Temurbek Rahmatullaev commited on
Commit
f9f8e60
β€’
1 Parent(s): 19d93ca

new weights based on MicrOmnic

Browse files
MSE-v8_500/deamon_metrics.json ADDED
@@ -0,0 +1,494 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": 0,
4
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/0",
5
+ "metrics": {
6
+ "IoU": 0.2573073785787923,
7
+ "IoU X-axis": 0.5124070409135215,
8
+ "IoU Y-axis": 0.45185581349972,
9
+ "Precision": 0.48676431989534874,
10
+ "Recall": 0.4899683952548239,
11
+ "F1 Score": 0.36945933906846934
12
+ }
13
+ },
14
+ {
15
+ "id": 500,
16
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/500",
17
+ "metrics": {
18
+ "IoU": 0.29261527701041873,
19
+ "IoU X-axis": 0.5350152751752992,
20
+ "IoU Y-axis": 0.4927368081763773,
21
+ "Precision": 0.45824114004260236,
22
+ "Recall": 0.5622275578254764,
23
+ "F1 Score": 0.41247836633091994
24
+ }
25
+ },
26
+ {
27
+ "id": 1000,
28
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/1000",
29
+ "metrics": {
30
+ "IoU": 0.2086817870451896,
31
+ "IoU X-axis": 0.4265646071041908,
32
+ "IoU Y-axis": 0.4269184602256855,
33
+ "Precision": 0.5236425506192884,
34
+ "Recall": 0.3442983683820104,
35
+ "F1 Score": 0.3061764364816441
36
+ }
37
+ },
38
+ {
39
+ "id": 1500,
40
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/1500",
41
+ "metrics": {
42
+ "IoU": 0.2373786419431733,
43
+ "IoU X-axis": 0.45811440284045085,
44
+ "IoU Y-axis": 0.46036883532657624,
45
+ "Precision": 0.5139010999594107,
46
+ "Recall": 0.42560539504677536,
47
+ "F1 Score": 0.3471482639691499
48
+ }
49
+ },
50
+ {
51
+ "id": 2000,
52
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/2000",
53
+ "metrics": {
54
+ "IoU": 0.2738231998988857,
55
+ "IoU X-axis": 0.4775217611085711,
56
+ "IoU Y-axis": 0.5180771587605383,
57
+ "Precision": 0.5536185552557404,
58
+ "Recall": 0.464618838639758,
59
+ "F1 Score": 0.39416055778898895
60
+ }
61
+ },
62
+ {
63
+ "id": 2500,
64
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/2500",
65
+ "metrics": {
66
+ "IoU": 0.25736577955218093,
67
+ "IoU X-axis": 0.4693905680106517,
68
+ "IoU Y-axis": 0.48682941104470023,
69
+ "Precision": 0.5418301552133302,
70
+ "Recall": 0.4080242084217252,
71
+ "F1 Score": 0.3704182637797203
72
+ }
73
+ },
74
+ {
75
+ "id": 3000,
76
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/3000",
77
+ "metrics": {
78
+ "IoU": 0.25082396388084294,
79
+ "IoU X-axis": 0.4497811471398459,
80
+ "IoU Y-axis": 0.49230778845105844,
81
+ "Precision": 0.5357412924692205,
82
+ "Recall": 0.3787923568197631,
83
+ "F1 Score": 0.3686916852365866
84
+ }
85
+ },
86
+ {
87
+ "id": 3500,
88
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/3500",
89
+ "metrics": {
90
+ "IoU": 0.2649904038176352,
91
+ "IoU X-axis": 0.4958043530115566,
92
+ "IoU Y-axis": 0.49039750598847687,
93
+ "Precision": 0.5180239452875058,
94
+ "Recall": 0.4237308398940503,
95
+ "F1 Score": 0.3820106080621794
96
+ }
97
+ },
98
+ {
99
+ "id": 4000,
100
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/4000",
101
+ "metrics": {
102
+ "IoU": 0.1626876747873239,
103
+ "IoU X-axis": 0.3979533181445103,
104
+ "IoU Y-axis": 0.3770971421050207,
105
+ "Precision": 0.5660427679175046,
106
+ "Recall": 0.2522166129722039,
107
+ "F1 Score": 0.24751488576145192
108
+ }
109
+ },
110
+ {
111
+ "id": 4500,
112
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/4500",
113
+ "metrics": {
114
+ "IoU": 0.12458729072267685,
115
+ "IoU X-axis": 0.30500781483846046,
116
+ "IoU Y-axis": 0.35801707503009583,
117
+ "Precision": 0.572967287487053,
118
+ "Recall": 0.17940665641745204,
119
+ "F1 Score": 0.1934661329154313
120
+ }
121
+ },
122
+ {
123
+ "id": 5000,
124
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/5000",
125
+ "metrics": {
126
+ "IoU": 0.1923190462328443,
127
+ "IoU X-axis": 0.3849245277697073,
128
+ "IoU Y-axis": 0.4480575105198035,
129
+ "Precision": 0.5531873187415247,
130
+ "Recall": 0.292012519116472,
131
+ "F1 Score": 0.2856175729184694
132
+ }
133
+ },
134
+ {
135
+ "id": 5500,
136
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/5500",
137
+ "metrics": {
138
+ "IoU": 0.1924568306978899,
139
+ "IoU X-axis": 0.3963210615593323,
140
+ "IoU Y-axis": 0.44731441237293734,
141
+ "Precision": 0.5947821029751958,
142
+ "Recall": 0.2729263848387383,
143
+ "F1 Score": 0.2897035798393723
144
+ }
145
+ },
146
+ {
147
+ "id": 6000,
148
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/6000",
149
+ "metrics": {
150
+ "IoU": 0.23810819963459934,
151
+ "IoU X-axis": 0.46086407149913355,
152
+ "IoU Y-axis": 0.4652542879647633,
153
+ "Precision": 0.571393161980918,
154
+ "Recall": 0.3630459300445307,
155
+ "F1 Score": 0.34995233863694336
156
+ }
157
+ },
158
+ {
159
+ "id": 6500,
160
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/6500",
161
+ "metrics": {
162
+ "IoU": 0.20355787522345614,
163
+ "IoU X-axis": 0.4098115429157392,
164
+ "IoU Y-axis": 0.4296242556299633,
165
+ "Precision": 0.5258156124148472,
166
+ "Recall": 0.3273490622200887,
