\u03c3": 150,
161
+ "\u03c6": 151,
162
+ "\u03e9": 152,
163
+ "\u03ea": 153,
164
+ "\u03eb": 154,
165
+ "\u03f3": 155,
166
+ "\u0408": 156,
167
+ "\u2013": 157,
168
+ "\u2014": 158,
169
+ "\u2020": 159,
170
+ "\u2022": 160,
171
+ "\u2026": 161,
172
+ "\u2192": 162,
173
+ "\u2206": 163,
174
+ "\u2212": 164,
175
+ "\u221e": 165,
176
+ "\u223c": 166,
177
+ "\u2245": 167,
178
+ "\u2423": 168,
179
+ "\u2424": 169,
180
+ "\uf044": 170,
181
+ "\uf062": 171
182
+ },
183
+ "vocab_tag": {
184
+ "<PAD>": 0,
185
+ "B-<label>": 1,
186
+ "B-<reference>": 2,
187
+ "I-<label>": 3,
188
+ "I-<reference>": 4,
189
+ "O": 5
190
+ },
191
+ "vocab_case": [
192
+ "<PAD>",
193
+ "numeric",
194
+ "allLower",
195
+ "allUpper",
196
+ "initialUpper",
197
+ "other",
198
+ "mainly_numeric",
199
+ "contains_digit"
200
+ ],
201
+ "max_char_length": 30,
202
+ "feature_preprocessor": {
203
+ "features_vocabulary_size": 12,
204
+ "features_indices": [
205
+ 9,
206
+ 10,
207
+ 11,
208
+ 12,
209
+ 13,
210
+ 14,
211
+ 15,
212
+ 16,
213
+ 17,
214
+ 18,
215
+ 19,
216
+ 20,
217
+ 21,
218
+ 22,
219
+ 23,
220
+ 24,
221
+ 25,
222
+ 26
223
+ ],
224
+ "features_map_to_index": {
225
+ "9": {
226
+ "LINEEND": 1,
227
+ "LINEIN": 2,
228
+ "LINESTART": 3
229
+ },
230
+ "10": {
231
+ "ALIGNEDLEFT": 13,
232
+ "LINEINDENT": 14
233
+ },
234
+ "11": {
235
+ "ALLCAP": 25,
236
+ "INITCAP": 26,
237
+ "NOCAPS": 27
238
+ },
239
+ "12": {
240
+ "ALLDIGIT": 37,
241
+ "CONTAINSDIGITS": 38,
242
+ "NODIGIT": 39
243
+ },
244
+ "13": {
245
+ "0": 49,
246
+ "1": 50
247
+ },
248
+ "14": {
249
+ "0": 61,
250
+ "1": 62
251
+ },
252
+ "15": {
253
+ "0": 73,
254
+ "1": 74
255
+ },
256
+ "16": {
257
+ "0": 85
258
+ },
259
+ "17": {
260
+ "0": 97
261
+ },
262
+ "18": {
263
+ "0": 109,
264
+ "1": 110
265
+ },
266
+ "19": {
267
+ "0": 121,
268
+ "1": 122
269
+ },
270
+ "20": {
271
+ "0": 133,
272
+ "1": 134
273
+ },
274
+ "21": {
275
+ "COMMA": 145,
276
+ "DOT": 146,
277
+ "ENDBRACKET": 147,
278
+ "HYPHEN": 148,
279
+ "NOPUNCT": 149,
280
+ "OPENBRACKET": 150,
281
+ "PUNCT": 151,
282
+ "QUOTE": 152
283
+ },
284
+ "22": {
285
+ "0": 157,
286
+ "1": 158,
287
+ "10": 159,
288
+ "2": 160,
289
+ "3": 161,
290
+ "4": 162,
291
+ "5": 163,
292
+ "6": 164,
293
+ "7": 165,
294
+ "8": 166,
295
+ "9": 167
296
+ },
297
+ "23": {
298
+ "0": 169,
299
+ "1": 170,
300
+ "10": 171,
301
+ "2": 172,
302
+ "3": 173,
303
+ "4": 174,
304
+ "5": 175,
305
+ "6": 176,
306
+ "7": 177,
307
+ "8": 178,
308
+ "9": 179
309
+ },
310
+ "24": {
311
+ "BLOCKEND": 181,
312
+ "BLOCKIN": 182,
313
+ "BLOCKSTART": 183
314
+ },
315
+ "25": {
316
+ "1": 193,
317
+ "10": 194,
318
+ "2": 195,
319
+ "3": 196,
320
+ "4": 197,
321
+ "5": 198,
322
+ "6": 199,
323
+ "7": 200,
324
+ "8": 201,
325
+ "9": 202,
326
+ "no": 203
327
+ },
328
+ "26": {
329
+ "0": 205
330
+ }
331
+ },
332
+ "continuous_features_indices": [],
333
+ "continuous_features_ranges": []
334
+ },
335
+ "indice_tag": {
336
+ "0": "<PAD>",
337
+ "1": "B-<label>",
338
+ "2": "B-<reference>",
339
+ "3": "I-<label>",
340
+ "4": "I-<reference>",
341
+ "5": "O"
342
+ }
343
+ }
grobid-reference-segmenter-BidLSTM_CRF_FEATURES-glove_840B/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "model_name": "grobid-reference-segmenter-BidLSTM_CRF_FEATURES",
3
  "architecture": "BidLSTM_CRF_FEATURES",
4
  "embeddings_name": "glove-840B",
5
  "char_vocab_size": 172,
@@ -30,6 +30,7 @@
30
  ],
31
  "features_embedding_size": 4,
32
  "features_lstm_units": 4,
 
