Upload folder using huggingface_hub
Browse files- act_dict.json +3 -2290
- config.json +3 -50
- default_qcfg.json +0 -0
- generation_config.json +3 -7
- results.json +3 -24
- special_tokens_map.json +3 -30
- tokenizer_config.json +3 -44
act_dict.json
CHANGED
|
@@ -1,2290 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
-0.22867023944854736,
|
| 5 |
-
1.1115107536315918
|
| 6 |
-
],
|
| 7 |
-
"output": [
|
| 8 |
-
-2.1261632442474365,
|
| 9 |
-
3.831766366958618
|
| 10 |
-
]
|
| 11 |
-
},
|
| 12 |
-
"model.layers.0.mlp.act_fn": {
|
| 13 |
-
"input2": [
|
| 14 |
-
2.046371889719012e-07,
|
| 15 |
-
0.7579811811447144
|
| 16 |
-
],
|
| 17 |
-
"output": [
|
| 18 |
-
-0.2726189196109772,
|
| 19 |
-
1.9698854684829712
|
| 20 |
-
]
|
| 21 |
-
},
|
| 22 |
-
"model.layers.0.mlp.w1": {
|
| 23 |
-
"output": [
|
| 24 |
-
-1.3973281383514404,
|
| 25 |
-
1.1478052139282227
|
| 26 |
-
]
|
| 27 |
-
},
|
| 28 |
-
"model.layers.0.mlp.w2": {
|
| 29 |
-
"input": [
|
| 30 |
-
-0.19404251873493195,
|
| 31 |
-
0.20824076235294342
|
| 32 |
-
],
|
| 33 |
-
"output": [
|
| 34 |
-
-0.6336596012115479,
|
| 35 |
-
0.544675350189209
|
| 36 |
-
]
|
| 37 |
-
},
|
| 38 |
-
"model.layers.0.mlp.w3": {
|
| 39 |
-
"output": [
|
| 40 |
-
-0.6615440845489502,
|
| 41 |
-
0.7680639028549194
|
| 42 |
-
]
|
| 43 |
-
},
|
| 44 |
-
"model.layers.0.post_attention_layernorm": {
|
| 45 |
-
"input": [
|
| 46 |
-
-0.5048871040344238,
|
| 47 |
-
0.5236737728118896
|
| 48 |
-
],
|
| 49 |
-
"output": [
|
| 50 |
-
-0.925523042678833,
|
| 51 |
-
0.7021209001541138
|
| 52 |
-
]
|
| 53 |
-
},
|
| 54 |
-
"model.layers.0.self_attn.k_proj": {
|
| 55 |
-
"output": [
|
| 56 |
-
-16.452835083007812,
|
| 57 |
-
6.599212646484375
|
| 58 |
-
]
|
| 59 |
-
},
|
| 60 |
-
"model.layers.0.self_attn.o_proj": {
|
| 61 |
-
"output": [
|
| 62 |
-
-0.5184494256973267,
|
| 63 |
-
0.46981656551361084
|
| 64 |
-
]
|
| 65 |
-
},
|
| 66 |
-
"model.layers.0.self_attn.pv_bmm": {
|
| 67 |
-
"input": [
|
| 68 |
-
-5.756418258728857e-11,
|
| 69 |
-
4.316623210906982
|
| 70 |
-
],
|
| 71 |
-
"input2": [
|
| 72 |
-
-0.23561592400074005,
|
| 73 |
-
0.33119601011276245
|
| 74 |
-
],
|
| 75 |
-
"output": [
|
| 76 |
-
-0.21975915133953094,
|
| 77 |
-
0.3089066743850708
|
| 78 |
-
]
|
| 79 |
-
},
|
| 80 |
-
"model.layers.0.self_attn.q_proj": {
|
| 81 |
-
"output": [
|
| 82 |
-
-9.491658210754395,
|
| 83 |
-
14.472428321838379
|
| 84 |
-
]
|
| 85 |
-
},
|
| 86 |
-
"model.layers.0.self_attn.qk_bmm": {
|
| 87 |
-
"input": [
|
| 88 |
-
-15.129252433776855,
|
| 89 |
-
15.248381614685059
|
| 90 |
-
],
|
| 91 |
-
"input2": [
|
| 92 |
-
-16.292478561401367,
|
| 93 |
-
16.165193557739258
|
| 94 |
-
],
|
| 95 |
-
"output": [
|
| 96 |
-
-350.88092041015625,
|
| 97 |
-
296.008544921875
|
| 98 |
-
]
|
| 99 |
-
},
|
| 100 |
-
"model.layers.0.self_attn.v_proj": {
|
| 101 |
-
"output": [
|
| 102 |
-
-0.23130042850971222,
|
| 103 |
-
0.3251298666000366
|
| 104 |
-
]
|
| 105 |
-
},
|
| 106 |
-
"model.layers.1.input_layernorm": {
|
| 107 |
-
"input": [
|
| 108 |
-
-0.6882500052452087,
|
| 109 |
-
0.5670577883720398
|
| 110 |
-
],
|
| 111 |
-
"output": [
|
| 112 |
-
-1.9846813678741455,
|
| 113 |
-
1.2388458251953125
|
| 114 |
-
]
|
| 115 |
-
},
|
| 116 |
-
"model.layers.1.mlp.act_fn": {
|
| 117 |
-
"input2": [
|
| 118 |
-
0.0,
|
| 119 |
-
0.7920277714729309
|
| 120 |
-
],
|
| 121 |
-
"output": [
|
| 122 |
-
-0.2325526624917984,
|
| 123 |
-
1.414695143699646
|
| 124 |
-
]
|
| 125 |
-
},
|
| 126 |
-
"model.layers.1.mlp.w1": {
|
| 127 |
-
"output": [
|
| 128 |
-
-1.9397541284561157,
|
| 129 |
-
1.1908618211746216
|
| 130 |
-
]
|
| 131 |
-
},
|
| 132 |
-
"model.layers.1.mlp.w2": {
|
| 133 |
-
"input": [
|
| 134 |
-
-0.19818152487277985,
|
| 135 |
-
0.3571622967720032
|
| 136 |
-
],
|
| 137 |
-
"output": [
|
| 138 |
-
-0.4769497513771057,
|
| 139 |
-
0.557122528553009
|
| 140 |
-
]
|
| 141 |
-
},
|
| 142 |
-
"model.layers.1.mlp.w3": {
|
| 143 |
-
"output": [
|
| 144 |
-
-0.8463128209114075,
|
| 145 |
-
0.9521018862724304
|
| 146 |
-
]
|
| 147 |
-
},
|
| 148 |
-
"model.layers.1.post_attention_layernorm": {
|
| 149 |
-
"input": [
|
| 150 |
-
-0.4584429860115051,
|
| 151 |
-
0.3836226463317871
|
| 152 |
-
],
|
| 153 |
-
"output": [
|
| 154 |
-
-0.4750775098800659,
|
| 155 |
-
0.45680534839630127
|
| 156 |
-
]
|
| 157 |
-
},
|
| 158 |
-
"model.layers.1.self_attn.k_proj": {
|
| 159 |
-
"output": [
|
| 160 |
-
-10.099939346313477,
|
| 161 |
-
9.865056991577148
|
| 162 |
-
]
|
| 163 |
-
},
|
| 164 |
-
"model.layers.1.self_attn.o_proj": {
|
| 165 |
-
"output": [
|
| 166 |
-
-0.19676999747753143,
|
| 167 |
-
0.458579957485199
|
| 168 |
-
]
|
| 169 |
-
},
|
| 170 |
-
"model.layers.1.self_attn.pv_bmm": {
|
| 171 |
-
"input": [
|
| 172 |
-
-2.383558073137948e-10,
|
| 173 |
-
3.8818066120147705
|
| 174 |
-
],
|
| 175 |
-
"input2": [
|
| 176 |
-
-0.5660212635993958,
|
| 177 |
-
0.6268333792686462
|
| 178 |
-
],
|
| 179 |
-
"output": [
|
| 180 |
-
-0.2186438888311386,
|
| 181 |
-
0.2836461067199707
|
| 182 |
-
]
|
| 183 |
-
},
|
| 184 |
-
"model.layers.1.self_attn.q_proj": {
|
| 185 |
-
"output": [
|
| 186 |
-
-6.189110279083252,
|
| 187 |
-
6.045177936553955
|
| 188 |
-
]
|
| 189 |
-
},
|
| 190 |
-
"model.layers.1.self_attn.qk_bmm": {
|
| 191 |
-
"input": [
|
| 192 |
-
-6.714675426483154,
|
| 193 |
-
6.662216663360596
|
| 194 |
-
],
|
| 195 |
-
"input2": [
|
| 196 |
-
-9.725031852722168,
|
| 197 |
-
9.801608085632324
|
| 198 |
-
],
|
| 199 |
-
"output": [
|
| 200 |
-
-283.8371887207031,
|
| 201 |
-
185.15756225585938
|
| 202 |
-
]
|
| 203 |
-
},
|
| 204 |
-
"model.layers.1.self_attn.v_proj": {
|
| 205 |
-
"output": [
|
| 206 |
-
-0.556850016117096,
|
| 207 |
-
0.6166768670082092
|
| 208 |
-
]
|
| 209 |
-
},
|
| 210 |
-
"model.layers.10.input_layernorm": {
|
| 211 |
-
"input": [
|
| 212 |
-
-99.1098861694336,
|
| 213 |
-
11.07666015625
|
| 214 |
-
],
|
| 215 |
-
"output": [
|
| 216 |
-
-1.4399017095565796,
|
| 217 |
-
1.4974979162216187
|
| 218 |
-
]
|
| 219 |
-
},
|
| 220 |
-
"model.layers.10.mlp.act_fn": {