167
+ "F1 Score": 0.3005714117243924
168
+ }
169
+ },
170
+ {
171
+ "id": 7000,
172
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/7000",
173
+ "metrics": {
174
+ "IoU": 0.1895895889878193,
175
+ "IoU X-axis": 0.4003860259743378,
176
+ "IoU Y-axis": 0.41784049503238035,
177
+ "Precision": 0.5731100461652181,
178
+ "Recall": 0.290938205962712,
179
+ "F1 Score": 0.28493987166127765
180
+ }
181
+ },
182
+ {
183
+ "id": 7500,
184
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/7500",
185
+ "metrics": {
186
+ "IoU": 0.18020708107999353,
187
+ "IoU X-axis": 0.4089860320783164,
188
+ "IoU Y-axis": 0.3889598723398427,
189
+ "Precision": 0.557979748390158,
190
+ "Recall": 0.2702766565342018,
191
+ "F1 Score": 0.26962478258780054
192
+ }
193
+ },
194
+ {
195
+ "id": 8000,
196
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/8000",
197
+ "metrics": {
198
+ "IoU": 0.21111016891640713,
199
+ "IoU X-axis": 0.43880538576158346,
200
+ "IoU Y-axis": 0.4248336188120112,
201
+ "Precision": 0.4763979418827746,
202
+ "Recall": 0.3506196395757508,
203
+ "F1 Score": 0.3106726208640294
204
+ }
205
+ },
206
+ {
207
+ "id": 8500,
208
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/8500",
209
+ "metrics": {
210
+ "IoU": 0.16922462751992756,
211
+ "IoU X-axis": 0.38508295683165256,
212
+ "IoU Y-axis": 0.37613050541635673,
213
+ "Precision": 0.5661092025072683,
214
+ "Recall": 0.2330950312116646,
215
+ "F1 Score": 0.255527965480918
216
+ }
217
+ },
218
+ {
219
+ "id": 9000,
220
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/9000",
221
+ "metrics": {
222
+ "IoU": 0.22723029035455375,
223
+ "IoU X-axis": 0.4402235440970547,
224
+ "IoU Y-axis": 0.46220864256668037,
225
+ "Precision": 0.5593948148355286,
226
+ "Recall": 0.3785080561254186,
227
+ "F1 Score": 0.3311487573688602
228
+ }
229
+ },
230
+ {
231
+ "id": 9500,
232
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/9500",
233
+ "metrics": {
234
+ "IoU": 0.2607876408001598,
235
+ "IoU X-axis": 0.4860001118898332,
236
+ "IoU Y-axis": 0.4662941254626641,
237
+ "Precision": 0.5262113802022309,
238
+ "Recall": 0.42789335385275606,
239
+ "F1 Score": 0.3716078958977861
240
+ }
241
+ },
242
+ {
243
+ "id": 10000,
244
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/10000",
245
+ "metrics": {
246
+ "IoU": 0.18902284391330376,
247
+ "IoU X-axis": 0.4263937993169028,
248
+ "IoU Y-axis": 0.38841559756868604,
249
+ "Precision": 0.5663261857076398,
250
+ "Recall": 0.2808461628474566,
251
+ "F1 Score": 0.2777918089875473
252
+ }
253
+ },
254
+ {
255
+ "id": 10500,
256
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/10500",
257
+ "metrics": {
258
+ "IoU": 0.22677133472089356,
259
+ "IoU X-axis": 0.4823130116444345,
260
+ "IoU Y-axis": 0.431983192505625,
261
+ "Precision": 0.5002983708996963,
262
+ "Recall": 0.39000127393194767,
263
+ "F1 Score": 0.32985596657051486
264
+ }
265
+ },
266
+ {
267
+ "id": 11000,
268
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/11000",
269
+ "metrics": {
270
+ "IoU": 0.19239614310751796,
271
+ "IoU X-axis": 0.4810857073315791,
272
+ "IoU Y-axis": 0.36735922451468356,
273
+ "Precision": 0.490983818371878,
274
+ "Recall": 0.3141861580589725,
275
+ "F1 Score": 0.2833296491341754
276
+ }
277
+ },
278
+ {
279
+ "id": 11500,
280
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/11500",
281
+ "metrics": {
282
+ "IoU": 0.2124931008115709,
283
+ "IoU X-axis": 0.4557770523145819,
284
+ "IoU Y-axis": 0.4122538173466141,
285
+ "Precision": 0.47862219721356847,
286
+ "Recall": 0.35933059074864704,
287
+ "F1 Score": 0.31135137022819004
288
+ }
289
+ },
290
+ {
291
+ "id": 12000,
292
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/12000",
293
+ "metrics": {
294
+ "IoU": 0.2108051702940953,
295
+ "IoU X-axis": 0.4860642168539168,
296
+ "IoU Y-axis": 0.3888905799518491,
297
+ "Precision": 0.5405617720602378,
298
+ "Recall": 0.35082128159982384,
299
+ "F1 Score": 0.31351870744278076
300
+ }
301
+ },
302
+ {
303
+ "id": 12500,
304
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/12500",
305
+ "metrics": {
306
+ "IoU": 0.19668757706346476,
307
+ "IoU X-axis": 0.44173051391832147,
308
+ "IoU Y-axis": 0.3949906223372994,
309
+ "Precision": 0.5331373729044838,
310
+ "Recall": 0.3143822272973992,
311
+ "F1 Score": 0.29400190368479273
312
+ }
313
+ },
314
+ {
315
+ "id": 13000,
316
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/13000",
317
+ "metrics": {
318
+ "IoU": 0.18415290124559852,
319
+ "IoU X-axis": 0.4329942847670981,
320
+ "IoU Y-axis": 0.37022415299559613,
321
+ "Precision": 0.5212383423598258,
322
+ "Recall": 0.27935519669867614,
323
+ "F1 Score": 0.275192405645684
324
+ }
325
+ },
326
+ {
327
+ "id": 13500,
328
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/13500",
329
+ "metrics": {
330
+ "IoU": 0.22874777427378012,
331
+ "IoU X-axis": 0.4881351614173073,
332
+ "IoU Y-axis": 0.4321560594770112,
333
+ "Precision": 0.5073839782484604,
334
+ "Recall": 0.3721083330348787,
335
+ "F1 Score": 0.3344707324872758
