abotana commited on
Commit
8bdf907
·
verified ·
1 Parent(s): c63f17c

Upload 4 files

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +436 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +3 -0
  5. tokenizer_config.json +25 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,436 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForTokenClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "classifier_activation": "silu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 1,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "dtype": "bfloat16",
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 2,
18
+ "global_attn_every_n_layers": 3,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 768,
22
+ "id2label": {
23
+ "0": "A0CN",
24
+ "1": "A0CP",
25
+ "2": "A0CS",
26
+ "3": "A0FP",
27
+ "4": "A0FS",
28
+ "5": "A0MP",
29
+ "6": "A0MS",
30
+ "7": "AAMP",
31
+ "8": "CC",
32
+ "9": "CS",
33
+ "10": "DFP",
34
+ "11": "DFS",
35
+ "12": "DMP",
36
+ "13": "DMS",
37
+ "14": "DNS",
38
+ "15": "E",
39
+ "16": "Faa",
40
+ "17": "Fat",
41
+ "18": "Fc",
42
+ "19": "Fca",
43
+ "20": "Fct",
44
+ "21": "Fd",
45
+ "22": "Fe",
46
+ "23": "Fg",
47
+ "24": "Fia",
48
+ "25": "Fit",
49
+ "26": "Fp",
50
+ "27": "Fpa",
51
+ "28": "Fpt",
52
+ "29": "Fra",
53
+ "30": "Frc",
54
+ "31": "Ft",
55
+ "32": "Fx",
56
+ "33": "Fz",
57
+ "34": "GCP",
58
+ "35": "GCS",
59
+ "36": "GFP",
60
+ "37": "GFS",
61
+ "38": "GMP",
62
+ "39": "GMS",
63
+ "40": "IFP0",
64
+ "41": "IFS0",
65
+ "42": "IMP0",
66
+ "43": "IMS0",
67
+ "44": "IMSA",
68
+ "45": "INP0",
69
+ "46": "INS0",
70
+ "47": "L",
71
+ "48": "MC0CN",
72
+ "49": "MC0FN",
73
+ "50": "MC0MN",
74
+ "51": "MO0FP",
75
+ "52": "MO0FS",
76
+ "53": "MO0MP",
77
+ "54": "MO0MS",
78
+ "55": "MP0FS",
79
+ "56": "MP0MS",
80
+ "57": "NCCP0",
81
+ "58": "NCCS0",
82
+ "59": "NCFP0",
83
+ "60": "NCFS0",
84
+ "61": "NCFSA",
85
+ "62": "NCMN0",
86
+ "63": "NCMP0",
87
+ "64": "NCMS0",
88
+ "65": "NP000",
89
+ "66": "O",
90
+ "67": "P1CPB0",
91
+ "68": "P1CPC0",
92
+ "69": "P1CSC0",
93
+ "70": "P1CSN0",
94
+ "71": "P1CSO0",
95
+ "72": "P2CPB0",
96
+ "73": "P2CPC0",
97
+ "74": "P2CSA0",
98
+ "75": "P2CSB0",
99
+ "76": "P3CNB0",
100
+ "77": "P3CNO0",
101
+ "78": "P3CNR0",
102
+ "79": "P3CPD0",
103
+ "80": "P3CSBP",
104
+ "81": "P3CSD0",
105
+ "82": "P3FPA0",
106
+ "83": "P3FPB0",
107
+ "84": "P3FSA0",
108
+ "85": "P3FSB0",
109
+ "86": "P3MPA0",
110
+ "87": "P3MPB0",
111
+ "88": "P3MSA0",
112
+ "89": "P3MSB0",
113
+ "90": "QCN0",
114
+ "91": "QCP0",
115
+ "92": "QCS0",
116
+ "93": "QFP0",
117
+ "94": "QFS0",