|
| 221 |
-
"input2": [
|
| 222 |
-
3.426980811127578e-06,
|
| 223 |
-
0.9152793288230896
|
| 224 |
-
],
|
| 225 |
-
"output": [
|
| 226 |
-
-0.2603260576725006,
|
| 227 |
-
4.84480619430542
|
| 228 |
-
]
|
| 229 |
-
},
|
| 230 |
-
"model.layers.10.mlp.w1": {
|
| 231 |
-
"output": [
|
| 232 |
-
-3.465219497680664,
|
| 233 |
-
2.4651899337768555
|
| 234 |
-
]
|
| 235 |
-
},
|
| 236 |
-
"model.layers.10.mlp.w2": {
|
| 237 |
-
"input": [
|
| 238 |
-
-0.282131165266037,
|
| 239 |
-
0.384011834859848
|
| 240 |
-
],
|
| 241 |
-
"output": [
|
| 242 |
-
-1.5551173686981201,
|
| 243 |
-
1.1471128463745117
|
| 244 |
-
]
|
| 245 |
-
},
|
| 246 |
-
"model.layers.10.mlp.w3": {
|
| 247 |
-
"output": [
|
| 248 |
-
-0.7345466017723083,
|
| 249 |
-
0.6632845997810364
|
| 250 |
-
]
|
| 251 |
-
},
|
| 252 |
-
"model.layers.10.post_attention_layernorm": {
|
| 253 |
-
"input": [
|
| 254 |
-
-44.71582794189453,
|
| 255 |
-
4.991600036621094
|
| 256 |
-
],
|
| 257 |
-
"output": [
|
| 258 |
-
-0.597541868686676,
|
| 259 |
-
0.8133209347724915
|
| 260 |
-
]
|
| 261 |
-
},
|
| 262 |
-
"model.layers.10.self_attn.k_proj": {
|
| 263 |
-
"output": [
|
| 264 |
-
-18.501943588256836,
|
| 265 |
-
14.959020614624023
|
| 266 |
-
]
|
| 267 |
-
},
|
| 268 |
-
"model.layers.10.self_attn.o_proj": {
|
| 269 |
-
"output": [
|
| 270 |
-
-1.499884009361267,
|
| 271 |
-
0.9227837324142456
|
| 272 |
-
]
|
| 273 |
-
},
|
| 274 |
-
"model.layers.10.self_attn.pv_bmm": {
|
| 275 |
-
"input": [
|
| 276 |
-
0.0,
|
| 277 |
-
10.06771469116211
|
| 278 |
-
],
|
| 279 |
-
"input2": [
|
| 280 |
-
-0.9095252752304077,
|
| 281 |
-
1.0232160091400146
|
| 282 |
-
],
|
| 283 |
-
"output": [
|
| 284 |
-
-0.5237104892730713,
|
| 285 |
-
0.6686661243438721
|
| 286 |
-
]
|
| 287 |
-
},
|
| 288 |
-
"model.layers.10.self_attn.q_proj": {
|
| 289 |
-
"output": [
|
| 290 |
-
-9.523984909057617,
|
| 291 |
-
10.38270378112793
|
| 292 |
-
]
|
| 293 |
-
},
|
| 294 |
-
"model.layers.10.self_attn.qk_bmm": {
|
| 295 |
-
"input": [
|
| 296 |
-
-10.853270530700684,
|
| 297 |
-
9.348071098327637
|
| 298 |
-
],
|
| 299 |
-
"input2": [
|
| 300 |
-
-18.354463577270508,
|
| 301 |
-
17.64851951599121
|
| 302 |
-
],
|
| 303 |
-
"output": [
|
| 304 |
-
-338.5840148925781,
|
| 305 |
-
253.34640502929688
|
| 306 |
-
]
|
| 307 |
-
},
|
| 308 |
-
"model.layers.10.self_attn.v_proj": {
|
| 309 |
-
"output": [
|
| 310 |
-
-0.9095847010612488,
|
| 311 |
-
1.023282766342163
|
| 312 |
-
]
|
| 313 |
-
},
|
| 314 |
-
"model.layers.11.input_layernorm": {
|
| 315 |
-
"input": [
|
| 316 |
-
-101.14524841308594,
|
| 317 |
-
11.28887939453125
|
| 318 |
-
],
|
| 319 |
-
"output": [
|
| 320 |
-
-1.5151044130325317,
|
| 321 |
-
1.873944878578186
|
| 322 |
-
]
|
| 323 |
-
},
|
| 324 |
-
"model.layers.11.mlp.act_fn": {
|
| 325 |
-
"input2": [
|
| 326 |
-
3.2362688671128126e-06,
|
| 327 |
-
0.9267445206642151
|
| 328 |
-
],
|
| 329 |
-
"output": [
|
| 330 |
-
-0.2646248936653137,
|
| 331 |
-
4.923959732055664
|
| 332 |
-
]
|
| 333 |
-
},
|
| 334 |
-
"model.layers.11.mlp.w1": {
|
| 335 |
-
"output": [
|
| 336 |
-
-3.655752658843994,
|
| 337 |
-
2.5590267181396484
|
| 338 |
-
]
|
| 339 |
-
},
|
| 340 |
-
"model.layers.11.mlp.w2": {
|
| 341 |
-
"input": [
|
| 342 |
-
-0.3750685453414917,
|
| 343 |
-
0.3230517506599426
|
| 344 |
-
],
|
| 345 |
-
"output": [
|
| 346 |
-
-1.2398120164871216,
|
| 347 |
-
0.937217116355896
|
| 348 |
-
]
|
| 349 |
-
},
|
| 350 |
-
"model.layers.11.mlp.w3": {
|
| 351 |
-
"output": [
|
| 352 |
-
-0.6163890361785889,
|
| 353 |
-
0.6410446166992188
|
| 354 |
-
]
|
| 355 |
-
},
|
| 356 |
-
"model.layers.11.post_attention_layernorm": {
|
| 357 |
-
"input": [
|
| 358 |
-
-77.12692260742188,
|
| 359 |
-
8.598007202148438
|
| 360 |
-
],
|
| 361 |
-
"output": [
|
| 362 |
-
-0.8170561790466309,
|
| 363 |
-
0.9191882610321045
|
| 364 |
-
]
|
| 365 |
-
},
|
| 366 |
-
"model.layers.11.self_attn.k_proj": {
|
| 367 |
-
"output": [
|
| 368 |
-
-22.057157516479492,
|
| 369 |
-
19.91728401184082
|
| 370 |
-
]
|
| 371 |
-
},
|
| 372 |
-
"model.layers.11.self_attn.o_proj": {
|
| 373 |
-
"output": [
|
| 374 |
-
-1.0617130994796753,
|
| 375 |
-
1.217335820198059
|
| 376 |
-
]
|
| 377 |
-
},
|
| 378 |
-
"model.layers.11.self_attn.pv_bmm": {
|
| 379 |
-
"input": [
|
| 380 |
-
0.0,
|
| 381 |
-
20.30547332763672
|
| 382 |
-
],
|
| 383 |
-
"input2": [
|
| 384 |
-
-1.1099920272827148,
|
| 385 |
-
1.2887194156646729
|
| 386 |
-
],
|
| 387 |
-
"output": [
|
| 388 |
-
-0.921210527420044,
|
| 389 |
-
0.7567086219787598
|
| 390 |
-
]
|
| 391 |
-
},
|
| 392 |
-
"model.layers.11.self_attn.q_proj": {
|
| 393 |
-
"output": [
|
| 394 |
-
-11.205497741699219,
|
| 395 |
-
10.441486358642578
|
| 396 |
-
]
|
| 397 |
-
},
|
| 398 |
-
"model.layers.11.self_attn.qk_bmm": {
|
| 399 |
-
"input": [
|
| 400 |
-
-10.428231239318848,
|
| 401 |
-
10.510344505310059
|
| 402 |
-
],
|
| 403 |
-
"input2": [
|
| 404 |
-
-22.121395111083984,
|
| 405 |
-
19.97528839111328
|
| 406 |
-
],
|
| 407 |
-
"output": [
|
| 408 |
-
-381.7677917480469,
|
| 409 |
-
238.34701538085938
|
| 410 |
-
]
|
| 411 |
-
},
|
| 412 |
-
"model.layers.11.self_attn.v_proj": {
|
| 413 |
-
"output": [
|
| 414 |
-
-1.1099989414215088,
|
| 415 |
-
1.2887275218963623
|
| 416 |
-
]
|
| 417 |
-
},
|
| 418 |
-
"model.layers.12.input_layernorm": {
|
| 419 |
-
"input": [
|
| 420 |
-
-99.4482650756836,
|
| 421 |
-
11.078857421875
|
| 422 |
-
],
|
| 423 |
-
"output": [
|
| 424 |
-
-1.569658875465393,
|
| 425 |
-
1.8513926267623901
|
| 426 |
-
]
|
| 427 |
-
},
|
| 428 |
-
"model.layers.12.mlp.act_fn": {
|
| 429 |
-
"input2": [
|
| 430 |
-
2.2228719842587452e-07,
|
| 431 |
-
0.9314825534820557
|
| 432 |
-
],
|
| 433 |
-
"output": [
|
| 434 |
-
-0.2631029188632965,
|
| 435 |
-
6.441186904907227
|
| 436 |
-
]
|
| 437 |
-
},
|
| 438 |
-
"model.layers.12.mlp.w1": {
|
| 439 |
-
"output": [
|
| 440 |
-
-3.6479241847991943,
|
| 441 |
-
3.3462159633636475
|
| 442 |
-
]
|
| 443 |
-
},
|
| 444 |
-
"model.layers.12.mlp.w2": {
|
| 445 |
-
"input": [
|
| 446 |
-