33
  "max_sequence_length": 3000,
34
  "word_embedding_size": 300,
35
  "num_word_lstm_units": 100,
@@ -41,6 +42,9 @@
41
  "fold_number": 1,
42
  "batch_size": 5,
43
  "transformer_name": null,
 
 
 
44
  "features_map_to_index": {
45
  "9": {
46
  "LINEEND": 1,
 
1
  {
2
+ "model_name": "grobid-reference-segmenter-BidLSTM_CRF_FEATURES-gloves_840B",
3
  "architecture": "BidLSTM_CRF_FEATURES",
4
  "embeddings_name": "glove-840B",
5
  "char_vocab_size": 172,
 
30
  ],
31
  "features_embedding_size": 4,
32
  "features_lstm_units": 4,
33
+ "continuous_features_indices": null,
34
  "max_sequence_length": 3000,
35
  "word_embedding_size": 300,
36
  "num_word_lstm_units": 100,
 
42
  "fold_number": 1,
43
  "batch_size": 5,
44
  "transformer_name": null,
45
+ "window_stride": null,
46
+ "text_features_indices": null,
47
+ "contextual_embedding_settings": null,
48
  "features_map_to_index": {
49
  "9": {
50
  "LINEEND": 1,
grobid-reference-segmenter-BidLSTM_CRF_FEATURES-glove_840B/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ab620cc656d203bdadcc2fd4161d0d53973a87120b9076b4a363d075fc2ef3
3
+ size 1621648
grobid-reference-segmenter-BidLSTM_CRF_FEATURES-glove_840B/preprocessor.json CHANGED
@@ -328,7 +328,9 @@
328
  "26": {
329
  "0": 205
330
  }
331
- }
 
 
332
  },
333
  "indice_tag": {
334
  "0": "<PAD>",
 
328
  "26": {
329
  "0": 205
330
  }
331
+ },
332
+ "continuous_features_indices": [],
333
+ "continuous_features_ranges": []
334
  },
335
  "indice_tag": {
336
  "0": "<PAD>",
grobid-reference-segmenter-BidLSTM_CRF_FEATURES-no_embeddings/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "model_name": "grobid-reference-segmenter-BidLSTM_CRF_FEATURES",
3
  "architecture": "BidLSTM_CRF_FEATURES",
4
  "embeddings_name": null,
5
  "char_vocab_size": 172,
@@ -30,6 +30,7 @@
30
  ],
31
  "features_embedding_size": 4,
32
  "features_lstm_units": 4,
 