336
+ }
337
+ },
338
+ {
339
+ "id": 14000,
340
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/14000",
341
+ "metrics": {
342
+ "IoU": 0.20106381831013742,
343
+ "IoU X-axis": 0.44314132717553206,
344
+ "IoU Y-axis": 0.41317677917555345,
345
+ "Precision": 0.5158708662568253,
346
+ "Recall": 0.34570189737034723,
347
+ "F1 Score": 0.298001728105715
348
+ }
349
+ },
350
+ {
351
+ "id": 14500,
352
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/14500",
353
+ "metrics": {
354
+ "IoU": 0.19690527387575948,
355
+ "IoU X-axis": 0.44062291715869234,
356
+ "IoU Y-axis": 0.4066910841218624,
357
+ "Precision": 0.5265281161696421,
358
+ "Recall": 0.31302915371632856,
359
+ "F1 Score": 0.29510591870093333
360
+ }
361
+ },
362
+ {
363
+ "id": 15000,
364
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/15000",
365
+ "metrics": {
366
+ "IoU": 0.1367996073222642,
367
+ "IoU X-axis": 0.3716025410206103,
368
+ "IoU Y-axis": 0.3439228075377031,
369
+ "Precision": 0.5880577036283847,
370
+ "Recall": 0.1869240589356138,
371
+ "F1 Score": 0.21841704237246173
372
+ }
373
+ },
374
+ {
375
+ "id": 15500,
376
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/15500",
377
+ "metrics": {
378
+ "IoU": 0.20985181516276014,
379
+ "IoU X-axis": 0.4396028704890865,
380
+ "IoU Y-axis": 0.42053265345978746,
381
+ "Precision": 0.5321430312440207,
382
+ "Recall": 0.32924655759434385,
383
+ "F1 Score": 0.30865870302298415
384
+ }
385
+ },
386
+ {
387
+ "id": 16000,
388
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/16000",
389
+ "metrics": {
390
+ "IoU": 0.2244717207714992,
391
+ "IoU X-axis": 0.4501551211369741,
392
+ "IoU Y-axis": 0.4609718054193405,
393
+ "Precision": 0.547007048870619,
394
+ "Recall": 0.3607929977130974,
395
+ "F1 Score": 0.33321307525428595
396
+ }
397
+ },
398
+ {
399
+ "id": 16500,
400
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/16500",
401
+ "metrics": {
402
+ "IoU": 0.20229700558096678,
403
+ "IoU X-axis": 0.45239468420587753,
404
+ "IoU Y-axis": 0.3989771046932674,
405
+ "Precision": 0.4966387938084334,
406
+ "Recall": 0.3223553427897163,
407
+ "F1 Score": 0.2986934442233425
408
+ }
409
+ },
410
+ {
411
+ "id": 17000,
412
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/17000",
413
+ "metrics": {
414
+ "IoU": 0.2191698160205444,
415
+ "IoU X-axis": 0.4462361638403316,
416
+ "IoU Y-axis": 0.4276635317567595,
417
+ "Precision": 0.5133372281492418,
418
+ "Recall": 0.33990130582133604,
419
+ "F1 Score": 0.3198265246657005
420
+ }
421
+ },
422
+ {
423
+ "id": 17500,
424
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/17500",
425
+ "metrics": {
426
+ "IoU": 0.2366728507505847,
427
+ "IoU X-axis": 0.46531028492134013,
428
+ "IoU Y-axis": 0.46781633536293316,
429
+ "Precision": 0.5205900738041735,
430
+ "Recall": 0.3807144049056005,
431
+ "F1 Score": 0.3485280777865687
432
+ }
433
+ },
434
+ {
435
+ "id": 18000,
436
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/18000",
437
+ "metrics": {
438
+ "IoU": 0.24897811490423458,
439
+ "IoU X-axis": 0.48472581621602634,
440
+ "IoU Y-axis": 0.46869362894786726,
441
+ "Precision": 0.4963018216178605,
442
+ "Recall": 0.4112225558859957,
443
+ "F1 Score": 0.3597984448781244
444
+ }
445
+ },
446
+ {
447
+ "id": 18500,
448
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/18500",
449
+ "metrics": {
450
+ "IoU": 0.20768915324788575,
451
+ "IoU X-axis": 0.4232083093190646,
452
+ "IoU Y-axis": 0.4293730572817871,
453
+ "Precision": 0.4925219901536748,
454
+ "Recall": 0.3349815933471095,
455
+ "F1 Score": 0.30499804658294444
456
+ }
457
+ },
458
+ {
459
+ "id": 19000,
460
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/19000",
461
+ "metrics": {
462
+ "IoU": 0.19039552711790309,
463
+ "IoU X-axis": 0.405954167427441,
464
+ "IoU Y-axis": 0.4157834750695693,
465
+ "Precision": 0.5245899691057866,
466
+ "Recall": 0.2796746766281925,
467
+ "F1 Score": 0.2836316546104034
468
+ }
469
+ },
470
+ {
471
+ "id": 19500,
472
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/19500",
473
+ "metrics": {
474
+ "IoU": 0.1914633135713152,
475
+ "IoU X-axis": 0.39745155786545444,
476
+ "IoU Y-axis": 0.43185751864811167,
477
+ "Precision": 0.515209317949084,
478
+ "Recall": 0.2995254350570057,
479
+ "F1 Score": 0.2855874031853457
480
+ }
481
+ },
482
+ {
483
+ "id": 20000,
484
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/20000",
485
+ "metrics": {
486
+ "IoU": 0.18856521172947857,
487
+ "IoU X-axis": 0.4261171924482662,
488
+ "IoU Y-axis": 0.40614538480400597,
489
+ "Precision": 0.5349037883697967,
490
+ "Recall": 0.2760203737653936,
491
+ "F1 Score": 0.28035406807835
492
+ }
493
+ }
494
+ ]
MSE-v8_500/deamon_metrics_train500.json ADDED
@@ -0,0 +1,494 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": 500,
4
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/500",
5
+ "metrics": {
6
+ "IoU": 0.0607852700171914,
7
+ "IoU X-axis": 0.15178441921160865,
8
+ "IoU Y-axis": 0.16139931337934502,
9