-0.4353678822517395,
|
| 447 |
-
0.3869936466217041
|
| 448 |
-
],
|
| 449 |
-
"output": [
|
| 450 |
-
-1.3589602708816528,
|
| 451 |
-
1.455013632774353
|
| 452 |
-
]
|
| 453 |
-
},
|
| 454 |
-
"model.layers.12.mlp.w3": {
|
| 455 |
-
"output": [
|
| 456 |
-
-0.8044908046722412,
|
| 457 |
-
0.5105422735214233
|
| 458 |
-
]
|
| 459 |
-
},
|
| 460 |
-
"model.layers.12.post_attention_layernorm": {
|
| 461 |
-
"input": [
|
| 462 |
-
-62.470062255859375,
|
| 463 |
-
6.949943542480469
|
| 464 |
-
],
|
| 465 |
-
"output": [
|
| 466 |
-
-1.0635490417480469,
|
| 467 |
-
1.0388154983520508
|
| 468 |
-
]
|
| 469 |
-
},
|
| 470 |
-
"model.layers.12.self_attn.k_proj": {
|
| 471 |
-
"output": [
|
| 472 |
-
-21.62252426147461,
|
| 473 |
-
17.76136016845703
|
| 474 |
-
]
|
| 475 |
-
},
|
| 476 |
-
"model.layers.12.self_attn.o_proj": {
|
| 477 |
-
"output": [
|
| 478 |
-
-0.8174425363540649,
|
| 479 |
-
0.9816339015960693
|
| 480 |
-
]
|
| 481 |
-
},
|
| 482 |
-
"model.layers.12.self_attn.pv_bmm": {
|
| 483 |
-
"input": [
|
| 484 |
-
0.0,
|
| 485 |
-
6.8579325675964355
|
| 486 |
-
],
|
| 487 |
-
"input2": [
|
| 488 |
-
-1.3389040231704712,
|
| 489 |
-
1.4144874811172485
|
| 490 |
-
],
|
| 491 |
-
"output": [
|
| 492 |
-
-0.7504150867462158,
|
| 493 |
-
0.6463429927825928
|
| 494 |
-
]
|
| 495 |
-
},
|
| 496 |
-
"model.layers.12.self_attn.q_proj": {
|
| 497 |
-
"output": [
|
| 498 |
-
-7.999295234680176,
|
| 499 |
-
9.738272666931152
|
| 500 |
-
]
|
| 501 |
-
},
|
| 502 |
-
"model.layers.12.self_attn.qk_bmm": {
|
| 503 |
-
"input": [
|
| 504 |
-
-7.916897296905518,
|
| 505 |
-
9.486627578735352
|
| 506 |
-
],
|
| 507 |
-
"input2": [
|
| 508 |
-
-21.433029174804688,
|
| 509 |
-
17.886558532714844
|
| 510 |
-
],
|
| 511 |
-
"output": [
|
| 512 |
-
-259.88922119140625,
|
| 513 |
-
216.72589111328125
|
| 514 |
-
]
|
| 515 |
-
},
|
| 516 |
-
"model.layers.12.self_attn.v_proj": {
|
| 517 |
-
"output": [
|
| 518 |
-
-1.3148822784423828,
|
| 519 |
-
1.3891096115112305
|
| 520 |
-
]
|
| 521 |
-
},
|
| 522 |
-
"model.layers.13.input_layernorm": {
|
| 523 |
-
"input": [
|
| 524 |
-
-86.26165771484375,
|
| 525 |
-
9.588691711425781
|
| 526 |
-
],
|
| 527 |
-
"output": [
|
| 528 |
-
-1.649336576461792,
|
| 529 |
-
1.9763603210449219
|
| 530 |
-
]
|
| 531 |
-
},
|
| 532 |
-
"model.layers.13.mlp.act_fn": {
|
| 533 |
-
"input2": [
|
| 534 |
-
2.544876906540594e-06,
|
| 535 |
-
0.9145498871803284
|
| 536 |
-
],
|
| 537 |
-
"output": [
|
| 538 |
-
-0.2592918276786804,
|
| 539 |
-
7.993622779846191
|
| 540 |
-
]
|
| 541 |
-
},
|
| 542 |
-
"model.layers.13.mlp.w1": {
|
| 543 |
-
"output": [
|
| 544 |
-
-5.687346458435059,
|
| 545 |
-
5.135588645935059
|
| 546 |
-
]
|
| 547 |
-
},
|
| 548 |
-
"model.layers.13.mlp.w2": {
|
| 549 |
-
"input": [
|
| 550 |
-
-0.5235582590103149,
|
| 551 |
-
0.4653850793838501
|
| 552 |
-
],
|
| 553 |
-
"output": [
|
| 554 |
-
-1.4153391122817993,
|
| 555 |
-
1.788828730583191
|
| 556 |
-
]
|
| 557 |
-
},
|
| 558 |
-
"model.layers.13.mlp.w3": {
|
| 559 |
-
"output": [
|
| 560 |
-
-0.7486878633499146,
|
| 561 |
-
1.123031735420227
|
| 562 |
-
]
|
| 563 |
-
},
|
| 564 |
-
"model.layers.13.post_attention_layernorm": {
|
| 565 |
-
"input": [
|
| 566 |
-
-63.23237609863281,
|
| 567 |
-
7.0157012939453125
|
| 568 |
-
],
|
| 569 |
-
"output": [
|
| 570 |
-
-0.8964369297027588,
|
| 571 |
-
1.1264958381652832
|
| 572 |
-
]
|
| 573 |
-
},
|
| 574 |
-
"model.layers.13.self_attn.k_proj": {
|
| 575 |
-
"output": [
|
| 576 |
-
-18.75926971435547,
|
| 577 |
-
22.478782653808594
|
| 578 |
-
]
|
| 579 |
-
},
|
| 580 |
-
"model.layers.13.self_attn.o_proj": {
|
| 581 |
-
"output": [
|
| 582 |
-
-0.9660946130752563,
|
| 583 |
-
1.3633023500442505
|
| 584 |
-
]
|
| 585 |
-
},
|
| 586 |
-
"model.layers.13.self_attn.pv_bmm": {
|
| 587 |
-
"input": [
|
| 588 |
-
0.0,
|
| 589 |
-
14.002142906188965
|
| 590 |
-
],
|
| 591 |
-
"input2": [
|
| 592 |
-
-1.2294055223464966,
|
| 593 |
-
1.3193620443344116
|
| 594 |
-
],
|
| 595 |
-
"output": [
|
| 596 |
-
-0.8531197309494019,
|
| 597 |
-
0.7348039150238037
|
| 598 |
-
]
|
| 599 |
-
},
|
| 600 |
-
"model.layers.13.self_attn.q_proj": {
|
| 601 |
-
"output": [
|
| 602 |
-
-8.40859603881836,
|
| 603 |
-
10.566553115844727
|
| 604 |
-
]
|
| 605 |
-
},
|
| 606 |
-
"model.layers.13.self_attn.qk_bmm": {
|
| 607 |
-
"input": [
|
| 608 |
-
-9.85166072845459,
|
| 609 |
-
9.03686237335205
|
| 610 |
-
],
|
| 611 |
-
"input2": [
|
| 612 |
-
-18.746200561523438,
|
| 613 |
-
22.11090087890625
|
| 614 |
-
],
|
| 615 |
-
"output": [
|
| 616 |
-
-304.88323974609375,
|
| 617 |
-
275.91217041015625
|
| 618 |
-
]
|
| 619 |
-
},
|
| 620 |
-
"model.layers.13.self_attn.v_proj": {
|
| 621 |
-
"output": [
|
| 622 |
-
-1.229308843612671,
|
| 623 |
-
1.319258451461792
|
| 624 |
-
]
|
| 625 |
-
},
|
| 626 |
-
"model.layers.14.input_layernorm": {
|
| 627 |
-
"input": [
|
| 628 |
-
-92.7020492553711,
|
| 629 |
-
10.2801513671875
|
| 630 |
-
],
|
| 631 |
-
"output": [
|
| 632 |
-
-1.568450927734375,
|
| 633 |
-
2.1694462299346924
|
| 634 |
-
]
|
| 635 |
-
},
|
| 636 |
-
"model.layers.14.mlp.act_fn": {
|
| 637 |
-
"input2": [
|
| 638 |
-
6.2880517361918464e-06,
|
| 639 |
-
0.9631829261779785
|
| 640 |
-
],
|
| 641 |
-
"output": [
|
| 642 |
-
-0.2625121474266052,
|
| 643 |
-
6.425864219665527
|
| 644 |
-
]
|
| 645 |
-
},
|
| 646 |
-
"model.layers.14.mlp.w1": {
|
| 647 |
-
"output": [
|
| 648 |
-
-3.615870475769043,
|
| 649 |
-
3.3168134689331055
|
| 650 |
-
]
|
| 651 |
-
},
|
| 652 |
-
"model.layers.14.mlp.w2": {
|
| 653 |
-
"input": [
|
| 654 |
-
-0.854144811630249,
|
| 655 |
-
0.49869322776794434
|
| 656 |
-
],
|
| 657 |
-
"output": [
|
| 658 |
-
-2.835049867630005,
|
| 659 |
-
2.239513635635376
|
| 660 |
-
]
|
| 661 |
-
},
|
| 662 |
-
"model.layers.14.mlp.w3": {
|
| 663 |
-
"output": [
|
| 664 |
-
-1.0184581279754639,
|
| 665 |
-
1.0759518146514893
|
| 666 |
-
]
|
| 667 |
-
},
|
| 668 |
-
"model.layers.14.post_attention_layernorm": {
|
| 669 |
-
"input": [
|
| 670 |
-
-62.98443603515625,
|
| 671 |
-
6.968025207519531