33
  "max_sequence_length": 3000,
34
  "word_embedding_size": 0,
35
  "num_word_lstm_units": 100,
@@ -41,6 +42,9 @@
41
  "fold_number": 1,
42
  "batch_size": 5,
43
  "transformer_name": null,
 
 
 
44
  "features_map_to_index": {
45
  "9": {
46
  "LINEEND": 1,
 
1
  {
2
+ "model_name": "grobid-reference-segmenter-BidLSTM_CRF_FEATURES-no_embeddings",
3
  "architecture": "BidLSTM_CRF_FEATURES",
4
  "embeddings_name": null,
5
  "char_vocab_size": 172,
 
30
  ],
31
  "features_embedding_size": 4,
32
  "features_lstm_units": 4,
33
+ "continuous_features_indices": null,
34
  "max_sequence_length": 3000,
35
  "word_embedding_size": 0,
36
  "num_word_lstm_units": 100,
 
42
  "fold_number": 1,
43
  "batch_size": 5,
44
  "transformer_name": null,
45
+ "window_stride": null,
46
+ "text_features_indices": null,
47
+ "contextual_embedding_settings": null,
48
  "features_map_to_index": {
49
  "9": {
50
  "LINEEND": 1,
grobid-reference-segmenter-BidLSTM_CRF_FEATURES-no_embeddings/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acdd960920b2ba37a0a889ec89e226e0bd6060e5e56ac61c31de5ea30ac4f72d
3
+ size 661592
grobid-reference-segmenter-BidLSTM_CRF_FEATURES-no_embeddings/preprocessor.json CHANGED
@@ -328,7 +328,9 @@
328
  "26": {
329
  "0": 205
330
  }
331
- }
 