+ "Precision": 0.1291351001216504,
10
+ "Recall": 0.11702542731925217,
11
+ "F1 Score": 0.09256301995369239
12
+ }
13
+ },
14
+ {
15
+ "id": 0,
16
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/0",
17
+ "metrics": {
18
+ "IoU": 0.05685002264518626,
19
+ "IoU X-axis": 0.14376179211002185,
20
+ "IoU Y-axis": 0.15940641804750258,
21
+ "Precision": 0.129168140071631,
22
+ "Recall": 0.1068343347186412,
23
+ "F1 Score": 0.08806122547167101
24
+ }
25
+ },
26
+ {
27
+ "id": 1000,
28
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/1000",
29
+ "metrics": {
30
+ "IoU": 0.05580205363935083,
31
+ "IoU X-axis": 0.13650587188277058,
32
+ "IoU Y-axis": 0.15925181427786192,
33
+ "Precision": 0.12237943920359248,
34
+ "Recall": 0.1006130164335385,
35
+ "F1 Score": 0.08456836560187685
36
+ }
37
+ },
38
+ {
39
+ "id": 1500,
40
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/1500",
41
+ "metrics": {
42
+ "IoU": 0.0600509138387318,
43
+ "IoU X-axis": 0.14924089306423668,
44
+ "IoU Y-axis": 0.15173701539664988,
45
+ "Precision": 0.14146296096172417,
46
+ "Recall": 0.10565210230684231,
47
+ "F1 Score": 0.09345748464509045
48
+ }
49
+ },
50
+ {
51
+ "id": 2000,
52
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/2000",
53
+ "metrics": {
54
+ "IoU": 0.0630548942194279,
55
+ "IoU X-axis": 0.1396671482791482,
56
+ "IoU Y-axis": 0.1820452969120934,
57
+ "Precision": 0.15298055976866365,
58
+ "Recall": 0.10639897665591931,
59
+ "F1 Score": 0.09632604610780499
60
+ }
61
+ },
62
+ {
63
+ "id": 2500,
64
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/2500",
65
+ "metrics": {
66
+ "IoU": 0.07035443261503505,
67
+ "IoU X-axis": 0.14017619487439037,
68
+ "IoU Y-axis": 0.20075356618207002,
69
+ "Precision": 0.15126753777530746,
70
+ "Recall": 0.13374609070512503,
71
+ "F1 Score": 0.10773859791931116
72
+ }
73
+ },
74
+ {
75
+ "id": 3000,
76
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/3000",
77
+ "metrics": {
78
+ "IoU": 0.05619282573859063,
79
+ "IoU X-axis": 0.12867971924176785,
80
+ "IoU Y-axis": 0.1694140032378731,
81
+ "Precision": 0.15193090909837623,
82
+ "Recall": 0.08782013853129092,
83
+ "F1 Score": 0.08866577027007283
84
+ }
85
+ },
86
+ {
87
+ "id": 3500,
88
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/3500",
89
+ "metrics": {
90
+ "IoU": 0.055169754866327664,
91
+ "IoU X-axis": 0.14324323699170963,
92
+ "IoU Y-axis": 0.145906967223906,
93
+ "Precision": 0.15179452480458755,
94
+ "Recall": 0.0885728458624773,
95
+ "F1 Score": 0.08700098392856868
96
+ }
97
+ },
98
+ {
99
+ "id": 4000,
100
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/4000",
101
+ "metrics": {
102
+ "IoU": 0.05304139609110143,
103
+ "IoU X-axis": 0.11775025059686688,
104
+ "IoU Y-axis": 0.17729378246211394,
105
+ "Precision": 0.14945468665691009,
106
+ "Recall": 0.08722715580699698,
107
+ "F1 Score": 0.08168278799179356
108
+ }
109
+ },
110
+ {
111
+ "id": 4500,
112
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/4500",
113
+ "metrics": {
114
+ "IoU": 0.04194447332787844,
115
+ "IoU X-axis": 0.10313724550664688,
116
+ "IoU Y-axis": 0.1591190176162311,
117
+ "Precision": 0.1523848976861699,
118
+ "Recall": 0.06446399840667698,
119
+ "F1 Score": 0.0667290690269042
120
+ }
121
+ },
122
+ {
123
+ "id": 5000,
124
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/5000",
125
+ "metrics": {
126
+ "IoU": 0.05104766298535363,
127
+ "IoU X-axis": 0.11292962322421761,
128
+ "IoU Y-axis": 0.17887358650060384,
129
+ "Precision": 0.14678168931249377,
130
+ "Recall": 0.0853371498917111,
131
+ "F1 Score": 0.07988472409114089
132
+ }
133
+ },
134
+ {
135
+ "id": 5500,
136
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/5500",
137
+ "metrics": {
138
+ "IoU": 0.048515283313162544,
139
+ "IoU X-axis": 0.12169728150752539,
140
+ "IoU Y-axis": 0.15298649901873507,
141
+ "Precision": 0.1402629293942355,
142
+ "Recall": 0.07465510010386067,
143
+ "F1 Score": 0.07583984337545896
144
+ }
145
+ },
146
+ {
147
+ "id": 6000,
148
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/6000",
149
+ "metrics": {
150
+ "IoU": 0.0630788482252231,
151
+ "IoU X-axis": 0.13729029978790766,
152
+ "IoU Y-axis": 0.17698412819707174,
153
+ "Precision": 0.14108850710746287,
154
+ "Recall": 0.1108970594464397,
155
+ "F1 Score": 0.09708549447127755
156
+ }
157
+ },
158
+ {
159
+ "id": 6500,
160
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/6500",
161
+ "metrics": {
162
+ "IoU": 0.06053485713322756,
163
+ "IoU X-axis": 0.12876462937272748,
164
+ "IoU Y-axis": 0.1706710568699383,
165
+ "Precision": 0.14189395303719488,
166
+ "Recall": 0.10795164588569064,
167
+ "F1 Score": 0.09286934671899394
168
+ }
169
+ },
170
+ {
171
+ "id": 7000,
172
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/7000",
173
+ "metrics": {
174
+ "IoU": 0.06129369578302763,
175
+ "IoU X-axis": 0.13203568384556527,
176
+ "IoU Y-axis": 0.18911041220217845,
177
+ "Precision": 0.14201186461844584,
178
+ "Recall": 0.1112444924017923,
179
+ "F1 Score": 0.09430692701335605