|
| 672 |
-
],
|
| 673 |
-
"output": [
|
| 674 |
-
-0.8999509811401367,
|
| 675 |
-
1.0614806413650513
|
| 676 |
-
]
|
| 677 |
-
},
|
| 678 |
-
"model.layers.14.self_attn.k_proj": {
|
| 679 |
-
"output": [
|
| 680 |
-
-15.748926162719727,
|
| 681 |
-
20.759946823120117
|
| 682 |
-
]
|
| 683 |
-
},
|
| 684 |
-
"model.layers.14.self_attn.o_proj": {
|
| 685 |
-
"output": [
|
| 686 |
-
-1.1212328672409058,
|
| 687 |
-
1.5860103368759155
|
| 688 |
-
]
|
| 689 |
-
},
|
| 690 |
-
"model.layers.14.self_attn.pv_bmm": {
|
| 691 |
-
"input": [
|
| 692 |
-
0.0,
|
| 693 |
-
25.853843688964844
|
| 694 |
-
],
|
| 695 |
-
"input2": [
|
| 696 |
-
-1.298612117767334,
|
| 697 |
-
1.2684118747711182
|
| 698 |
-
],
|
| 699 |
-
"output": [
|
| 700 |
-
-0.9813904166221619,
|
| 701 |
-
1.0367913246154785
|
| 702 |
-
]
|
| 703 |
-
},
|
| 704 |
-
"model.layers.14.self_attn.q_proj": {
|
| 705 |
-
"output": [
|
| 706 |
-
-7.34971284866333,
|
| 707 |
-
11.581365585327148
|
| 708 |
-
]
|
| 709 |
-
},
|
| 710 |
-
"model.layers.14.self_attn.qk_bmm": {
|
| 711 |
-
"input": [
|
| 712 |
-
-12.523106575012207,
|
| 713 |
-
10.125065803527832
|
| 714 |
-
],
|
| 715 |
-
"input2": [
|
| 716 |
-
-21.095430374145508,
|
| 717 |
-
20.93062400817871
|
| 718 |
-
],
|
| 719 |
-
"output": [
|
| 720 |
-
-370.3804626464844,
|
| 721 |
-
339.1870422363281
|
| 722 |
-
]
|
| 723 |
-
},
|
| 724 |
-
"model.layers.14.self_attn.v_proj": {
|
| 725 |
-
"output": [
|
| 726 |
-
-1.2987051010131836,
|
| 727 |
-
1.2685027122497559
|
| 728 |
-
]
|
| 729 |
-
},
|
| 730 |
-
"model.layers.15.input_layernorm": {
|
| 731 |
-
"input": [
|
| 732 |
-
-96.00485229492188,
|
| 733 |
-
10.613883972167969
|
| 734 |
-
],
|
| 735 |
-
"output": [
|
| 736 |
-
-1.5501868724822998,
|
| 737 |
-
1.7997932434082031
|
| 738 |
-
]
|
| 739 |
-
},
|
| 740 |
-
"model.layers.15.mlp.act_fn": {
|
| 741 |
-
"input2": [
|
| 742 |
-
1.4850113529973896e-06,
|
| 743 |
-
0.9971228241920471
|
| 744 |
-
],
|
| 745 |
-
"output": [
|
| 746 |
-
-0.2568572461605072,
|
| 747 |
-
9.069701194763184
|
| 748 |
-
]
|
| 749 |
-
},
|
| 750 |
-
"model.layers.15.mlp.w1": {
|
| 751 |
-
"output": [
|
| 752 |
-
-4.972715377807617,
|
| 753 |
-
5.011870384216309
|
| 754 |
-
]
|
| 755 |
-
},
|
| 756 |
-
"model.layers.15.mlp.w2": {
|
| 757 |
-
"input": [
|
| 758 |
-
-0.5734550952911377,
|
| 759 |
-
0.7439417839050293
|
| 760 |
-
],
|
| 761 |
-
"output": [
|
| 762 |
-
-2.318004608154297,
|
| 763 |
-
2.227762222290039
|
| 764 |
-
]
|
| 765 |
-
},
|
| 766 |
-
"model.layers.15.mlp.w3": {
|
| 767 |
-
"output": [
|
| 768 |
-
-0.6860116124153137,
|
| 769 |
-
0.545910656452179
|
| 770 |
-
]
|
| 771 |
-
},
|
| 772 |
-
"model.layers.15.post_attention_layernorm": {
|
| 773 |
-
"input": [
|
| 774 |
-
-49.25102996826172,
|
| 775 |
-
5.433860778808594
|
| 776 |
-
],
|
| 777 |
-
"output": [
|
| 778 |
-
-0.9355494976043701,
|
| 779 |
-
0.9282405376434326
|
| 780 |
-
]
|
| 781 |
-
},
|
| 782 |
-
"model.layers.15.self_attn.k_proj": {
|
| 783 |
-
"output": [
|
| 784 |
-
-18.496917724609375,
|
| 785 |
-
17.78549575805664
|
| 786 |
-
]
|
| 787 |
-
},
|
| 788 |
-
"model.layers.15.self_attn.o_proj": {
|
| 789 |
-
"output": [
|
| 790 |
-
-1.700047492980957,
|
| 791 |
-
1.5626873970031738
|
| 792 |
-
]
|
| 793 |
-
},
|
| 794 |
-
"model.layers.15.self_attn.pv_bmm": {
|
| 795 |
-
"input": [
|
| 796 |
-
0.0,
|
| 797 |
-
17.365955352783203
|
| 798 |
-
],
|
| 799 |
-
"input2": [
|
| 800 |
-
-1.4967215061187744,
|
| 801 |
-
1.2101151943206787
|
| 802 |
-
],
|
| 803 |
-
"output": [
|
| 804 |
-
-1.2445505857467651,
|
| 805 |
-
0.9747527837753296
|
| 806 |
-
]
|
| 807 |
-
},
|
| 808 |
-
"model.layers.15.self_attn.q_proj": {
|
| 809 |
-
"output": [
|
| 810 |
-
-12.66657829284668,
|
| 811 |
-
15.178054809570312
|
| 812 |
-
]
|
| 813 |
-
},
|
| 814 |
-
"model.layers.15.self_attn.qk_bmm": {
|
| 815 |
-
"input": [
|
| 816 |
-
-13.573946952819824,
|
| 817 |
-
13.897137641906738
|
| 818 |
-
],
|
| 819 |
-
"input2": [
|
| 820 |
-
-21.92919921875,
|
| 821 |
-
17.450702667236328
|
| 822 |
-
],
|
| 823 |
-
"output": [
|
| 824 |
-
-510.9229431152344,
|
| 825 |
-
232.58938598632812
|
| 826 |
-
]
|
| 827 |
-
},
|
| 828 |
-
"model.layers.15.self_attn.v_proj": {
|
| 829 |
-
"output": [
|
| 830 |
-
-1.496742606163025,
|
| 831 |
-
1.2101324796676636
|
| 832 |
-
]
|
| 833 |
-
},
|
| 834 |
-
"model.layers.16.input_layernorm": {
|
| 835 |
-
"input": [
|
| 836 |
-
-100.52581787109375,
|
| 837 |
-
11.0853271484375
|
| 838 |
-
],
|
| 839 |
-
"output": [
|
| 840 |
-
-1.5624299049377441,
|
| 841 |
-
1.8722219467163086
|
| 842 |
-
]
|
| 843 |
-
},
|
| 844 |
-
"model.layers.16.mlp.act_fn": {
|
| 845 |
-
"input2": [
|
| 846 |
-
1.0168923836317845e-06,
|
| 847 |
-
0.9851000905036926
|
| 848 |
-
],
|
| 849 |
-
"output": [
|
| 850 |
-
-0.2558925151824951,
|
| 851 |
-
10.573112487792969
|
| 852 |
-
]
|
| 853 |
-
},
|
| 854 |
-
"model.layers.16.mlp.w1": {
|
| 855 |
-
"output": [
|
| 856 |
-
-4.58713960647583,
|
| 857 |
-
6.344828128814697
|
| 858 |
-
]
|
| 859 |
-
},
|
| 860 |
-
"model.layers.16.mlp.w2": {
|
| 861 |
-
"input": [
|
| 862 |
-
-0.9895568490028381,
|
| 863 |
-
0.8258172869682312
|
| 864 |
-
],
|
| 865 |
-
"output": [
|
| 866 |
-
-2.62292742729187,
|
| 867 |
-
3.516347646713257
|
| 868 |
-
]
|
| 869 |
-
},
|
| 870 |
-
"model.layers.16.mlp.w3": {
|
| 871 |
-
"output": [
|
| 872 |
-
-0.651694118976593,
|
| 873 |
-
0.710453450679779
|
| 874 |
-
]
|
| 875 |
-
},
|
| 876 |
-
"model.layers.16.post_attention_layernorm": {
|
| 877 |
-
"input": [
|
| 878 |
-
-62.668067932128906,
|
| 879 |
-
6.895301818847656
|
| 880 |
-
],
|
| 881 |
-
"output": [
|
| 882 |
-
-0.9683569073677063,
|
| 883 |
-
1.0723953247070312
|
| 884 |
-
]
|
| 885 |
-
},
|
| 886 |
-
"model.layers.16.self_attn.k_proj": {
|
| 887 |
-
"output": [
|
| 888 |
-
-19.975080490112305,
|
| 889 |
-
19.20680809020996
|
| 890 |
-
]
|
| 891 |
-
},
|
| 892 |
-
"model.layers.16.self_attn.o_proj": {
|
| 893 |
-
"output": [
|
| 894 |
-
-1.0730109214782715,
|
| 895 |
-
0.9763514995574951
|
| 896 |
-
]
|
| 897 |