 
332
  },
333
  "indice_tag": {
334
  "0": "<PAD>",
 
328
  "26": {
329
  "0": 205
330
  }
331
+ },
332
+ "continuous_features_indices": [],
333
+ "continuous_features_ranges": []
334
  },
335
  "indice_tag": {
336
  "0": "<PAD>",
grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-dev/config.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-dev",
3
+ "architecture": "BidLSTM_ChainCRF_FEATURES",
4
+ "embeddings_name": "glove-840B",
5
+ "char_vocab_size": 172,
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": [
12
+ 9,
13
+ 10,
14
+ 11,
15
+ 12,
16
+ 13,
17
+ 14,
18
+ 15,
19
+ 16,
20
+ 17,
21
+ 18,
22
+ 19,
23
+ 20,
24
+ 21,
25
+ 22,
26
+ 23,
27
+ 24,
28
+ 25,
29
+ 26
30
+ ],
31
+ "features_embedding_size": 4,
32
+ "features_lstm_units": 4,
33
+ "continuous_features_indices": null,
34
+ "max_sequence_length": 3000,
35
+ "word_embedding_size": 300,
36
+ "num_word_lstm_units": 100,
37
+ "case_embedding_size": 5,
38
+ "dropout": 0.5,
39
+ "recurrent_dropout": 0.5,
40
+ "use_crf": false,
41
+ "use_chain_crf": false,
42
+ "fold_number": 1,
43
+ "batch_size": 5,
44
+ "transformer_name": null,
45
+ "window_stride": null,
46
+ "text_features_indices": null,
47
+ "contextual_embedding_settings": null,
48
+ "features_map_to_index": {
49
+ "9": {
50
+ "LINEEND": 1,
51
+ "LINEIN": 2,
52
+ "LINESTART": 3
53
+ },
54
+ "10": {
55
+ "ALIGNEDLEFT": 13,
56
+ "LINEINDENT": 14
57
+ },
58
+ "11": {
59
+ "ALLCAP": 25,
60
+ "INITCAP": 26,
61
+ "NOCAPS": 27
62
+ },
63
+ "12": {
64
+ "ALLDIGIT": 37,
65
+ "CONTAINSDIGITS": 38,
66
+ "NODIGIT": 39
67
+ },
68
+ "13": {
69
+ "0": 49,
70
+ "1": 50
71
+ },
72
+ "14": {
73
+ "0": 61,
74
+ "1": 62
75
+ },
76
+ "15": {
77
+ "0": 73,
78
+ "1": 74
79
+ },
80
+ "16": {
81
+ "0": 85
82
+ },
83
+ "17": {
84
+ "0": 97
85
+ },
86
+ "18": {
87
+ "0": 109,
88
+ "1": 110
89
+ },
90
+ "19": {
91
+ "0": 121,
92
+ "1": 122
93
+ },
94
+ "20": {
95
+ "0": 133,
96
+ "1": 134
97
+ },
98
+ "21": {
99
+ "COMMA": 145,
100
+ "DOT": 146,
101
+ "ENDBRACKET": 147,
102
+ "HYPHEN": 148,
103
+ "NOPUNCT": 149,
104
+ "OPENBRACKET": 150,
105
+ "PUNCT": 151,
106
+ "QUOTE": 152
107
+ },
108
+ "22": {
109
+ "0": 157,
110
+ "1": 158,
111
+ "10": 159,
112
+ "2": 160,
113
+ "3": 161,
114
+ "4": 162,
115
+ "5": 163,
116
+ "6": 164,
117
+ "7": 165,
118
+ "8": 166,
119
+ "9": 167
120
+ },
121
+ "23": {
122
+ "0": 169,
123
+ "1": 170,
124
+ "10": 171,
125
+ "2": 172,
126
+ "3": 173,
127
+ "4": 174,
128
+ "5": 175,
129
+ "6": 176,
130
+ "7": 177,
131
+ "8": 178,
132
+ "9": 179
133
+ },
134
+ "24": {
135
+ "BLOCKEND": 181,
136
+ "BLOCKIN": 182,
137
+ "BLOCKSTART": 183
138
+ },
139
+ "25": {
140
+ "1": 193,
141
+ "10": 194,
142
+ "2": 195,
143
+ "3": 196,
144
+ "4": 197,
145
+ "5": 198,
146
+ "6": 199,
147
+ "7": 200,
148
+ "8": 201,
149
+ "9": 202,
150
+ "no": 203
151
+ },
152
+ "26": {
153
+ "0": 205
154
+ }
155
+ }
156
+ }
grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-dev/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0db615b0c3c0ff3bc382bce4cfade3a10b4d0962a921ba0119a01263eae2f6f
3
+ size 1621608
grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-dev/preprocessor.json ADDED
@@ -0,0 +1,343 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "padding": true,
3
+ "return_lengths": false,
4
+ "return_word_embeddings": false,
5
+ "return_casing": false,
6
+ "return_features": true,
7
+ "return_chars": false,
8
+ "return_bert_embeddings": false,
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
+ "0": 16,
27
+ "1": 17,
28
+ "2": 18,
29
+ "3": 19,
30
+ "4": 20,
31
+ "5": 21,
32
+ "6": 22,
33
+ "7": 23,
34
+ "8": 24,
35
+ "9": 25,
36
+ ":": 26,
37
+ ";": 27,
38
+ "<": 28,
39
+ "=": 29,
40
+ ">": 30,
41
+ "?": 31,
42
+ "@": 32,
43
+ "A": 33,
44
+ "B": 34,
45
+ "C": 35,
46
+ "D": 36,
47
+ "E": 37,
48
+ "F": 38,
49
+ "G": 39,
50
+ "H": 40,
51
+ "I": 41,
52
+ "J": 42,
53
+ "K": 43,
54
+ "L": 44,
55
+ "M": 45,
56
+ "N": 46,
57
+ "O": 47,
58
+ "P": 48,
59
+ "Q": 49,
60
+ "R": 50,
61
+ "S": 51,
62
+ "T": 52,
63
+ "U": 53,
64
+ "V": 54,
65
+ "W": 55,
66
+ "X": 56,
67
+ "Y": 57,
68
+ "Z": 58,
69
+ "[": 59,
70
+ "]": 60,
71
+ "_": 61,
72
+ "`": 62,
73
+ "a": 63,
74
+ "b": 64,
75
+ "c": 65,
76
+ "d": 66,
77
+ "e": 67,
78
+ "f": 68,
79
+ "g": 69,
80
+ "h": 70,
81
+ "i": 71,
82
+ "j": 72,
83
+ "k": 73,
84
+ "l": 74,
85
+ "m": 75,
86
+ "n": 76,
87
+ "o": 77,
88
+ "p": 78,
89
+ "q": 79,
90
+ "r": 80,
91
+ "s": 81,
92
+ "t": 82,
93
+ "u": 83,
94
+ "v": 84,
95
+ "w": 85,
96
+ "x": 86,
97
+ "y": 87,
98
+ "z": 88,
99
+ "{": 89,
100
+ "|": 90,
101
+ "}": 91,
102
+ "~": 92,
103
+ "\u00a8": 93,
104
+ "\u00b1": 94,
105
+ "\u00b4": 95,
106
+ "\u00b8": 96,
107
+ "\u00c1": 97,
108
+ "\u00c3": 98,
109
+ "\u00c9": 99,
110
+ "\u00d6": 100,
111
+ "\u00d7": 101,
112
+ "\u00d8": 102,
113
+ "\u00df": 103,
114
+ "\u00e0": 104,
115
+ "\u00e1": 105,
116
+ "\u00e2": 106,
117
+ "\u00e3": 107,
118
+ "\u00e4": 108,
119
+ "\u00e5": 109,
120
+ "\u00e7": 110,
121
+ "\u00e8": 111,
122
+ "\u00e9": 112,
123
+ "\u00ea": 113,
124
+ "\u00ec": 114,
125
+ "\u00ed": 115,
126
+ "\u00ee": 116,
127
+ "\u00f1": 117,
128
+ "\u00f2": 118,
129
+ "\u00f3": 119,
130
+ "\u00f4": 120,
131
+ "\u00f6": 121,
132
+ "\u00f8": 122,
133
+ "\u00fa": 123,
134
+ "\u00fc": 124,
135
+ "\u00fd": 125,
136
+ "\u00ff": 126,
137
+ "\u0102": 127,
138
+ "\u0107": 128,
139
+ "\u010d": 129,
140
+ "\u011f": 130,
141
+ "\u0130": 131,
142
+ "\u0131": 132,
143
+ "\u0132": 133,
144
+ "\u013e": 134,
145
+ "\u0142": 135,
146
+ "\u0144": 136,
147
+ "\u0148": 137,
148
+ "\u0159": 138,
149
+ "\u015f": 139,
150
+ "\u0161": 140,
151
+ "\u016f": 141,
152
+ "\u0179": 142,
153
+ "\u017e": 143,
154
+ "\u02c6": 144,
155
+ "\u02dc": 145,
156
+ "\u039b": 146,
157
+ "\u03b2": 147,
158
+ "\u03b3": 148,
159
+ "\u03c0": 149,
160
+ "\u03c3": 150,
161
+ "\u03c6": 151,
162
+ "\u03e9": 152,
163
+ "\u03ea": 153,
164
+ "\u03eb": 154,
165
+ "\u03f3": 155,
166
+ "\u0408": 156,
167
+ "\u2013": 157,
168
+ "\u2014": 158,
169
+ "\u2020": 159,
170
+ "\u2022": 160,
171
+ "\u2026": 161,
172
+ "\u2192": 162,
173
+ "\u2206": 163,
174
+ "\u2212": 164,
175
+ "\u221e": 165,
176
+ "\u223c": 166,
177
+ "\u2245": 167,
178
+ "\u2423": 168,
179