180
+ }
181
+ },
182
+ {
183
+ "id": 7500,
184
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/7500",
185
+ "metrics": {
186
+ "IoU": 0.05066782640539729,
187
+ "IoU X-axis": 0.11885901848542005,
188
+ "IoU Y-axis": 0.1749777031675486,
189
+ "Precision": 0.14857084841890042,
190
+ "Recall": 0.07953838155038254,
191
+ "F1 Score": 0.07952988627147477
192
+ }
193
+ },
194
+ {
195
+ "id": 8000,
196
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/8000",
197
+ "metrics": {
198
+ "IoU": 0.06110624506717144,
199
+ "IoU X-axis": 0.1347467614941592,
200
+ "IoU Y-axis": 0.17721238707907866,
201
+ "Precision": 0.14612149402783461,
202
+ "Recall": 0.11041333950631424,
203
+ "F1 Score": 0.09549613753596288
204
+ }
205
+ },
206
+ {
207
+ "id": 8500,
208
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/8500",
209
+ "metrics": {
210
+ "IoU": 0.05517064217852158,
211
+ "IoU X-axis": 0.12041310537715927,
212
+ "IoU Y-axis": 0.17840648222194366,
213
+ "Precision": 0.14990839752952548,
214
+ "Recall": 0.09037876043519744,
215
+ "F1 Score": 0.0867195138805944
216
+ }
217
+ },
218
+ {
219
+ "id": 9000,
220
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/9000",
221
+ "metrics": {
222
+ "IoU": 0.06343917191927638,
223
+ "IoU X-axis": 0.1329019139400965,
224
+ "IoU Y-axis": 0.1831192317511843,
225
+ "Precision": 0.1477862568961482,
226
+ "Recall": 0.11247870629263164,
227
+ "F1 Score": 0.09781702857294036
228
+ }
229
+ },
230
+ {
231
+ "id": 9500,
232
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/9500",
233
+ "metrics": {
234
+ "IoU": 0.06547534781646311,
235
+ "IoU X-axis": 0.13260650851315625,
236
+ "IoU Y-axis": 0.19065442482263312,
237
+ "Precision": 0.15297993313181968,
238
+ "Recall": 0.11419751095395332,
239
+ "F1 Score": 0.10081857491313684
240
+ }
241
+ },
242
+ {
243
+ "id": 10000,
244
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/10000",
245
+ "metrics": {
246
+ "IoU": 0.05719340798285019,
247
+ "IoU X-axis": 0.13260553781705772,
248
+ "IoU Y-axis": 0.1690505478701698,
249
+ "Precision": 0.14175694248112658,
250
+ "Recall": 0.09566945524688084,
251
+ "F1 Score": 0.08861187004611426
252
+ }
253
+ },
254
+ {
255
+ "id": 10500,
256
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/10500",
257
+ "metrics": {
258
+ "IoU": 0.06485635799869743,
259
+ "IoU X-axis": 0.1503247114304141,
260
+ "IoU Y-axis": 0.16936068070831575,
261
+ "Precision": 0.14384346802725634,
262
+ "Recall": 0.11718829208974736,
263
+ "F1 Score": 0.1003158402509028
264
+ }
265
+ },
266
+ {
267
+ "id": 11000,
268
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/11000",
269
+ "metrics": {
270
+ "IoU": 0.057854859127905514,
271
+ "IoU X-axis": 0.15268993319899,
272
+ "IoU Y-axis": 0.1506018711707987,
273
+ "Precision": 0.144759209972625,
274
+ "Recall": 0.09756171742911794,
275
+ "F1 Score": 0.09030860882143349
276
+ }
277
+ },
278
+ {
279
+ "id": 11500,
280
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/11500",
281
+ "metrics": {
282
+ "IoU": 0.06782959262434494,
283
+ "IoU X-axis": 0.1468686763441846,
284
+ "IoU Y-axis": 0.16528534989138507,
285
+ "Precision": 0.1432371288429415,
286
+ "Recall": 0.12017161729182299,
287
+ "F1 Score": 0.10398054191238323
288
+ }
289
+ },
290
+ {
291
+ "id": 12000,
292
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/12000",
293
+ "metrics": {
294
+ "IoU": 0.05538228639836877,
295
+ "IoU X-axis": 0.1338146624730743,
296
+ "IoU Y-axis": 0.1523928666794218,
297
+ "Precision": 0.1494483644637433,
298
+ "Recall": 0.09008099292652878,
299
+ "F1 Score": 0.0872516157667503
300
+ }
301
+ },
302
+ {
303
+ "id": 12500,
304
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/12500",
305
+ "metrics": {
306
+ "IoU": 0.056606721993580605,
307
+ "IoU X-axis": 0.13811549338364054,
308
+ "IoU Y-axis": 0.15164015843924003,
309
+ "Precision": 0.150883495796045,
310
+ "Recall": 0.09019744959358565,
311
+ "F1 Score": 0.08890883173199586
312
+ }
313
+ },
314
+ {
315
+ "id": 13000,
316
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/13000",
317
+ "metrics": {
318
+ "IoU": 0.04527808076042746,
319
+ "IoU X-axis": 0.11880031197027624,
320
+ "IoU Y-axis": 0.14270185470562416,
321
+ "Precision": 0.14551480040598658,
322
+ "Recall": 0.07247758536966313,
323
+ "F1 Score": 0.07311605195192888
324
+ }
325
+ },
326
+ {
327
+ "id": 13500,
328
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/13500",
329
+ "metrics": {
330
+ "IoU": 0.06213428936549827,
331
+ "IoU X-axis": 0.14296028635226823,
332
+ "IoU Y-axis": 0.16517027397260212,
333
+ "Precision": 0.1497700600537293,
334
+ "Recall": 0.1019592959373636,
335
+ "F1 Score": 0.09504983303168858
336
+ }
337
+ },
338
+ {
339
+ "id": 14000,
340
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/14000",
341
+ "metrics": {
342
+ "IoU": 0.05692437242106916,
343
+ "IoU X-axis": 0.1282793774917829,
344
+ "IoU Y-axis": 0.16045156324202162,
345
+ "Precision": 0.14418484607703372,
346
+ "Recall": 0.09610691383472565,
347
+ "F1 Score": 0.08844893597716658
