zeromodels/deberta_v2_xlarge
05
1{2 "metadata": {3 "total_size": 4335387024.04 },5 "weight_map": {6 "/layers/deberta_v2_embeddings/layer_norm/vars": [7 "model_00000.weights.h5"8 ],9 "/layers/deberta_v2_embeddings/word_embeddings/vars": "model_00000.weights.h5",10 "/layers/deberta_v2_relative_embedding/vars": "model_00000.weights.h5",11 "/layers/layer_normalization/vars": [12 "model_00000.weights.h5"13 ],14 "/layers/deberta_v2_disentangled_self_attention/key_proj/vars": [15 "model_00000.weights.h5"16 ],17 "/layers/deberta_v2_disentangled_self_attention/query_proj/vars": [18 "model_00000.weights.h5"19 ],20 "/layers/deberta_v2_disentangled_self_attention/value_proj/vars": [21 "model_00000.weights.h5"22 ],23 "/layers/dense/vars": [24 "model_00000.weights.h5"25 ],26 "/layers/layer_normalization_1/vars": [27 "model_00000.weights.h5"28 ],29 "/layers/dense_1/vars": [30 "model_00000.weights.h5"31 ],32 "/layers/dense_2/vars": [33 "model_00000.weights.h5"34 ],35 "/layers/layer_normalization_2/vars": [36 "model_00000.weights.h5"37 ],38 "/layers/deberta_v2_conv_layer/conv/vars": [39 "model_00000.weights.h5"40 ],41 "/layers/deberta_v2_conv_layer/layer_norm/vars": [42 "model_00000.weights.h5"43 ],44 "/layers/deberta_v2_disentangled_self_attention_1/key_proj/vars": [45 "model_00000.weights.h5"46 ],47 "/layers/deberta_v2_disentangled_self_attention_1/query_proj/vars": [48 "model_00000.weights.h5"49 ],50 "/layers/deberta_v2_disentangled_self_attention_1/value_proj/vars": [51 "model_00000.weights.h5"52 ],53 "/layers/dense_3/vars": [54 "model_00000.weights.h5"55 ],56 "/layers/layer_normalization_3/vars": [57 "model_00000.weights.h5"58 ],59 "/layers/dense_4/vars": [60 "model_00000.weights.h5"61 ],62 "/layers/dense_5/vars": [63 "model_00000.weights.h5"64 ],65 "/layers/layer_normalization_4/vars": [66 "model_00000.weights.h5"67 ],68 "/layers/deberta_v2_disentangled_self_attention_2/key_proj/vars": [69 "model_00000.weights.h5"70 ],71 "/layers/deberta_v2_disentangled_self_attention_2/query_proj/vars": [72 "model_00000.weights.h5"73 ],74 "/layers/deberta_v2_disentangled_self_attention_2/value_proj/vars": [75 "model_00000.weights.h5"76 ],77 "/layers/dense_6/vars": [78 "model_00000.weights.h5"79 ],80 "/layers/layer_normalization_5/vars": [81 "model_00000.weights.h5"82 ],83 "/layers/dense_7/vars": [84 "model_00000.weights.h5"85 ],86 "/layers/dense_8/vars": [87 "model_00000.weights.h5"88 ],89 "/layers/layer_normalization_6/vars": [90 "model_00000.weights.h5"91 ],92 "/layers/deberta_v2_disentangled_self_attention_3/key_proj/vars": [93 "model_00000.weights.h5"94 ],95 "/layers/deberta_v2_disentangled_self_attention_3/query_proj/vars": [96 "model_00000.weights.h5"97 ],98 "/layers/deberta_v2_disentangled_self_attention_3/value_proj/vars": [99 "model_00000.weights.h5"100 ],101 "/layers/dense_9/vars": [102 "model_00000.weights.h5"103 ],104 "/layers/layer_normalization_7/vars": [105 "model_00000.weights.h5"106 ],107 "/layers/dense_10/vars": [108 "model_00000.weights.h5"109 ],110 "/layers/dense_11/vars": [111 "model_00000.weights.h5"112 ],113 "/layers/layer_normalization_8/vars": [114 "model_00000.weights.h5"115 ],116 "/layers/deberta_v2_disentangled_self_attention_4/key_proj/vars": [117 "model_00000.weights.h5"118 ],119 "/layers/deberta_v2_disentangled_self_attention_4/query_proj/vars": [120 "model_00000.weights.h5"121 ],122 "/layers/deberta_v2_disentangled_self_attention_4/value_proj/vars": [123 "model_00000.weights.h5"124 ],125 "/layers/dense_12/vars": [126 "model_00000.weights.h5"127 ],128 "/layers/layer_normalization_9/vars": [129 "model_00000.weights.h5"130 ],131 "/layers/dense_13/vars": [132 "model_00000.weights.h5"133 ],134 "/layers/dense_14/vars": [135 "model_00000.weights.h5"136 ],137 "/layers/layer_normalization_10/vars": [138 "model_00000.weights.h5"139 ],140 "/layers/deberta_v2_disentangled_self_attention_5/key_proj/vars": [141 "model_00000.weights.h5"142 ],143 "/layers/deberta_v2_disentangled_self_attention_5/query_proj/vars": [144 "model_00000.weights.h5"145 ],146 "/layers/deberta_v2_disentangled_self_attention_5/value_proj/vars": [147 "model_00000.weights.h5"148 ],149 "/layers/dense_15/vars": [150 "model_00000.weights.h5"151 ],152 "/layers/layer_normalization_11/vars": [153 "model_00000.weights.h5"154 ],155 "/layers/dense_16/vars": [156 "model_00000.weights.h5"157 ],158 "/layers/dense_17/vars": [159 "model_00000.weights.h5"160 ],161 "/layers/layer_normalization_12/vars": [162 "model_00000.weights.h5"163 ],164 "/layers/deberta_v2_disentangled_self_attention_6/key_proj/vars": [165 "model_00000.weights.h5"166 ],167 "/layers/deberta_v2_disentangled_self_attention_6/query_proj/vars": [168 "model_00000.weights.h5"169 ],170 "/layers/deberta_v2_disentangled_self_attention_6/value_proj/vars": [171 "model_00000.weights.h5"172 ],173 "/layers/dense_18/vars": [174 "model_00000.weights.h5"175 ],176 "/layers/layer_normalization_13/vars": [177 "model_00000.weights.h5"178 ],179 "/layers/dense_19/vars": [180 "model_00000.weights.h5"181 ],182 "/layers/dense_20/vars": [183 "model_00000.weights.h5"184 ],185 "/layers/layer_normalization_14/vars": [186 "model_00000.weights.h5"187 ],188 "/layers/deberta_v2_disentangled_self_attention_7/key_proj/vars": [189 "model_00000.weights.h5"190 ],191 "/layers/deberta_v2_disentangled_self_attention_7/query_proj/vars": [192 "model_00000.weights.h5"193 ],194 "/layers/deberta_v2_disentangled_self_attention_7/value_proj/vars": [195 "model_00000.weights.h5"196 ],197 "/layers/dense_21/vars": [198 "model_00000.weights.h5"199 ],200 "/layers/layer_normalization_15/vars": [201 "model_00000.weights.h5"202 ],203 "/layers/dense_22/vars": [204 "model_00000.weights.h5"205 ],206 "/layers/dense_23/vars": [207 "model_00000.weights.h5"208 ],209 "/layers/layer_normalization_16/vars": [210 "model_00000.weights.h5"211 ],212 "/layers/deberta_v2_disentangled_self_attention_8/key_proj/vars": [213 "model_00000.weights.h5"214 ],215 "/layers/deberta_v2_disentangled_self_attention_8/query_proj/vars": [216 "model_00000.weights.h5"217 ],218 "/layers/deberta_v2_disentangled_self_attention_8/value_proj/vars": [219 "model_00000.weights.h5"220 ],221 "/layers/dense_24/vars": [222 "model_00000.weights.h5"223 ],224 "/layers/layer_normalization_17/vars": [225 "model_00000.weights.h5"226 ],227 "/layers/dense_25/vars": [228 "model_00000.weights.h5"229 ],230 "/layers/dense_26/vars": [231 "model_00000.weights.h5"232 ],233 "/layers/layer_normalization_18/vars": [234 "model_00000.weights.h5"235 ],236 "/layers/deberta_v2_disentangled_self_attention_9/key_proj/vars": [237 "model_00000.weights.h5"238 ],239 "/layers/deberta_v2_disentangled_self_attention_9/query_proj/vars": [240 "model_00000.weights.h5"241 ],242 "/layers/deberta_v2_disentangled_self_attention_9/value_proj/vars": [243 "model_00000.weights.h5"244 ],245 "/layers/dense_27/vars": [246 "model_00000.weights.h5"247 ],248 "/layers/layer_normalization_19/vars": [249 "model_00000.weights.h5"250 ],251 "/layers/dense_28/vars": [252 "model_00000.weights.h5"253 ],254 "/layers/dense_29/vars": [255 "model_00000.weights.h5"256 ],257 "/layers/layer_normalization_20/vars": [258 "model_00000.weights.h5"259 ],260 "/layers/deberta_v2_disentangled_self_attention_10/key_proj/vars": [261 "model_00000.weights.h5"262 ],263 "/layers/deberta_v2_disentangled_self_attention_10/query_proj/vars": [264 "model_00000.weights.h5"265 ],266 "/layers/deberta_v2_disentangled_self_attention_10/value_proj/vars": [267 "model_00000.weights.h5"268 ],269 "/layers/dense_30/vars": [270 "model_00000.weights.h5"271 ],272 "/layers/layer_normalization_21/vars": [273 "model_00000.weights.h5"274 ],275 "/layers/dense_31/vars": [276 "model_00000.weights.h5"277 ],278 "/layers/dense_32/vars": [279 "model_00000.weights.h5"280 ],281 "/layers/layer_normalization_22/vars": [282 "model_00000.weights.h5"283 ],284 "/layers/deberta_v2_disentangled_self_attention_11/key_proj/vars": [285 "model_00000.weights.h5"286 ],287 "/layers/deberta_v2_disentangled_self_attention_11/query_proj/vars": [288 "model_00000.weights.h5"289 ],290 "/layers/deberta_v2_disentangled_self_attention_11/value_proj/vars": [291 "model_00000.weights.h5"292 ],293 "/layers/dense_33/vars": [294 "model_00000.weights.h5"295 ],296 "/layers/layer_normalization_23/vars": [297 "model_00000.weights.h5"298 ],299 "/layers/dense_34/vars": [300 "model_00000.weights.h5"301 ],302 "/layers/dense_35/vars": [303 "model_00000.weights.h5"304 ],305 "/layers/layer_normalization_24/vars": [306 "model_00000.weights.h5"307 ],308 "/layers/deberta_v2_disentangled_self_attention_12/key_proj/vars": [309 "model_00000.weights.h5"310 ],311 "/layers/deberta_v2_disentangled_self_attention_12/query_proj/vars": [312 "model_00000.weights.h5"313 ],314 "/layers/deberta_v2_disentangled_self_attention_12/value_proj/vars": [315 "model_00000.weights.h5"316 ],317 "/layers/dense_36/vars": [318 "model_00000.weights.h5"319 ],320 "/layers/layer_normalization_25/vars": [321 "model_00000.weights.h5"322 ],323 "/layers/dense_37/vars": [324 "model_00000.weights.h5"325 ],326 "/layers/dense_38/vars": [327 "model_00000.weights.h5"328 ],329 "/layers/layer_normalization_26/vars": [330 "model_00000.weights.h5"331 ],332 "/layers/deberta_v2_disentangled_self_attention_13/key_proj/vars": [333 "model_00000.weights.h5"334 ],335 "/layers/deberta_v2_disentangled_self_attention_13/query_proj/vars": [336 "model_00000.weights.h5"337 ],338 "/layers/deberta_v2_disentangled_self_attention_13/value_proj/vars": [339 "model_00000.weights.h5"340 ],341 "/layers/dense_39/vars": [342 "model_00000.weights.h5"343 ],344 "/layers/layer_normalization_27/vars": [345 "model_00000.weights.h5"346 ],347 "/layers/dense_40/vars": [348 "model_00000.weights.h5"349 ],350 "/layers/dense_41/vars": [351 "model_00000.weights.h5"352 ],353 "/layers/layer_normalization_28/vars": [354 "model_00000.weights.h5"355 ],356 "/layers/deberta_v2_disentangled_self_attention_14/key_proj/vars": [357 "model_00000.weights.h5"358 ],359 "/layers/deberta_v2_disentangled_self_attention_14/query_proj/vars": [360 "model_00000.weights.h5"361 ],362 "/layers/deberta_v2_disentangled_self_attention_14/value_proj/vars": [363 "model_00000.weights.h5"364 ],365 "/layers/dense_42/vars": [366 "model_00000.weights.h5"367 ],368 "/layers/layer_normalization_29/vars": [369 "model_00000.weights.h5"370 ],371 "/layers/dense_43/vars": [372 "model_00000.weights.h5"373 ],374 "/layers/dense_44/vars": [375 "model_00000.weights.h5"376 ],377 "/layers/layer_normalization_30/vars": [378 "model_00000.weights.h5"379 ],380 "/layers/deberta_v2_disentangled_self_attention_15/key_proj/vars": [381 "model_00000.weights.h5"382 ],383 "/layers/deberta_v2_disentangled_self_attention_15/query_proj/vars": [384 "model_00000.weights.h5"385 ],386 "/layers/deberta_v2_disentangled_self_attention_15/value_proj/vars": [387 "model_00000.weights.h5"388 ],389 "/layers/dense_45/vars": [390 "model_00000.weights.h5"391 ],392 "/layers/layer_normalization_31/vars": [393 "model_00000.weights.h5"394 ],395 "/layers/dense_46/vars": [396 "model_00000.weights.h5"397 ],398 "/layers/dense_47/vars": [399 "model_00000.weights.h5"400 ],401 "/layers/layer_normalization_32/vars": [402 "model_00000.weights.h5"403 ],404 "/layers/deberta_v2_disentangled_self_attention_16/key_proj/vars": [405 "model_00000.weights.h5"406 ],407 "/layers/deberta_v2_disentangled_self_attention_16/query_proj/vars": [408 "model_00000.weights.h5"409 ],410 "/layers/deberta_v2_disentangled_self_attention_16/value_proj/vars": [411 "model_00000.weights.h5"412 ],413 "/layers/dense_48/vars": [414 "model_00000.weights.h5"415 ],416 "/layers/layer_normalization_33/vars": [417 "model_00000.weights.h5"418 ],419 "/layers/dense_49/vars": [420 "model_00000.weights.h5"421 ],422 "/layers/dense_50/vars": [423 "model_00000.weights.h5"424 ],425 "/layers/layer_normalization_34/vars": [426 "model_00000.weights.h5"427 ],428 "/layers/deberta_v2_disentangled_self_attention_17/key_proj/vars": [429 "model_00000.weights.h5"430 ],431 "/layers/deberta_v2_disentangled_self_attention_17/query_proj/vars": [432 "model_00000.weights.h5"433 ],434 "/layers/deberta_v2_disentangled_self_attention_17/value_proj/vars": [435 "model_00000.weights.h5"436 ],437 "/layers/dense_51/vars": [438 "model_00000.weights.h5"439 ],440 "/layers/layer_normalization_35/vars": [441 "model_00000.weights.h5"442 ],443 "/layers/dense_52/vars": [444 "model_00000.weights.h5"445 ],446 "/layers/dense_53/vars": [447 "model_00000.weights.h5"448 ],449 "/layers/layer_normalization_36/vars": [450 "model_00000.weights.h5"451 ],452 "/layers/deberta_v2_disentangled_self_attention_18/key_proj/vars": [453 "model_00000.weights.h5"454 ],455 "/layers/deberta_v2_disentangled_self_attention_18/query_proj/vars": [456 "model_00000.weights.h5"457 ],458 "/layers/deberta_v2_disentangled_self_attention_18/value_proj/vars": [459 "model_00000.weights.h5"460 ],461 "/layers/dense_54/vars": [462 "model_00000.weights.h5"463 ],464 "/layers/layer_normalization_37/vars": [465 "model_00000.weights.h5"466 ],467 "/layers/dense_55/vars": [468 "model_00000.weights.h5"469 ],470 "/layers/dense_56/vars": [471 "model_00000.weights.h5"472 ],473 "/layers/layer_normalization_38/vars": [474 "model_00000.weights.h5"475 ],476 "/layers/deberta_v2_disentangled_self_attention_19/key_proj/vars": [477 "model_00000.weights.h5"478 ],479 "/layers/deberta_v2_disentangled_self_attention_19/query_proj/vars": [480 "model_00000.weights.h5"481 ],482 "/layers/deberta_v2_disentangled_self_attention_19/value_proj/vars": [483 "model_00000.weights.h5"484 ],485 "/layers/dense_57/vars": [486 "model_00000.weights.h5"487 ],488 "/layers/layer_normalization_39/vars": [489 "model_00000.weights.h5"490 ],491 "/layers/dense_58/vars": [492 "model_00000.weights.h5"493 ],494 "/layers/dense_59/vars": [495 "model_00000.weights.h5"496 ],497 "/layers/layer_normalization_40/vars": [498 "model_00000.weights.h5"499 ],500 "/layers/deberta_v2_disentangled_self_attention_20/key_proj/vars": [501 "model_00000.weights.h5"502 ],503 "/layers/deberta_v2_disentangled_self_attention_20/query_proj/vars": [504 "model_00000.weights.h5"505 ],506 "/layers/deberta_v2_disentangled_self_attention_20/value_proj/vars": [507 "model_00000.weights.h5"508 ],509 "/layers/dense_60/vars": [510 "model_00000.weights.h5"511 ],512 "/layers/layer_normalization_41/vars": [513 "model_00000.weights.h5"514 ],515 "/layers/dense_61/vars": [516 "model_00000.weights.h5"517 ],518 "/layers/dense_62/vars": [519 "model_00000.weights.h5"520 ],521 "/layers/layer_normalization_42/vars": [522 "model_00000.weights.h5"523 ],524 "/layers/deberta_v2_disentangled_self_attention_21/key_proj/vars": [525 "model_00000.weights.h5"526 ],527 "/layers/deberta_v2_disentangled_self_attention_21/query_proj/vars": [528 "model_00000.weights.h5"529 ],530 "/layers/deberta_v2_disentangled_self_attention_21/value_proj/vars": [531 "model_00000.weights.h5"532 ],533 "/layers/dense_63/vars": [534 "model_00000.weights.h5"535 ],536 "/layers/layer_normalization_43/vars": [537 "model_00000.weights.h5"538 ],539 "/layers/dense_64/vars": [540 "model_00000.weights.h5"541 ],542 "/layers/dense_65/vars": [543 "model_00000.weights.h5"544 ],545 "/layers/layer_normalization_44/vars": [546 "model_00000.weights.h5"547 ],548 "/layers/deberta_v2_disentangled_self_attention_22/key_proj/vars": [549 "model_00000.weights.h5"550 ],551 "/layers/deberta_v2_disentangled_self_attention_22/query_proj/vars": [552 "model_00000.weights.h5"553 ],554 "/layers/deberta_v2_disentangled_self_attention_22/value_proj/vars": [555 "model_00000.weights.h5"556 ],557 "/layers/dense_66/vars": [558 "model_00000.weights.h5"559 ],560 "/layers/layer_normalization_45/vars": [561 "model_00000.weights.h5"562 ],563 "/layers/dense_67/vars": [564 "model_00000.weights.h5"565 ],566 "/layers/dense_68/vars": [567 "model_00000.weights.h5"568 ],569 "/layers/layer_normalization_46/vars": [570 "model_00000.weights.h5"571 ],572 "/layers/deberta_v2_disentangled_self_attention_23/key_proj/vars": [573 "model_00000.weights.h5"574 ],575 "/layers/deberta_v2_disentangled_self_attention_23/query_proj/vars": [576 "model_00000.weights.h5"577 ],578 "/layers/deberta_v2_disentangled_self_attention_23/value_proj/vars": [579 "model_00000.weights.h5"580 ],581 "/layers/dense_69/vars": [582 "model_00000.weights.h5"583 ],584 "/layers/layer_normalization_47/vars": [585 "model_00000.weights.h5"586 ],587 "/layers/dense_70/vars": [588 "model_00000.weights.h5"589 ],590 "/layers/dense_71/vars": [591 "model_00000.weights.h5"592 ],593 "/layers/layer_normalization_48/vars": [594 "model_00000.weights.h5"595 ],596 "/layers/dense_72/vars": [597 "model_00000.weights.h5"598 ],599 "/layers/layer_normalization_49/vars": [600 "model_00000.weights.h5"601 ],602 "/layers/dense_73/vars": [603 "model_00001.weights.h5"604 ]605 }606}