-
},
|
| 898 |
-
"model.layers.16.self_attn.pv_bmm": {
|
| 899 |
-
"input": [
|
| 900 |
-
0.0,
|
| 901 |
-
10.039031028747559
|
| 902 |
-
],
|
| 903 |
-
"input2": [
|
| 904 |
-
-1.5520944595336914,
|
| 905 |
-
1.1964061260223389
|
| 906 |
-
],
|
| 907 |
-
"output": [
|
| 908 |
-
-1.0620307922363281,
|
| 909 |
-
0.9147418737411499
|
| 910 |
-
]
|
| 911 |
-
},
|
| 912 |
-
"model.layers.16.self_attn.q_proj": {
|
| 913 |
-
"output": [
|
| 914 |
-
-9.887508392333984,
|
| 915 |
-
10.283008575439453
|
| 916 |
-
]
|
| 917 |
-
},
|
| 918 |
-
"model.layers.16.self_attn.qk_bmm": {
|
| 919 |
-
"input": [
|
| 920 |
-
-9.462581634521484,
|
| 921 |
-
10.154966354370117
|
| 922 |
-
],
|
| 923 |
-
"input2": [
|
| 924 |
-
-19.422739028930664,
|
| 925 |
-
19.575674057006836
|
| 926 |
-
],
|
| 927 |
-
"output": [
|
| 928 |
-
-327.813720703125,
|
| 929 |
-
297.045166015625
|
| 930 |
-
]
|
| 931 |
-
},
|
| 932 |
-
"model.layers.16.self_attn.v_proj": {
|
| 933 |
-
"output": [
|
| 934 |
-
-1.5520508289337158,
|
| 935 |
-
1.1963725090026855
|
| 936 |
-
]
|
| 937 |
-
},
|
| 938 |
-
"model.layers.17.input_layernorm": {
|
| 939 |
-
"input": [
|
| 940 |
-
-69.5985107421875,
|
| 941 |
-
7.65130615234375
|
| 942 |
-
],
|
| 943 |
-
"output": [
|
| 944 |
-
-1.562252163887024,
|
| 945 |
-
1.9631842374801636
|
| 946 |
-
]
|
| 947 |
-
},
|
| 948 |
-
"model.layers.17.mlp.act_fn": {
|
| 949 |
-
"input2": [
|
| 950 |
-
3.43927308676939e-06,
|
| 951 |
-
0.9986145496368408
|
| 952 |
-
],
|
| 953 |
-
"output": [
|
| 954 |
-
-0.2538253664970398,
|
| 955 |
-
10.493779182434082
|
| 956 |
-
]
|
| 957 |
-
},
|
| 958 |
-
"model.layers.17.mlp.w1": {
|
| 959 |
-
"output": [
|
| 960 |
-
-8.031157493591309,
|
| 961 |
-
7.366927146911621
|
| 962 |
-
]
|
| 963 |
-
},
|
| 964 |
-
"model.layers.17.mlp.w2": {
|
| 965 |
-
"input": [
|
| 966 |
-
-0.7215433716773987,
|
| 967 |
-
1.100175142288208
|
| 968 |
-
],
|
| 969 |
-
"output": [
|
| 970 |
-
-1.9865412712097168,
|
| 971 |
-
2.7032275199890137
|
| 972 |
-
]
|
| 973 |
-
},
|
| 974 |
-
"model.layers.17.mlp.w3": {
|
| 975 |
-
"output": [
|
| 976 |
-
-0.8852017521858215,
|
| 977 |
-
0.6933049559593201
|
| 978 |
-
]
|
| 979 |
-
},
|
| 980 |
-
"model.layers.17.post_attention_layernorm": {
|
| 981 |
-
"input": [
|
| 982 |
-
-60.717594146728516,
|
| 983 |
-
6.662433624267578
|
| 984 |
-
],
|
| 985 |
-
"output": [
|
| 986 |
-
-1.0898340940475464,
|
| 987 |
-
0.8811424970626831
|
| 988 |
-
]
|
| 989 |
-
},
|
| 990 |
-
"model.layers.17.self_attn.k_proj": {
|
| 991 |
-
"output": [
|
| 992 |
-
-17.243209838867188,
|
| 993 |
-
20.019657135009766
|
| 994 |
-
]
|
| 995 |
-
},
|
| 996 |
-
"model.layers.17.self_attn.o_proj": {
|
| 997 |
-
"output": [
|
| 998 |
-
-1.8149468898773193,
|
| 999 |
-
1.7124121189117432
|
| 1000 |
-
]
|
| 1001 |
-
},
|
| 1002 |
-
"model.layers.17.self_attn.pv_bmm": {
|
| 1003 |
-
"input": [
|
| 1004 |
-
-1.9625843172832447e-09,
|
| 1005 |
-
24.50324058532715
|
| 1006 |
-
],
|
| 1007 |
-
"input2": [
|
| 1008 |
-
-1.8348536491394043,
|
| 1009 |
-
1.6309809684753418
|
| 1010 |
-
],
|
| 1011 |
-
"output": [
|
| 1012 |
-
-1.139207124710083,
|
| 1013 |
-
1.0449869632720947
|
| 1014 |
-
]
|
| 1015 |
-
},
|
| 1016 |
-
"model.layers.17.self_attn.q_proj": {
|
| 1017 |
-
"output": [
|
| 1018 |
-
-11.556499481201172,
|
| 1019 |
-
10.272443771362305
|
| 1020 |
-
]
|
| 1021 |
-
},
|
| 1022 |
-
"model.layers.17.self_attn.qk_bmm": {
|
| 1023 |
-
"input": [
|
| 1024 |
-
-9.140716552734375,
|
| 1025 |
-
11.486564636230469
|
| 1026 |
-
],
|
| 1027 |
-
"input2": [
|
| 1028 |
-
-19.73405647277832,
|
| 1029 |
-
20.20391273498535
|
| 1030 |
-
],
|
| 1031 |
-
"output": [
|
| 1032 |
-
-374.51507568359375,
|
| 1033 |
-
302.01531982421875
|
| 1034 |
-
]
|
| 1035 |
-
},
|
| 1036 |
-
"model.layers.17.self_attn.v_proj": {
|
| 1037 |
-
"output": [
|
| 1038 |
-
-1.8348592519760132,
|
| 1039 |
-
1.6309860944747925
|
| 1040 |
-
]
|
| 1041 |
-
},
|
| 1042 |
-
"model.layers.18.input_layernorm": {
|
| 1043 |
-
"input": [
|
| 1044 |
-
-99.9640121459961,
|
| 1045 |
-
10.972625732421875
|
| 1046 |
-
],
|
| 1047 |
-
"output": [
|
| 1048 |
-
-1.8908522129058838,
|
| 1049 |
-
2.1609737873077393
|
| 1050 |
-
]
|
| 1051 |
-
},
|
| 1052 |
-
"model.layers.18.mlp.act_fn": {
|
| 1053 |
-
"input2": [
|
| 1054 |
-
2.1923647182120476e-06,
|
| 1055 |
-
0.9952065944671631
|
| 1056 |
-
],
|
| 1057 |
-
"output": [
|
| 1058 |
-
-0.2591128349304199,
|
| 1059 |
-
9.149469375610352
|
| 1060 |
-
]
|
| 1061 |
-
},
|
| 1062 |
-
"model.layers.18.mlp.w1": {
|
| 1063 |
-
"output": [
|
| 1064 |
-
-4.569403171539307,
|
| 1065 |
-
5.83414888381958
|
| 1066 |
-
]
|
| 1067 |
-
},
|
| 1068 |
-
"model.layers.18.mlp.w2": {
|
| 1069 |
-
"input": [
|
| 1070 |
-
-1.471362829208374,
|
| 1071 |
-
1.2874424457550049
|
| 1072 |
-
],
|
| 1073 |
-
"output": [
|
| 1074 |
-
-1.6179473400115967,
|
| 1075 |
-
2.5631320476531982
|
| 1076 |
-
]
|
| 1077 |
-
},
|
| 1078 |
-
"model.layers.18.mlp.w3": {
|
| 1079 |
-
"output": [
|
| 1080 |
-
-0.9652486443519592,
|
| 1081 |
-
1.1750853061676025
|
| 1082 |
-
]
|
| 1083 |
-
},
|
| 1084 |
-
"model.layers.18.post_attention_layernorm": {
|
| 1085 |
-
"input": [
|
| 1086 |
-
-81.42882537841797,
|
| 1087 |
-
8.924331665039062
|
| 1088 |
-
],
|
| 1089 |
-
"output": [
|
| 1090 |
-
-1.0480235815048218,
|
| 1091 |
-
0.9463497400283813
|
| 1092 |
-
]
|
| 1093 |
-
},
|
| 1094 |
-
"model.layers.18.self_attn.k_proj": {
|
| 1095 |
-
"output": [
|
| 1096 |
-
-20.276676177978516,
|
| 1097 |
-
13.96539306640625
|
| 1098 |
-
]
|
| 1099 |
-
},
|
| 1100 |
-
"model.layers.18.self_attn.o_proj": {
|
| 1101 |
-
"output": [
|
| 1102 |
-
-1.4689831733703613,
|
| 1103 |
-
3.1518197059631348
|
| 1104 |
-
]
|
| 1105 |
-
},
|
| 1106 |
-
"model.layers.18.self_attn.pv_bmm": {
|
| 1107 |
-
"input": [
|
| 1108 |
-
-2.13810147364768e-09,
|
| 1109 |
-
9.233264923095703
|
| 1110 |
-
],
|
| 1111 |
-
"input2": [
|
| 1112 |
-
-2.1445376873016357,
|
| 1113 |
-
2.1277835369110107
|
| 1114 |
-
],
|
| 1115 |
-
"output": [
|
| 1116 |
-
-1.4730726480484009,
|
| 1117 |