348
+ }
349
+ },
350
+ {
351
+ "id": 14500,
352
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/14500",
353
+ "metrics": {
354
+ "IoU": 0.04750842143388468,
355
+ "IoU X-axis": 0.13397202921567455,
356
+ "IoU Y-axis": 0.1394221978148948,
357
+ "Precision": 0.1341837992355762,
358
+ "Recall": 0.077161108696745,
359
+ "F1 Score": 0.07485594129771773
360
+ }
361
+ },
362
+ {
363
+ "id": 15000,
364
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/15000",
365
+ "metrics": {
366
+ "IoU": 0.04079562318041693,
367
+ "IoU X-axis": 0.11845134171411091,
368
+ "IoU Y-axis": 0.13126974323394505,
369
+ "Precision": 0.1588735049686149,
370
+ "Recall": 0.05696209557530684,
371
+ "F1 Score": 0.06529867327980195
372
+ }
373
+ },
374
+ {
375
+ "id": 15500,
376
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/15500",
377
+ "metrics": {
378
+ "IoU": 0.04837183395733647,
379
+ "IoU X-axis": 0.1331174196044172,
380
+ "IoU Y-axis": 0.13497376202597974,
381
+ "Precision": 0.14307327783249524,
382
+ "Recall": 0.0698079366264875,
383
+ "F1 Score": 0.07621342716116092
384
+ }
385
+ },
386
+ {
387
+ "id": 16000,
388
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/16000",
389
+ "metrics": {
390
+ "IoU": 0.05573611242395049,
391
+ "IoU X-axis": 0.13841348223546424,
392
+ "IoU Y-axis": 0.15429319342284578,
393
+ "Precision": 0.16315096147732322,
394
+ "Recall": 0.08140934924339945,
395
+ "F1 Score": 0.08759482308436334
396
+ }
397
+ },
398
+ {
399
+ "id": 16500,
400
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/16500",
401
+ "metrics": {
402
+ "IoU": 0.05542210909302098,
403
+ "IoU X-axis": 0.13853557106079456,
404
+ "IoU Y-axis": 0.15028873468937065,
405
+ "Precision": 0.14926127123660812,
406
+ "Recall": 0.08520743125221807,
407
+ "F1 Score": 0.08564518483677264
408
+ }
409
+ },
410
+ {
411
+ "id": 17000,
412
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/17000",
413
+ "metrics": {
414
+ "IoU": 0.05583263472367675,
415
+ "IoU X-axis": 0.140521447991848,
416
+ "IoU Y-axis": 0.15319588107594295,
417
+ "Precision": 0.14052374244315283,
418
+ "Recall": 0.09114275786717818,
419
+ "F1 Score": 0.08586809891800798
420
+ }
421
+ },
422
+ {
423
+ "id": 17500,
424
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/17500",
425
+ "metrics": {
426
+ "IoU": 0.05410030106732123,
427
+ "IoU X-axis": 0.14084669926664936,
428
+ "IoU Y-axis": 0.15989167170371382,
429
+ "Precision": 0.1588916198271515,
430
+ "Recall": 0.08210491768136625,
431
+ "F1 Score": 0.0843676090435058
432
+ }
433
+ },
434
+ {
435
+ "id": 18000,
436
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/18000",
437
+ "metrics": {
438
+ "IoU": 0.05989994426853154,
439
+ "IoU X-axis": 0.14171854295379155,
440
+ "IoU Y-axis": 0.16508000246927412,
441
+ "Precision": 0.1499166830451333,
442
+ "Recall": 0.10084491411686411,
443
+ "F1 Score": 0.09120225762525498
444
+ }
445
+ },
446
+ {
447
+ "id": 18500,
448
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/18500",
449
+ "metrics": {
450
+ "IoU": 0.06038080963894347,
451
+ "IoU X-axis": 0.13702135445460856,
452
+ "IoU Y-axis": 0.16106738000926488,
453
+ "Precision": 0.15199515077126807,
454
+ "Recall": 0.1003876634065495,
455
+ "F1 Score": 0.09212957398048129
456
+ }
457
+ },
458
+ {
459
+ "id": 19000,
460
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/19000",
461
+ "metrics": {
462
+ "IoU": 0.052260423578186985,
463
+ "IoU X-axis": 0.1341748529339686,
464
+ "IoU Y-axis": 0.1509741518112611,
465
+ "Precision": 0.13892161251327387,
466
+ "Recall": 0.08297041317522538,
467
+ "F1 Score": 0.08080127367454225
468
+ }
469
+ },
470
+ {
471
+ "id": 19500,
472
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/19500",
473
+ "metrics": {
474
+ "IoU": 0.04962958072198959,
475
+ "IoU X-axis": 0.12880194098924072,
476
+ "IoU Y-axis": 0.14640764487738006,
477
+ "Precision": 0.12565141740233304,
478
+ "Recall": 0.08640932885468221,
479
+ "F1 Score": 0.07680902145124487
480
+ }
481
+ },
482
+ {
483
+ "id": 20000,
484
+ "ckpt_path": "./ckpts/Grounding_MSE/version_8/20000",
485
+ "metrics": {
486
+ "IoU": 0.056507157407369335,
487
+ "IoU X-axis": 0.1449164458683974,
488
+ "IoU Y-axis": 0.15348494293039547,
489
+ "Precision": 0.13661026141816032,
490
+ "Recall": 0.09686934656793803,
491
+ "F1 Score": 0.08662505893523831
492
+ }
493
+ }
494
+ ]
MSE-v8_500/hparams.yaml ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ cfg: !!python/object:__main__.Config
2
+ batch_size: 16
3
+ ckp_iterations_step: 500
4
+ emb_dim: 2048
5
+ exp_name: Grounding_MSE/version_8
6
+ grad_accum: 2
7
+ image_folder: data/
8
+ json_data_path: data/OMNIGROUND_stacked_train.json
9
+ learning_rate: 0.005
10
+ max_context_len: 2048
11
+ n_epochs: 1
12
+ num_devices:
13
+ - 0
14
+ - 1
15
+ - 2
16
+ - 3
17
+ num_workers: 16
18
+ original_ckp: ./OmniFusion/MicroOmnic
19
+ pad_id: 0
20
+ pretrain_path: ./ckpts/Grounding_MSE/version_4/104000
21
+ projection_num_head: 4
22
+ prompt: 'This is a dialog with AI assistant.