118
+ "95": "QMP0",
119
+ "96": "QMS0",
120
+ "97": "R0",
121
+ "98": "S",
122
+ "99": "TCN0",
123
+ "100": "TCP0",
124
+ "101": "TCS0",
125
+ "102": "TMP0",
126
+ "103": "TMS0",
127
+ "104": "U",
128
+ "105": "VIA1P00",
129
+ "106": "VIA2S00",
130
+ "107": "VIA3P00",
131
+ "108": "VIA3S00",
132
+ "109": "VIC1P00",
133
+ "110": "VIC2P00",
134
+ "111": "VIC2S00",
135
+ "112": "VIC3P00",
136
+ "113": "VIC3S00",
137
+ "114": "VIF1P00",
138
+ "115": "VIF2P00",
139
+ "116": "VIF2S00",
140
+ "117": "VIF3P00",
141
+ "118": "VIF3S00",
142
+ "119": "VII1P00",
143
+ "120": "VII2S00",
144
+ "121": "VII3P00",
145
+ "122": "VII3S00",
146
+ "123": "VIP1P00",
147
+ "124": "VIP1S00",
148
+ "125": "VIP2P00",
149
+ "126": "VIP2S00",
150
+ "127": "VIP3P00",
151
+ "128": "VIP3S00",
152
+ "129": "VIS1P00",
153
+ "130": "VIS1S00",
154
+ "131": "VIS2P00",
155
+ "132": "VIS2S00",
156
+ "133": "VIS3P00",
157
+ "134": "VIS3S00",
158
+ "135": "VM02P00",
159
+ "136": "VM02S00",
160
+ "137": "VN00000",
161
+ "138": "VN01P00",
162
+ "139": "VN02S00",
163
+ "140": "VN03P00",
164
+ "141": "VP00PC0",
165
+ "142": "VP00PF0",
166
+ "143": "VP00PM0",
167
+ "144": "VP00SF0",
168
+ "145": "VP00SM0",
169
+ "146": "VP3S00",
170
+ "147": "VSF3S00",
171
+ "148": "VSI1P00",
172
+ "149": "VSI2S00",
173
+ "150": "VSI3P00",
174
+ "151": "VSI3S00",
175
+ "152": "VSP1P00",
176
+ "153": "VSP2P00",
177
+ "154": "VSP2S00",
178
+ "155": "VSP3P00",
179
+ "156": "VSP3S00",
180
+ "157": "VX00000",
181
+ "158": "X1FPP",
182
+ "159": "X1FSP",
183
+ "160": "X1FSS",
184
+ "161": "X1MPP",
185
+ "162": "X1MPS",
186
+ "163": "X1MSP",
187
+ "164": "X1MSS",
188
+ "165": "X2FPP",
189
+ "166": "X2FPS",
190
+ "167": "X2FSP",
191
+ "168": "X2FSS",
192
+ "169": "X2MPS",
193
+ "170": "X2MSS",
194
+ "171": "X3FP0",
195
+ "172": "X3FS0",
196
+ "173": "X3MP0",
197
+ "174": "X3MS0",
198
+ "175": "Y",
199
+ "176": "Z"
200
+ },
201
+ "initializer_cutoff_factor": 2.0,
202
+ "initializer_range": 0.02,
203
+ "intermediate_size": 1152,
204
+ "label2id": {
205
+ "A0CN": 0,
206
+ "A0CP": 1,
207
+ "A0CS": 2,
208
+ "A0FP": 3,
209
+ "A0FS": 4,
210
+ "A0MP": 5,
211
+ "A0MS": 6,
212
+ "AAMP": 7,
213
+ "CC": 8,
214
+ "CS": 9,
215
+ "DFP": 10,
216
+ "DFS": 11,
217
+ "DMP": 12,
218
+ "DMS": 13,
219
+ "DNS": 14,
220
+ "E": 15,
221
+ "Faa": 16,
222
+ "Fat": 17,
223
+ "Fc": 18,
224
+ "Fca": 19,
225
+ "Fct": 20,
226
+ "Fd": 21,
227
+ "Fe": 22,
228
+ "Fg": 23,
229
+ "Fia": 24,
230
+ "Fit": 25,
231
+ "Fp": 26,
232
+ "Fpa": 27,
233
+ "Fpt": 28,
234
+ "Fra": 29,
235
+ "Frc": 30,
236
+ "Ft": 31,
237
+ "Fx": 32,