-
1.3943589925765991
|
| 1118 |
-
]
|
| 1119 |
-
},
|
| 1120 |
-
"model.layers.18.self_attn.q_proj": {
|
| 1121 |
-
"output": [
|
| 1122 |
-
-11.622716903686523,
|
| 1123 |
-
11.89944839477539
|
| 1124 |
-
]
|
| 1125 |
-
},
|
| 1126 |
-
"model.layers.18.self_attn.qk_bmm": {
|
| 1127 |
-
"input": [
|
| 1128 |
-
-10.726187705993652,
|
| 1129 |
-
11.693303108215332
|
| 1130 |
-
],
|
| 1131 |
-
"input2": [
|
| 1132 |
-
-18.65675163269043,
|
| 1133 |
-
17.384702682495117
|
| 1134 |
-
],
|
| 1135 |
-
"output": [
|
| 1136 |
-
-323.7893371582031,
|
| 1137 |
-
281.9984436035156
|
| 1138 |
-
]
|
| 1139 |
-
},
|
| 1140 |
-
"model.layers.18.self_attn.v_proj": {
|
| 1141 |
-
"output": [
|
| 1142 |
-
-2.1445248126983643,
|
| 1143 |
-
2.1277706623077393
|
| 1144 |
-
]
|
| 1145 |
-
},
|
| 1146 |
-
"model.layers.19.input_layernorm": {
|
| 1147 |
-
"input": [
|
| 1148 |
-
-78.49484252929688,
|
| 1149 |
-
8.620475769042969
|
| 1150 |
-
],
|
| 1151 |
-
"output": [
|
| 1152 |
-
-1.798056960105896,
|
| 1153 |
-
1.8699792623519897
|
| 1154 |
-
]
|
| 1155 |
-
},
|
| 1156 |
-
"model.layers.19.mlp.act_fn": {
|
| 1157 |
-
"input2": [
|
| 1158 |
-
1.7838705446138192e-07,
|
| 1159 |
-
1.007856011390686
|
| 1160 |
-
],
|
| 1161 |
-
"output": [
|
| 1162 |
-
-0.2515661120414734,
|
| 1163 |
-
12.509735107421875
|
| 1164 |
-
]
|
| 1165 |
-
},
|
| 1166 |
-
"model.layers.19.mlp.w1": {
|
| 1167 |
-
"output": [
|
| 1168 |
-
-7.22218656539917,
|
| 1169 |
-
8.253927230834961
|
| 1170 |
-
]
|
| 1171 |
-
},
|
| 1172 |
-
"model.layers.19.mlp.w2": {
|
| 1173 |
-
"input": [
|
| 1174 |
-
-1.2253239154815674,
|
| 1175 |
-
1.445253849029541
|
| 1176 |
-
],
|
| 1177 |
-
"output": [
|
| 1178 |
-
-4.075857639312744,
|
| 1179 |
-
5.675578594207764
|
| 1180 |
-
]
|
| 1181 |
-
},
|
| 1182 |
-
"model.layers.19.mlp.w3": {
|
| 1183 |
-
"output": [
|
| 1184 |
-
-0.8933815360069275,
|
| 1185 |
-
0.7455558180809021
|
| 1186 |
-
]
|
| 1187 |
-
},
|
| 1188 |
-
"model.layers.19.post_attention_layernorm": {
|
| 1189 |
-
"input": [
|
| 1190 |
-
-105.57499694824219,
|
| 1191 |
-
11.590507507324219
|
| 1192 |
-
],
|
| 1193 |
-
"output": [
|
| 1194 |
-
-1.3605623245239258,
|
| 1195 |
-
0.863433837890625
|
| 1196 |
-
]
|
| 1197 |
-
},
|
| 1198 |
-
"model.layers.19.self_attn.k_proj": {
|
| 1199 |
-
"output": [
|
| 1200 |
-
-21.901290893554688,
|
| 1201 |
-
20.40802001953125
|
| 1202 |
-
]
|
| 1203 |
-
},
|
| 1204 |
-
"model.layers.19.self_attn.o_proj": {
|
| 1205 |
-
"output": [
|
| 1206 |
-
-1.9629877805709839,
|
| 1207 |
-
1.8841489553451538
|
| 1208 |
-
]
|
| 1209 |
-
},
|
| 1210 |
-
"model.layers.19.self_attn.pv_bmm": {
|
| 1211 |
-
"input": [
|
| 1212 |
-
-6.853270173579062e-10,
|
| 1213 |
-
21.860992431640625
|
| 1214 |
-
],
|
| 1215 |
-
"input2": [
|
| 1216 |
-
-2.382417678833008,
|
| 1217 |
-
2.4391417503356934
|
| 1218 |
-
],
|
| 1219 |
-
"output": [
|
| 1220 |
-
-1.411903738975525,
|
| 1221 |
-
1.1782792806625366
|
| 1222 |
-
]
|
| 1223 |
-
},
|
| 1224 |
-
"model.layers.19.self_attn.q_proj": {
|
| 1225 |
-
"output": [
|
| 1226 |
-
-15.740455627441406,
|
| 1227 |
-
13.135919570922852
|
| 1228 |
-
]
|
| 1229 |
-
},
|
| 1230 |
-
"model.layers.19.self_attn.qk_bmm": {
|
| 1231 |
-
"input": [
|
| 1232 |
-
-17.215229034423828,
|
| 1233 |
-
15.545093536376953
|
| 1234 |
-
],
|
| 1235 |
-
"input2": [
|
| 1236 |
-
-20.727087020874023,
|
| 1237 |
-
19.313875198364258
|
| 1238 |
-
],
|
| 1239 |
-
"output": [
|
| 1240 |
-
-431.6451721191406,
|
| 1241 |
-
358.5186462402344
|
| 1242 |
-
]
|
| 1243 |
-
},
|
| 1244 |
-
"model.layers.19.self_attn.v_proj": {
|
| 1245 |
-
"output": [
|
| 1246 |
-
-2.3823821544647217,
|
| 1247 |
-
2.439105272293091
|
| 1248 |
-
]
|
| 1249 |
-
},
|
| 1250 |
-
"model.layers.2.input_layernorm": {
|
| 1251 |
-
"input": [
|
| 1252 |
-
-0.8590171933174133,
|
| 1253 |
-
1.0888631343841553
|
| 1254 |
-
],
|
| 1255 |
-
"output": [
|
| 1256 |
-
-1.7529939413070679,
|
| 1257 |
-
1.168662667274475
|
| 1258 |
-
]
|
| 1259 |
-
},
|
| 1260 |
-
"model.layers.2.mlp.act_fn": {
|
| 1261 |
-
"input2": [
|
| 1262 |
-
3.966258191212546e-06,
|
| 1263 |
-
0.9987732768058777
|
| 1264 |
-
],
|
| 1265 |
-
"output": [
|
| 1266 |
-
-0.18402370810508728,
|
| 1267 |
-
11.531486511230469
|
| 1268 |
-
]
|
| 1269 |
-
},
|
| 1270 |
-
"model.layers.2.mlp.w1": {
|
| 1271 |
-
"output": [
|
| 1272 |
-
-19.380216598510742,
|
| 1273 |
-
14.468793869018555
|
| 1274 |
-
]
|
| 1275 |
-
},
|
| 1276 |
-
"model.layers.2.mlp.w2": {
|
| 1277 |
-
"input": [
|
| 1278 |
-
-0.6558618545532227,
|
| 1279 |
-
8.63491439819336
|
| 1280 |
-
],
|
| 1281 |
-
"output": [
|
| 1282 |
-
-75.92266082763672,
|
| 1283 |
-
11.691207885742188
|
| 1284 |
-
]
|
| 1285 |
-
},
|
| 1286 |
-
"model.layers.2.mlp.w3": {
|
| 1287 |
-
"output": [
|
| 1288 |
-
-9.166142463684082,
|
| 1289 |
-
2.6387386322021484
|
| 1290 |
-
]
|
| 1291 |
-
},
|
| 1292 |
-
"model.layers.2.post_attention_layernorm": {
|
| 1293 |
-
"input": [
|
| 1294 |
-
-0.7533947229385376,
|
| 1295 |
-
0.8142738342285156
|
| 1296 |
-
],
|
| 1297 |
-
"output": [
|
| 1298 |
-
-0.4843924641609192,
|
| 1299 |
-
0.5449416041374207
|
| 1300 |
-
]
|
| 1301 |
-
},
|
| 1302 |
-
"model.layers.2.self_attn.k_proj": {
|
| 1303 |
-
"output": [
|
| 1304 |
-
-9.543099403381348,
|
| 1305 |
-
10.241374015808105
|
| 1306 |
-
]
|
| 1307 |
-
},
|
| 1308 |
-
"model.layers.2.self_attn.o_proj": {
|
| 1309 |
-
"output": [
|
| 1310 |
-
-0.726354718208313,
|
| 1311 |
-
0.5078719854354858
|
| 1312 |
-
]
|
| 1313 |
-
},
|
| 1314 |
-
"model.layers.2.self_attn.pv_bmm": {
|
| 1315 |
-
"input": [
|
| 1316 |
-
-6.111011696674495e-11,
|
| 1317 |
-
1.5878328084945679
|
| 1318 |
-
],
|
| 1319 |
-
"input2": [
|
| 1320 |
-
-0.338035523891449,
|
| 1321 |
-
0.36276984214782715
|
| 1322 |
-
],
|
| 1323 |
-
"output": [
|
| 1324 |
-
-0.20621609687805176,
|
| 1325 |
-
0.22130507230758667
|
| 1326 |
-
]
|
| 1327 |
-
},
|
| 1328 |
-
"model.layers.2.self_attn.q_proj": {
|
| 1329 |
-
"output": [
|
| 1330 |
-
-6.53659200668335,
|
| 1331 |
-
5.810304164886475
|
| 1332 |
-
]
|
| 1333 |
-