23
+
24
+ '
25
+ tokenizer_ckp: TinyLlama/TinyLlama-1.1B-Chat-v1.0
26
+ vision_emb_num: 576
tokenizer.model β†’ MSE-v8_500/model/grounding_head.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d12d52ed791f2c3d1b0fcde3ea4b222f4d768ce08c97745e0f7a017cf69fb2b
3
+ size 35586
projection.pt β†’ MSE-v8_500/model/projection.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2a66d5ba53ebdacc95529ad51abf6743561bfaabc793339a7317b40368f7209
3
- size 25205035
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382647da608ae5c5da62097cacabf4e1224870fc832127b51b017ec203da50d0
3
+ size 21007330
special_embeddings.pt β†’ MSE-v8_500/model/special_embeddings.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6df04f7e59cd1a04f3934854737b1dbed5c78bd2fe57d2f7ffb50cd15323f10f
3
- size 34337
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d908407470a948e31dbb19c2b7081f4b25f5a48a85e815978db1497605c04b5
3
+ size 18408
MSE-v8_500/model/tuned-model/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.37.1",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
MSE-v8_500/model/tuned-model/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.37.1"
7
+ }
model-00002-of-00003.safetensors β†’ MSE-v8_500/model/tuned-model/model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89fb88e53ddb470028c0e4148b3f11d03db415a5563ee74f3cf110e8b9338235
3
- size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c51f80f8e5d10e5503d3c85639a82efe96f4aac952066f4075591bfe09eeb57
3
+ size 2200119864
README.md DELETED
@@ -1,6 +0,0 @@
1
- ---
2
- library_name: transformers
3
- tags: []
4
- ---
5
-
6
- OmniMistral-7b_v3_9999
 
 
 
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,298 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 14483464192
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00003-of-00003.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
- "model.norm.weight": "model-00003-of-00003.safetensors"
297
- }
298
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
orig-v19_2000/deamon_metrics.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": 0,
4
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/0",
5
+ "metrics": {
6
+ "IoU": 0.30558388359434957,
7
+ "IoU X-axis": 0.43919762885602454,
8
+ "IoU Y-axis": 0.5771551423794644,
9
+ "Precision": 0.35319130896116774,
10
+ "Recall": 0.6307068699725886,
11
+ "F1 Score": 0.40719000961364343
12
+ }
13
+ },
14
+ {
15
+ "id": 1000,
16
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/1000",
17
+ "metrics": {
18
+ "IoU": 0.309035504056807,
19
+ "IoU X-axis": 0.42515315823640387,
20
+ "IoU Y-axis": 0.5899673850177798,
21
+ "Precision": 0.3475039779639078,
22
+ "Recall": 0.621760860487341,
23
+ "F1 Score": 0.40894976479315587
24
+ }
25
+ },
26
+ {
27
+ "id": 2000,
28
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/2000",
29
+ "metrics": {
30
+ "IoU": 0.311195036789808,
31
+ "IoU X-axis": 0.4216363926615186,
32
+ "IoU Y-axis": 0.6039929855090924,
33
+ "Precision": 0.3447932451661313,
34
+ "Recall": 0.6292984291647035,
35
+ "F1 Score": 0.40794990388703056
36
+ }
37
+ },
38
+ {
39
+ "id": 3000,
40
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/3000",
41
+ "metrics": {
42
+ "IoU": 0.26549898888332346,
43
+ "IoU X-axis": 0.39026351550930516,
44
+ "IoU Y-axis": 0.5503499038123383,
45
+ "Precision": 0.305574045651455,
46
+ "Recall": 0.5512903366107842,
47
+ "F1 Score": 0.3548486738679323
48
+ }
49
+ },
50
+ {
51
+ "id": 4000,
52
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/4000",
53
+ "metrics": {
54
+ "IoU": 0.29102050958810943,
55
+ "IoU X-axis": 0.415312529562027,
56
+ "IoU Y-axis": 0.571862043717228,
57
+ "Precision": 0.32325420377535274,
58
+ "Recall": 0.6021205048126106,
59
+ "F1 Score": 0.38194255446613723
60
+ }
61
+ },
62
+ {
63
+ "id": 5000,
64
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/5000",
65
+ "metrics": {
66
+ "IoU": 0.2673608894348029,
67
+ "IoU X-axis": 0.39306308258054257,
68
+ "IoU Y-axis": 0.5078254197006258,
69
+ "Precision": 0.3009487610204082,
70
+ "Recall": 0.5853196158471533,
71
+ "F1 Score": 0.3560805756193068
72
+ }
73
+ },
74
+ {
75
+ "id": 6000,
76
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/6000",
77
+ "metrics": {
78
+ "IoU": 0.28336261097386034,
79
+ "IoU X-axis": 0.4018478680029074,
80
+ "IoU Y-axis": 0.5504036593941035,
81
+ "Precision": 0.3196951494968821,
82
+ "Recall": 0.5977613250143989,
83
+ "F1 Score": 0.3746557316350878
84
+ }
85
+ },
86
+ {
87
+ "id": 7000,
88
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/7000",
89
+ "metrics": {
90
+ "IoU": 0.28589155302571845,
91
+ "IoU X-axis": 0.40171331578445885,
92
+ "IoU Y-axis": 0.559070086505551,
93
+ "Precision": 0.31699201404006044,
94
+ "Recall": 0.6105903057818016,
95
+ "F1 Score": 0.37753229671932914
96
+ }
97
+ },
98
+ {
99
+ "id": 8000,
100
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/8000",
101
+ "metrics": {
102
+ "IoU": 0.29793162665872247,
103
+ "IoU X-axis": 0.4056827059409615,
104
+ "IoU Y-axis": 0.567298900304166,
105
+ "Precision": 0.33686545021101033,
106
+ "Recall": 0.6012773408994075,
107
+ "F1 Score": 0.3929331720075697
108
+ }
109
+ },
110
+ {
111
+ "id": 9000,
112
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/9000",
113
+ "metrics": {
114
+ "IoU": 0.2883074533178669,
115
+ "IoU X-axis": 0.3940397012973179,
116
+ "IoU Y-axis": 0.5703466950173859,
117
+ "Precision": 0.3237723602050265,
118
+ "Recall": 0.5978776013547055,
119
+ "F1 Score": 0.3791110239323364
120
+ }
121
+ },
122
+ {
123
+ "id": -1,
124
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/",
125
+ "metrics": {
126
+ "IoU": 0.29048541285062546,
127
+ "IoU X-axis": 0.39995099846821025,
128
+ "IoU Y-axis": 0.567161254021535,
129
+ "Precision": 0.3279886289890401,
130
+ "Recall": 0.5969391439634957,
131
+ "F1 Score": 0.38318740304283244
132
+ }
133
+ }
134
+ ]
orig-v19_2000/deamon_metrics_train500.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "id": 0,
4
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/0",
5
+ "metrics": {
6
+ "IoU": 0.19054752535555794,
7
+ "IoU X-axis": 0.28681942746455724,
8
+ "IoU Y-axis": 0.6022778251933539,
9
+ "Precision": 0.21534548362169312,
10
+ "Recall": 0.4567113888196363,
11
+ "F1 Score": 0.2674302790495823
12
+ }
13
+ },
14
+ {
15
+ "id": 2000,
16
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/2000",
17
+ "metrics": {
18
+ "IoU": 0.18780749440700203,
19
+ "IoU X-axis": 0.27817969910159424,
20
+ "IoU Y-axis": 0.5889075903022304,
21
+ "Precision": 0.20816799045767195,
22
+ "Recall": 0.45156391465398893,
23
+ "F1 Score": 0.2618098038502784