+ "\u2424": 169,
180
+ "\uf044": 170,
181
+ "\uf062": 171
182
+ },
183
+ "vocab_tag": {
184
+ "<PAD>": 0,
185
+ "B-<label>": 1,
186
+ "B-<reference>": 2,
187
+ "I-<label>": 3,
188
+ "I-<reference>": 4,
189
+ "O": 5
190
+ },
191
+ "vocab_case": [
192
+ "<PAD>",
193
+ "numeric",
194
+ "allLower",
195
+ "allUpper",
196
+ "initialUpper",
197
+ "other",
198
+ "mainly_numeric",
199
+ "contains_digit"
200
+ ],
201
+ "max_char_length": 30,
202
+ "feature_preprocessor": {
203
+ "features_vocabulary_size": 12,
204
+ "features_indices": [
205
+ 9,
206
+ 10,
207
+ 11,
208
+ 12,
209
+ 13,
210
+ 14,
211
+ 15,
212
+ 16,
213
+ 17,
214
+ 18,
215
+ 19,
216
+ 20,
217
+ 21,
218
+ 22,
219
+ 23,
220
+ 24,
221
+ 25,
222
+ 26
223
+ ],
224
+ "features_map_to_index": {
225
+ "9": {
226
+ "LINEEND": 1,
227
+ "LINEIN": 2,
228
+ "LINESTART": 3
229
+ },
230
+ "10": {
231
+ "ALIGNEDLEFT": 13,
232
+ "LINEINDENT": 14
233
+ },
234
+ "11": {
235
+ "ALLCAP": 25,
236
+ "INITCAP": 26,
237
+ "NOCAPS": 27
238
+ },
239
+ "12": {
240
+ "ALLDIGIT": 37,
241
+ "CONTAINSDIGITS": 38,
242
+ "NODIGIT": 39
243
+ },
244
+ "13": {
245
+ "0": 49,
246
+ "1": 50
247
+ },
248
+ "14": {
249
+ "0": 61,
250
+ "1": 62
251
+ },
252
+ "15": {
253
+ "0": 73,
254
+ "1": 74
255
+ },
256
+ "16": {
257
+ "0": 85
258
+ },
259
+ "17": {
260
+ "0": 97
261
+ },
262
+ "18": {
263
+ "0": 109,
264
+ "1": 110
265
+ },
266
+ "19": {
267
+ "0": 121,
268
+ "1": 122
269
+ },
270
+ "20": {
271
+ "0": 133,
272
+ "1": 134
273
+ },
274
+ "21": {
275
+ "COMMA": 145,
276
+ "DOT": 146,
277
+ "ENDBRACKET": 147,
278
+ "HYPHEN": 148,
279
+ "NOPUNCT": 149,
280
+ "OPENBRACKET": 150,
281
+ "PUNCT": 151,
282
+ "QUOTE": 152
283
+ },
284
+ "22": {
285
+ "0": 157,
286
+ "1": 158,
287
+ "10": 159,
288
+ "2": 160,
289
+ "3": 161,
290
+ "4": 162,
291
+ "5": 163,
292
+ "6": 164,
293
+ "7": 165,
294
+ "8": 166,
295
+ "9": 167
296
+ },
297
+ "23": {
298
+ "0": 169,
299
+ "1": 170,
300
+ "10": 171,
301
+ "2": 172,
302
+ "3": 173,
303
+ "4": 174,
304
+ "5": 175,
305
+ "6": 176,
306
+ "7": 177,
307
+ "8": 178,
308
+ "9": 179
309
+ },
310
+ "24": {
311
+ "BLOCKEND": 181,
312
+ "BLOCKIN": 182,
313
+ "BLOCKSTART": 183
314
+ },
315
+ "25": {
316
+ "1": 193,
317
+ "10": 194,
318
+ "2": 195,
319
+ "3": 196,
320
+ "4": 197,
321
+ "5": 198,
322
+ "6": 199,
323
+ "7": 200,
324
+ "8": 201,
325
+ "9": 202,
326
+ "no": 203
327
+ },
328
+ "26": {
329
+ "0": 205
330
+ }
331
+ },
332
+ "continuous_features_indices": [],
333
+ "continuous_features_ranges": []
334
+ },
335
+ "indice_tag": {
336
+ "0": "<PAD>",
337
+ "1": "B-<label>",
338
+ "2": "B-<reference>",
339
+ "3": "I-<label>",
340
+ "4": "I-<reference>",
341
+ "5": "O"
342
+ }
343
+ }
grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-glove_840B/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "model_name": "grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES",
3
  "architecture": "BidLSTM_ChainCRF_FEATURES",
4
  "embeddings_name": "glove-840B",
5
  "char_vocab_size": 172,
@@ -30,6 +30,7 @@
30
  ],
31
  "features_embedding_size": 4,
32
  "features_lstm_units": 4,
 