},
|
| 1334 |
-
"model.layers.2.self_attn.qk_bmm": {
|
| 1335 |
-
"input": [
|
| 1336 |
-
-6.120059967041016,
|
| 1337 |
-
6.072246551513672
|
| 1338 |
-
],
|
| 1339 |
-
"input2": [
|
| 1340 |
-
-10.258339881896973,
|
| 1341 |
-
10.33911418914795
|
| 1342 |
-
],
|
| 1343 |
-
"output": [
|
| 1344 |
-
-225.0656280517578,
|
| 1345 |
-
169.3107452392578
|
| 1346 |
-
]
|
| 1347 |
-
},
|
| 1348 |
-
"model.layers.2.self_attn.v_proj": {
|
| 1349 |
-
"output": [
|
| 1350 |
-
-0.33430781960487366,
|
| 1351 |
-
0.35876932740211487
|
| 1352 |
-
]
|
| 1353 |
-
},
|
| 1354 |
-
"model.layers.20.input_layernorm": {
|
| 1355 |
-
"input": [
|
| 1356 |
-
-115.20829772949219,
|
| 1357 |
-
12.693580627441406
|
| 1358 |
-
],
|
| 1359 |
-
"output": [
|
| 1360 |
-
-1.69486403465271,
|
| 1361 |
-
1.5065457820892334
|
| 1362 |
-
]
|
| 1363 |
-
},
|
| 1364 |
-
"model.layers.20.mlp.act_fn": {
|
| 1365 |
-
"input2": [
|
| 1366 |
-
2.50033565407648e-07,
|
| 1367 |
-
0.9959600567817688
|
| 1368 |
-
],
|
| 1369 |
-
"output": [
|
| 1370 |
-
-0.2553894817829132,
|
| 1371 |
-
10.56139850616455
|
| 1372 |
-
]
|
| 1373 |
-
},
|
| 1374 |
-
"model.layers.20.mlp.w1": {
|
| 1375 |
-
"output": [
|
| 1376 |
-
-5.983047962188721,
|
| 1377 |
-
7.761791706085205
|
| 1378 |
-
]
|
| 1379 |
-
},
|
| 1380 |
-
"model.layers.20.mlp.w2": {
|
| 1381 |
-
"input": [
|
| 1382 |
-
-7.271407604217529,
|
| 1383 |
-
2.8058152198791504
|
| 1384 |
-
],
|
| 1385 |
-
"output": [
|
| 1386 |
-
-11.011977195739746,
|
| 1387 |
-
6.784623146057129
|
| 1388 |
-
]
|
| 1389 |
-
},
|
| 1390 |
-
"model.layers.20.mlp.w3": {
|
| 1391 |
-
"output": [
|
| 1392 |
-
-3.3427953720092773,
|
| 1393 |
-
2.2285304069519043
|
| 1394 |
-
]
|
| 1395 |
-
},
|
| 1396 |
-
"model.layers.20.post_attention_layernorm": {
|
| 1397 |
-
"input": [
|
| 1398 |
-
-113.40253448486328,
|
| 1399 |
-
12.49249267578125
|
| 1400 |
-
],
|
| 1401 |
-
"output": [
|
| 1402 |
-
-1.8028979301452637,
|
| 1403 |
-
0.9336435794830322
|
| 1404 |
-
]
|
| 1405 |
-
},
|
| 1406 |
-
"model.layers.20.self_attn.k_proj": {
|
| 1407 |
-
"output": [
|
| 1408 |
-
-21.391155242919922,
|
| 1409 |
-
19.014358520507812
|
| 1410 |
-
]
|
| 1411 |
-
},
|
| 1412 |
-
"model.layers.20.self_attn.o_proj": {
|
| 1413 |
-
"output": [
|
| 1414 |
-
-2.64984393119812,
|
| 1415 |
-
3.5715410709381104
|
| 1416 |
-
]
|
| 1417 |
-
},
|
| 1418 |
-
"model.layers.20.self_attn.pv_bmm": {
|
| 1419 |
-
"input": [
|
| 1420 |
-
-1.4543530824084883e-09,
|
| 1421 |
-
17.021509170532227
|
| 1422 |
-
],
|
| 1423 |
-
"input2": [
|
| 1424 |
-
-2.695246458053589,
|
| 1425 |
-
2.2139523029327393
|
| 1426 |
-
],
|
| 1427 |
-
"output": [
|
| 1428 |
-
-2.0278091430664062,
|
| 1429 |
-
1.692272424697876
|
| 1430 |
-
]
|
| 1431 |
-
},
|
| 1432 |
-
"model.layers.20.self_attn.q_proj": {
|
| 1433 |
-
"output": [
|
| 1434 |
-
-17.26282501220703,
|
| 1435 |
-
15.835071563720703
|
| 1436 |
-
]
|
| 1437 |
-
},
|
| 1438 |
-
"model.layers.20.self_attn.qk_bmm": {
|
| 1439 |
-
"input": [
|
| 1440 |
-
-15.574592590332031,
|
| 1441 |
-
14.286468505859375
|
| 1442 |
-
],
|
| 1443 |
-
"input2": [
|
| 1444 |
-
-18.195837020874023,
|
| 1445 |
-
19.527238845825195
|
| 1446 |
-
],
|
| 1447 |
-
"output": [
|
| 1448 |
-
-459.4617919921875,
|
| 1449 |
-
400.9951171875
|
| 1450 |
-
]
|
| 1451 |
-
},
|
| 1452 |
-
"model.layers.20.self_attn.v_proj": {
|
| 1453 |
-
"output": [
|
| 1454 |
-
-2.695233106613159,
|
| 1455 |
-
2.2139413356781006
|
| 1456 |
-
]
|
| 1457 |
-
},
|
| 1458 |
-
"model.layers.21.input_layernorm": {
|
| 1459 |
-
"input": [
|
| 1460 |
-
-146.54869079589844,
|
| 1461 |
-
16.176971435546875
|
| 1462 |
-
],
|
| 1463 |
-
"output": [
|
| 1464 |
-
-1.708757758140564,
|
| 1465 |
-
1.6174501180648804
|
| 1466 |
-
]
|
| 1467 |
-
},
|
| 1468 |
-
"model.layers.21.mlp.act_fn": {
|
| 1469 |
-
"input2": [
|
| 1470 |
-
-8.81209771819158e-09,
|
| 1471 |
-
0.9954389333724976
|
| 1472 |
-
],
|
| 1473 |
-
"output": [
|
| 1474 |
-
-0.26087066531181335,
|
| 1475 |
-
13.050216674804688
|
| 1476 |
-
]
|
| 1477 |
-
},
|
| 1478 |
-
"model.layers.21.mlp.w1": {
|
| 1479 |
-
"output": [
|
| 1480 |
-
-107.37953186035156,
|
| 1481 |
-
14.317276000976562
|
| 1482 |
-
]
|
| 1483 |
-
},
|
| 1484 |
-
"model.layers.21.mlp.w2": {
|
| 1485 |
-
"input": [
|
| 1486 |
-
-4.829046249389648,
|
| 1487 |
-
10.758381843566895
|
| 1488 |
-
],
|
| 1489 |
-
"output": [
|
| 1490 |
-
-43.75098419189453,
|
| 1491 |
-
143.9803466796875
|
| 1492 |
-
]
|
| 1493 |
-
},
|
| 1494 |
-
"model.layers.21.mlp.w3": {
|
| 1495 |
-
"output": [
|
| 1496 |
-
-7.738009452819824,
|
| 1497 |
-
2.0302696228027344
|
| 1498 |
-
]
|
| 1499 |
-
},
|
| 1500 |
-
"model.layers.21.post_attention_layernorm": {
|
| 1501 |
-
"input": [
|
| 1502 |
-
-179.94740295410156,
|
| 1503 |
-
22.532821655273438
|
| 1504 |
-
],
|
| 1505 |
-
"output": [
|
| 1506 |
-
-2.6346614360809326,
|
| 1507 |
-
1.5907390117645264
|
| 1508 |
-
]
|
| 1509 |
-
},
|
| 1510 |
-
"model.layers.21.self_attn.k_proj": {
|
| 1511 |
-
"output": [
|
| 1512 |
-
-26.96712875366211,
|
| 1513 |
-
25.128459930419922
|
| 1514 |
-
]
|
| 1515 |
-
},
|
| 1516 |
-
"model.layers.21.self_attn.o_proj": {
|
| 1517 |
-
"output": [
|
| 1518 |
-
-6.288361072540283,
|
| 1519 |
-
10.057985305786133
|
| 1520 |
-
]
|
| 1521 |
-
},
|
| 1522 |
-
"model.layers.21.self_attn.pv_bmm": {
|
| 1523 |
-
"input": [
|
| 1524 |
-
-2.280847288815835e-09,
|
| 1525 |
-
7.910551071166992
|
| 1526 |
-
],
|
| 1527 |
-
"input2": [
|
| 1528 |
-
-4.1691460609436035,
|
| 1529 |
-
3.3707995414733887
|
| 1530 |
-
],
|
| 1531 |
-
"output": [
|
| 1532 |
-
-3.265413761138916,
|
| 1533 |
-
2.725093364715576
|
| 1534 |
-
]
|
| 1535 |
-
},
|
| 1536 |
-
"model.layers.21.self_attn.q_proj": {
|
| 1537 |
-
"output": [
|
| 1538 |
-
-15.797935485839844,
|
| 1539 |
-
16.689754486083984
|
| 1540 |
-
]
|
| 1541 |
-
},
|
| 1542 |
-
"model.layers.21.self_attn.qk_bmm": {
|
| 1543 |
-
"input": [
|
| 1544 |
-
-16.69371223449707,
|
| 1545 |
-
16.825159072875977
|
| 1546 |
-
],
|
| 1547 |
-
"input2": [
|
| 1548 |
-
-24.006988525390625,
|