24
+ }
25
+ },
26
+ {
27
+ "id": 1000,
28
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/1000",
29
+ "metrics": {
30
+ "IoU": 0.1971924264430956,
31
+ "IoU X-axis": 0.28950369484490435,
32
+ "IoU Y-axis": 0.607388895921615,
33
+ "Precision": 0.2190709213710317,
34
+ "Recall": 0.47313788247614175,
35
+ "F1 Score": 0.2742507735645332
36
+ }
37
+ },
38
+ {
39
+ "id": 4000,
40
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/4000",
41
+ "metrics": {
42
+ "IoU": 0.2049829374154959,
43
+ "IoU X-axis": 0.2939266234856933,
44
+ "IoU Y-axis": 0.5828849575284405,
45
+ "Precision": 0.23131935429872133,
46
+ "Recall": 0.4615848131405128,
47
+ "F1 Score": 0.28187240398378005
48
+ }
49
+ },
50
+ {
51
+ "id": 3000,
52
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/3000",
53
+ "metrics": {
54
+ "IoU": 0.2043638531265059,
55
+ "IoU X-axis": 0.3089586823572199,
56
+ "IoU Y-axis": 0.5722786518276325,
57
+ "Precision": 0.23112420296693123,
58
+ "Recall": 0.42781696760312354,
59
+ "F1 Score": 0.27762605684437364
60
+ }
61
+ },
62
+ {
63
+ "id": 5000,
64
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/5000",
65
+ "metrics": {
66
+ "IoU": 0.21551666942444136,
67
+ "IoU X-axis": 0.3045487713917804,
68
+ "IoU Y-axis": 0.5639674224737267,
69
+ "Precision": 0.23929817313646384,
70
+ "Recall": 0.47056124520281106,
71
+ "F1 Score": 0.2943689385029061
72
+ }
73
+ },
74
+ {
75
+ "id": 7000,
76
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/7000",
77
+ "metrics": {
78
+ "IoU": 0.2012155978825925,
79
+ "IoU X-axis": 0.28311230552390815,
80
+ "IoU Y-axis": 0.5608630030631204,
81
+ "Precision": 0.2241464813707168,
82
+ "Recall": 0.45346886836152545,
83
+ "F1 Score": 0.27534253439104794
84
+ }
85
+ },
86
+ {
87
+ "id": 6000,
88
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/6000",
89
+ "metrics": {
90
+ "IoU": 0.20760201996479652,
91
+ "IoU X-axis": 0.29627412343210746,
92
+ "IoU Y-axis": 0.5591573049200574,
93
+ "Precision": 0.23084833352040815,
94
+ "Recall": 0.46296489372466304,
95
+ "F1 Score": 0.2843427725472369
96
+ }
97
+ },
98
+ {
99
+ "id": 8000,
100
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/8000",
101
+ "metrics": {
102
+ "IoU": 0.19390211519740805,
103
+ "IoU X-axis": 0.274319166347376,
104
+ "IoU Y-axis": 0.5480837969383242,
105
+ "Precision": 0.21343772329509952,
106
+ "Recall": 0.4436095367103791,
107
+ "F1 Score": 0.26548999177150856
108
+ }
109
+ },
110
+ {
111
+ "id": -1,
112
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/",
113
+ "metrics": {
114
+ "IoU": 0.1985249935255598,
115
+ "IoU X-axis": 0.2800195628607395,
116
+ "IoU Y-axis": 0.549383595837675,
117
+ "Precision": 0.21833993114751826,
118
+ "Recall": 0.4474378103560755,
119
+ "F1 Score": 0.27070575675247904
120
+ }
121
+ },
122
+ {
123
+ "id": 9000,
124
+ "ckpt_path": "./ckpts/Grouning_1B/version_19/9000",
125
+ "metrics": {
126
+ "IoU": 0.20051535309376672,
127
+ "IoU X-axis": 0.2825724552829181,
128
+ "IoU Y-axis": 0.5540889652706387,
129
+ "Precision": 0.2199964456020723,
130
+ "Recall": 0.4532975833717852,
131
+ "F1 Score": 0.273948005749244
132
+ }
133
+ }
134
+ ]
orig-v19_2000/hparams.yaml ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ cfg: !!python/object:__main__.Config
2
+ batch_size: 8
3
+ ckp_iterations_step: 1000
4
+ emb_dim: 2048
5
+ exp_name: Grouning_1B/version_19
6
+ freeze: 2
7
+ grad_accum: 2
8
+ image_folder: data/
9
+ json_data_path: data/ref3rec_new_train_1digts.json
10
+ learning_rate: 0.002
11
+ max_context_len: 2048
12
+ model_ckp: TinyLlama/TinyLlama-1.1B-Chat-v1.0
13
+ n_epochs: 1
14
+ num_devices:
15
+ - 1
16
+ - 2
17
+ - 3
18
+ num_workers: 16
19
+ pad_id: 0
20
+ pretrain_path: ./ckpts/Grouning_1B/version_18/9000
21
+ projection_num_head: 4
22
+ prompt: 'This is a dialog with AI assistant.
23
+
24
+ '
25
+ vision_emb_num: 576
model-00001-of-00003.safetensors β†’ orig-v19_2000/model/projection.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:135c686d66fc875e6db8cfd742dbfb12db1afe796a11380e5da1f4506742b27b
3
- size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dcedb97def529dcaf2170a1a7658eded7b9bb16e20abb1e05f2e34763eef083
3
+ size 21007330
orig-v19_2000/model/special_embeddings.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd74d7d1340b47ba76f006ee94d5b74464d645b189c70f205003a85cd499796
3
+ size 18408
config.json β†’ orig-v19_2000/model/tuned-model/config.json RENAMED
@@ -1,23 +1,25 @@
1
  {
2
- "_name_or_path": "../ckpts/Grouning_0/version_6/44999/tuned-model",
3
  "architectures": [
4
- "MistralForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
  "hidden_act": "silu",
10
- "hidden_size": 4096,
11
  "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
  "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
 
18
  "rms_norm_eps": 1e-05,
 
19
  "rope_theta": 10000.0,
20
- "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.0",
 
1
  {
2
+ "_name_or_path": "./OmniFusion/MicroOmnic",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
  "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
  "rope_theta": 10000.0,
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.40.0",
generation_config.json β†’ orig-v19_2000/model/tuned-model/generation_config.json RENAMED
@@ -1,6 +1,7 @@
1
  {
2
- "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
 
 
5
  "transformers_version": "4.40.0"
6
  }
 
1
  {
 
2
  "bos_token_id": 1,
3
  "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
  "transformers_version": "4.40.0"
7
  }
model-00003-of-00003.safetensors β†’ orig-v19_2000/model/tuned-model/model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c887c73d47ef926ceaf521b23605f92a585f8272baddc1f2ab548489f1b0b05
3
- size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c51f80f8e5d10e5503d3c85639a82efe96f4aac952066f4075591bfe09eeb57
3
+ size 2200119864
special_tokens_map.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": true,
5
- "added_tokens_decoder": {
6
- "0": {
7
- "content": "<unk>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "1": {
15
- "content": "<s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "2": {
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": true
29
- }
30
- },
31
- "additional_special_tokens": [],
32
- "bos_token": "<s>",
33
- "clean_up_tokenization_spaces": false,
34
- "eos_token": "</s>",
35
- "legacy": true,
36
- "model_max_length": 1000000000000000019884624838656,
37
- "pad_token": null,
38
- "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
- "tokenizer_class": "LlamaTokenizer",
41
- "unk_token": "<unk>",
42
- "use_default_system_prompt": false
43
- }