33
  "max_sequence_length": 3000,
34
  "word_embedding_size": 300,
35
  "num_word_lstm_units": 100,
@@ -41,6 +42,9 @@
41
  "fold_number": 1,
42
  "batch_size": 5,
43
  "transformer_name": null,
 
 
 
44
  "features_map_to_index": {
45
  "9": {
46
  "LINEEND": 1,
 
1
  {
2
+ "model_name": "grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-gloves_840B",
3
  "architecture": "BidLSTM_ChainCRF_FEATURES",
4
  "embeddings_name": "glove-840B",
5
  "char_vocab_size": 172,
 
30
  ],
31
  "features_embedding_size": 4,
32
  "features_lstm_units": 4,
33
+ "continuous_features_indices": null,
34
  "max_sequence_length": 3000,
35
  "word_embedding_size": 300,
36
  "num_word_lstm_units": 100,
 
42
  "fold_number": 1,
43
  "batch_size": 5,
44
  "transformer_name": null,
45
+ "window_stride": null,
46
+ "text_features_indices": null,
47
+ "contextual_embedding_settings": null,
48
  "features_map_to_index": {
49
  "9": {
50
  "LINEEND": 1,
grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-glove_840B/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34072fb44f03623e2362aa90a7d216d8208c09d89e8fcc3c70e0a9d03c863737
3
+ size 1621608
grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-glove_840B/preprocessor.json CHANGED
@@ -328,7 +328,9 @@
328
  "26": {
329
  "0": 205
330
  }
331
- }
 
 
332
  },
333
  "indice_tag": {
334
  "0": "<PAD>",
 
328
  "26": {
329
  "0": 205
330
  }
331
+ },
332
+ "continuous_features_indices": [],
333
+ "continuous_features_ranges": []
334
  },
335
  "indice_tag": {
336
  "0": "<PAD>",
grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-no_embeddings/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "model_name": "grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES",
3
  "architecture": "BidLSTM_ChainCRF_FEATURES",
4
  "embeddings_name": null,
5
  "char_vocab_size": 172,
@@ -30,6 +30,7 @@
30
  ],
31
  "features_embedding_size": 4,
32
  "features_lstm_units": 4,
 
33
  "max_sequence_length": 3000,
34
  "word_embedding_size": 0,
35
  "num_word_lstm_units": 100,
@@ -41,6 +42,9 @@
41
  "fold_number": 1,
42
  "batch_size": 5,
43
  "transformer_name": null,
 
 
 
44
  "features_map_to_index": {
45
  "9": {
46
  "LINEEND": 1,
 
1
  {
2
+ "model_name": "grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-no_embeddings",
3
  "architecture": "BidLSTM_ChainCRF_FEATURES",
4
  "embeddings_name": null,
5
  "char_vocab_size": 172,
 
30
  ],
31
  "features_embedding_size": 4,
32
  "features_lstm_units": 4,
33
+ "continuous_features_indices": null,
34
  "max_sequence_length": 3000,
35
  "word_embedding_size": 0,
36
  "num_word_lstm_units": 100,
 
42
  "fold_number": 1,
43
  "batch_size": 5,
44
  "transformer_name": null,
45
+ "window_stride": null,
46
+ "text_features_indices": null,
47
+ "contextual_embedding_settings": null,
48
  "features_map_to_index": {
49
  "9": {
50
  "LINEEND": 1,
grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-no_embeddings/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:320a48e89073abacc92d647826d877839bb44c321ff31eb3af9c718ef4ebf1aa
3
+ size 661552
grobid-reference-segmenter-BidLSTM_ChainCRF_FEATURES-no_embeddings/preprocessor.json CHANGED
@@ -328,7 +328,9 @@
328
  "26": {
329
  "0": 205
330
  }
331
- }
 
 
332
  },
333
  "indice_tag": {
334
  "0": "<PAD>",
 
328
  "26": {
329
  "0": 205
330
  }
331
+ },
332
+ "continuous_features_indices": [],
333
+ "continuous_features_ranges": []
334
  },
335
  "indice_tag": {
336
  "0": "<PAD>",