238
+ "Fz": 33,
239
+ "GCP": 34,
240
+ "GCS": 35,
241
+ "GFP": 36,
242
+ "GFS": 37,
243
+ "GMP": 38,
244
+ "GMS": 39,
245
+ "IFP0": 40,
246
+ "IFS0": 41,
247
+ "IMP0": 42,
248
+ "IMS0": 43,
249
+ "IMSA": 44,
250
+ "INP0": 45,
251
+ "INS0": 46,
252
+ "L": 47,
253
+ "MC0CN": 48,
254
+ "MC0FN": 49,
255
+ "MC0MN": 50,
256
+ "MO0FP": 51,
257
+ "MO0FS": 52,
258
+ "MO0MP": 53,
259
+ "MO0MS": 54,
260
+ "MP0FS": 55,
261
+ "MP0MS": 56,
262
+ "NCCP0": 57,
263
+ "NCCS0": 58,
264
+ "NCFP0": 59,
265
+ "NCFS0": 60,
266
+ "NCFSA": 61,
267
+ "NCMN0": 62,
268
+ "NCMP0": 63,
269
+ "NCMS0": 64,
270
+ "NP000": 65,
271
+ "O": 66,
272
+ "P1CPB0": 67,
273
+ "P1CPC0": 68,
274
+ "P1CSC0": 69,
275
+ "P1CSN0": 70,
276
+ "P1CSO0": 71,
277
+ "P2CPB0": 72,
278
+ "P2CPC0": 73,
279
+ "P2CSA0": 74,
280
+ "P2CSB0": 75,
281
+ "P3CNB0": 76,
282
+ "P3CNO0": 77,
283
+ "P3CNR0": 78,
284
+ "P3CPD0": 79,
285
+ "P3CSBP": 80,
286
+ "P3CSD0": 81,
287
+ "P3FPA0": 82,
288
+ "P3FPB0": 83,
289
+ "P3FSA0": 84,
290
+ "P3FSB0": 85,
291
+ "P3MPA0": 86,
292
+ "P3MPB0": 87,
293
+ "P3MSA0": 88,
294
+ "P3MSB0": 89,
295
+ "QCN0": 90,
296
+ "QCP0": 91,
297
+ "QCS0": 92,
298
+ "QFP0": 93,
299
+ "QFS0": 94,
300
+ "QMP0": 95,
301
+ "QMS0": 96,
302
+ "R0": 97,
303
+ "S": 98,
304
+ "TCN0": 99,
305
+ "TCP0": 100,
306
+ "TCS0": 101,
307
+ "TMP0": 102,
308
+ "TMS0": 103,
309
+ "U": 104,
310
+ "VIA1P00": 105,
311
+ "VIA2S00": 106,
312
+ "VIA3P00": 107,
313
+ "VIA3S00": 108,
314
+ "VIC1P00": 109,
315
+ "VIC2P00": 110,
316
+ "VIC2S00": 111,
317
+ "VIC3P00": 112,
318
+ "VIC3S00": 113,
319
+ "VIF1P00": 114,
320
+ "VIF2P00": 115,
321
+ "VIF2S00": 116,
322
+ "VIF3P00": 117,
323
+ "VIF3S00": 118,
324
+ "VII1P00": 119,
325
+ "VII2S00": 120,
326
+ "VII3P00": 121,
327
+ "VII3S00": 122,
328
+ "VIP1P00": 123,
329
+ "VIP1S00": 124,
330
+ "VIP2P00": 125,
331
+ "VIP2S00": 126,
332
+ "VIP3P00": 127,
333
+ "VIP3S00": 128,
334
+ "VIS1P00": 129,
335
+ "VIS1S00": 130,
336
+ "VIS2P00": 131,
337
+ "VIS2S00": 132,
338
+ "VIS3P00": 133,
339
+ "VIS3S00": 134,
340
+ "VM02P00": 135,
341
+ "VM02S00": 136,
342
+ "VN00000": 137,
343
+ "VN01P00": 138,
344
+ "VN02S00": 139,
345
+ "VN03P00": 140,
346
+ "VP00PC0": 141,
347
+ "VP00PF0": 142,
348
+ "VP00PM0": 143,
349
+ "VP00SF0": 144,
350
+ "VP00SM0": 145,
351
+ "VP3S00": 146,
352
+ "VSF3S00": 147,
353
+ "VSI1P00": 148,
354
+ "VSI2S00": 149,
355
+ "VSI3P00": 150,
356
+ "VSI3S00": 151,
357
+ "VSP1P00": 152,
358
+ "VSP2P00": 153,
359
+ "VSP2S00": 154,
360
+ "VSP3P00": 155,
361
+ "VSP3S00": 156,
362
+ "VX00000": 157,
363
+ "X1FPP": 158,
364
+ "X1FSP": 159,
365
+ "X1FSS": 160,
366
+ "X1MPP": 161,
367
+ "X1MPS": 162,
368
+ "X1MSP": 163,
369
+ "X1MSS": 164,
370
+ "X2FPP": 165,
371
+ "X2FPS": 166,
372
+ "X2FSP": 167,
373
+ "X2FSS": 168,
374
+ "X2MPS": 169,
375
+ "X2MSS": 170,
376
+ "X3FP0": 171,
377
+ "X3FS0": 172,
378
+ "X3MP0": 173,
379
+ "X3MS0": 174,
380
+ "Y": 175,
381
+ "Z": 176
382
+ },
383
+ "layer_norm_eps": 1e-05,
384
+ "layer_types": [
385
+ "full_attention",
386
+ "sliding_attention",
387
+ "sliding_attention",
388
+ "full_attention",
389
+ "sliding_attention",
390
+ "sliding_attention",
391
+ "full_attention",
392
+ "sliding_attention",
393
+ "sliding_attention",
394
+ "full_attention",
395
+ "sliding_attention",
396
+ "sliding_attention",
397
+ "full_attention",
398
+ "sliding_attention",
399
+ "sliding_attention",
400
+ "full_attention",
401
+ "sliding_attention",
402
+ "sliding_attention",
403
+ "full_attention",
404
+ "sliding_attention",
405
+ "sliding_attention",
406
+ "full_attention"
407
+ ],
408
+ "local_attention": 128,
409
+ "max_position_embeddings": 1024,
410
+ "mlp_bias": false,
411
+ "mlp_dropout": 0.0,
412
+ "model_type": "modernbert",
413
+ "norm_bias": false,
414
+ "norm_eps": 1e-05,
415
+ "num_attention_heads": 12,
416
+ "num_hidden_layers": 22,
417
+ "pad_token_id": 3,
418
+ "position_embedding_type": "absolute",
419
+ "rope_parameters": {
420
+ "full_attention": {
421
+ "rope_theta": 10000.0,
422
+ "rope_type": "default"
423
+ },
424
+ "sliding_attention": {
425
+ "rope_theta": 10000.0,
426
+ "rope_type": "default"
427
+ }
428
+ },
429
+ "sep_token_id": 2,
430
+ "sparse_pred_ignore_index": -100,
431
+ "sparse_prediction": false,
432
+ "tie_word_embeddings": true,
433
+ "transformers_version": "5.2.0",
434
+ "use_cache": false,
435
+ "vocab_size": 256000
436
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2230b316bf459326a63da151ad52b473be4df378904b958987ba1edc81a790
3
+ size 615347034
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3cc267e5cc5f6cdbb2bdb26232696ebbec34817140a2368d9ffbaca4b74024c
3
+ size 37008053
tokenizer_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "extra_special_tokens": [
8
+ "<|translation|>"
9
+ ],
10
+ "is_local": true,
11
+ "legacy": true,
12
+ "mask_token": "<mask>",
13
+ "model_input_names": [
14
+ "input_ids",
15
+ "attention_mask"
16
+ ],
17
+ "model_max_length": 1024,
18
+ "pad_token": "<pad>",
19
+ "padding_side": "right",
20
+ "sp_model_kwargs": {},
21
+ "spaces_between_special_tokens": false,
22
+ "tokenizer_class": "TokenizersBackend",
23
+ "unk_token": "<unk>",
24
+ "use_default_system_prompt": false
25
+ }