| 1549 |
-
24.578582763671875
|
| 1550 |
-
],
|
| 1551 |
-
"output": [
|
| 1552 |
-
-675.0399780273438,
|
| 1553 |
-
528.8992309570312
|
| 1554 |
-
]
|
| 1555 |
-
},
|
| 1556 |
-
"model.layers.21.self_attn.v_proj": {
|
| 1557 |
-
"output": [
|
| 1558 |
-
-4.104138374328613,
|
| 1559 |
-
3.318239212036133
|
| 1560 |
-
]
|
| 1561 |
-
},
|
| 1562 |
-
"model.layers.3.input_layernorm": {
|
| 1563 |
-
"input": [
|
| 1564 |
-
-72.91954803466797,
|
| 1565 |
-
11.20062255859375
|
| 1566 |
-
],
|
| 1567 |
-
"output": [
|
| 1568 |
-
-1.0544137954711914,
|
| 1569 |
-
0.9825220108032227
|
| 1570 |
-
]
|
| 1571 |
-
},
|
| 1572 |
-
"model.layers.3.mlp.act_fn": {
|
| 1573 |
-
"input2": [
|
| 1574 |
-
0.0,
|
| 1575 |
-
0.9181910157203674
|
| 1576 |
-
],
|
| 1577 |
-
"output": [
|
| 1578 |
-
-0.2546980381011963,
|
| 1579 |
-
2.1507670879364014
|
| 1580 |
-
]
|
| 1581 |
-
},
|
| 1582 |
-
"model.layers.3.mlp.w1": {
|
| 1583 |
-
"output": [
|
| 1584 |
-
-2.0251128673553467,
|
| 1585 |
-
1.6373252868652344
|
| 1586 |
-
]
|
| 1587 |
-
},
|
| 1588 |
-
"model.layers.3.mlp.w2": {
|
| 1589 |
-
"input": [
|
| 1590 |
-
-0.2622146010398865,
|
| 1591 |
-
0.26427924633026123
|
| 1592 |
-
],
|
| 1593 |
-
"output": [
|
| 1594 |
-
-0.4150099754333496,
|
| 1595 |
-
0.240339994430542
|
| 1596 |
-
]
|
| 1597 |
-
},
|
| 1598 |
-
"model.layers.3.mlp.w3": {
|
| 1599 |
-
"output": [
|
| 1600 |
-
-0.5215353965759277,
|
| 1601 |
-
0.5596965551376343
|
| 1602 |
-
]
|
| 1603 |
-
},
|
| 1604 |
-
"model.layers.3.post_attention_layernorm": {
|
| 1605 |
-
"input": [
|
| 1606 |
-
-15.465083122253418,
|
| 1607 |
-
2.37296199798584
|
| 1608 |
-
],
|
| 1609 |
-
"output": [
|
| 1610 |
-
-0.4020472466945648,
|
| 1611 |
-
0.3408661186695099
|
| 1612 |
-
]
|
| 1613 |
-
},
|
| 1614 |
-
"model.layers.3.self_attn.k_proj": {
|
| 1615 |
-
"output": [
|
| 1616 |
-
-15.118288040161133,
|
| 1617 |
-
10.582801818847656
|
| 1618 |
-
]
|
| 1619 |
-
},
|
| 1620 |
-
"model.layers.3.self_attn.o_proj": {
|
| 1621 |
-
"output": [
|
| 1622 |
-
-0.24997998774051666,
|
| 1623 |
-
0.40536999702453613
|
| 1624 |
-
]
|
| 1625 |
-
},
|
| 1626 |
-
"model.layers.3.self_attn.pv_bmm": {
|
| 1627 |
-
"input": [
|
| 1628 |
-
-7.779653032891076e-10,
|
| 1629 |
-
10.15169906616211
|
| 1630 |
-
],
|
| 1631 |
-
"input2": [
|
| 1632 |
-
-0.5302785634994507,
|
| 1633 |
-
0.46399378776550293
|
| 1634 |
-
],
|
| 1635 |
-
"output": [
|
| 1636 |
-
-0.2814144492149353,
|
| 1637 |
-
0.2462376356124878
|
| 1638 |
-
]
|
| 1639 |
-
},
|
| 1640 |
-
"model.layers.3.self_attn.q_proj": {
|
| 1641 |
-
"output": [
|
| 1642 |
-
-6.861732482910156,
|
| 1643 |
-
7.025106430053711
|
| 1644 |
-
]
|
| 1645 |
-
},
|
| 1646 |
-
"model.layers.3.self_attn.qk_bmm": {
|
| 1647 |
-
"input": [
|
| 1648 |
-
-6.992506980895996,
|
| 1649 |
-
7.272207260131836
|
| 1650 |
-
],
|
| 1651 |
-
"input2": [
|
| 1652 |
-
-15.041023254394531,
|
| 1653 |
-
14.462522506713867
|
| 1654 |
-
],
|
| 1655 |
-
"output": [
|
| 1656 |
-
-235.2082061767578,
|
| 1657 |
-
207.6825714111328
|
| 1658 |
-
]
|
| 1659 |
-
},
|
| 1660 |
-
"model.layers.3.self_attn.v_proj": {
|
| 1661 |
-
"output": [
|
| 1662 |
-
-0.5320653319358826,
|
| 1663 |
-
0.4655570983886719
|
| 1664 |
-
]
|
| 1665 |
-
},
|
| 1666 |
-
"model.layers.4.input_layernorm": {
|
| 1667 |
-
"input": [
|
| 1668 |
-
-69.28654479980469,
|
| 1669 |
-
10.645393371582031
|
| 1670 |
-
],
|
| 1671 |
-
"output": [
|
| 1672 |
-
-1.145024061203003,
|
| 1673 |
-
1.0339395999908447
|
| 1674 |
-
]
|
| 1675 |
-
},
|
| 1676 |
-
"model.layers.4.mlp.act_fn": {
|
| 1677 |
-
"input2": [
|
| 1678 |
-
6.099214715504786e-07,
|
| 1679 |
-
0.8969005942344666
|
| 1680 |
-
],
|
| 1681 |
-
"output": [
|
| 1682 |
-
-0.2554253041744232,
|
| 1683 |
-
3.815385580062866
|
| 1684 |
-
]
|
| 1685 |
-
},
|
| 1686 |
-
"model.layers.4.mlp.w1": {
|
| 1687 |
-
"output": [
|
| 1688 |
-
-3.362837076187134,
|
| 1689 |
-
2.0645267963409424
|
| 1690 |
-
]
|
| 1691 |
-
},
|
| 1692 |
-
"model.layers.4.mlp.w2": {
|
| 1693 |
-
"input": [
|
| 1694 |
-
-0.2999441921710968,
|
| 1695 |
-
0.2929687201976776
|
| 1696 |
-
],
|
| 1697 |
-
"output": [
|
| 1698 |
-
-0.8785357475280762,
|
| 1699 |
-
0.474479079246521
|
| 1700 |
-
]
|
| 1701 |
-
},
|
| 1702 |
-
"model.layers.4.mlp.w3": {
|
| 1703 |
-
"output": [
|
| 1704 |
-
-0.5457059144973755,
|
| 1705 |
-
0.7548081874847412
|
| 1706 |
-
]
|
| 1707 |
-
},
|
| 1708 |
-
"model.layers.4.post_attention_layernorm": {
|
| 1709 |
-
"input": [
|
| 1710 |
-
-25.324718475341797,
|
| 1711 |
-
3.8873672485351562
|
| 1712 |
-
],
|
| 1713 |
-
"output": [
|
| 1714 |
-
-0.4368909001350403,
|
| 1715 |
-
0.35887467861175537
|
| 1716 |
-
]
|
| 1717 |
-
},
|
| 1718 |
-
"model.layers.4.self_attn.k_proj": {
|
| 1719 |
-
"output": [
|
| 1720 |
-
-17.51902961730957,
|
| 1721 |
-
9.888040542602539
|
| 1722 |
-
]
|
| 1723 |
-
},
|
| 1724 |
-
"model.layers.4.self_attn.o_proj": {
|
| 1725 |
-
"output": [
|
| 1726 |
-
-1.472687005996704,
|
| 1727 |
-
0.4930652379989624
|
| 1728 |
-
]
|
| 1729 |
-
},
|
| 1730 |
-
"model.layers.4.self_attn.pv_bmm": {
|
| 1731 |
-
"input": [
|
| 1732 |
-
-9.67083635394772e-10,
|
| 1733 |
-
3.160961151123047
|
| 1734 |
-
],
|
| 1735 |
-
"input2": [
|
| 1736 |
-
-0.6620192527770996,
|
| 1737 |
-
0.5792667865753174
|
| 1738 |
-
],
|
| 1739 |
-
"output": [
|
| 1740 |
-
-0.42088180780410767,
|
| 1741 |
-
0.3983919620513916
|
| 1742 |
-
]
|
| 1743 |
-
},
|
| 1744 |
-
"model.layers.4.self_attn.q_proj": {
|
| 1745 |
-
"output": [
|
| 1746 |
-
-8.15958309173584,
|
| 1747 |
-
7.139636039733887
|
| 1748 |
-
]
|
| 1749 |
-
},
|
| 1750 |
-
"model.layers.4.self_attn.qk_bmm": {
|
| 1751 |
-
"input": [
|
| 1752 |
-
-7.773740768432617,
|
| 1753 |
-
7.834951400756836
|
| 1754 |
-
],
|
| 1755 |
-
"input2": [
|
| 1756 |
-
-18.371265411376953,
|
| 1757 |
-
17.944026947021484
|
| 1758 |
-
],
|
| 1759 |
-
"output": [
|
| 1760 |
-
-286.5303649902344,
|
| 1761 |
-
196.67303466796875
|
| 1762 |
-
]
|
| 1763 |
-
},
|
| 1764 |
-
"model.layers.4.self_attn.v_proj": {
|
| 1765 |
-
"output": [
|
| 1766 |
-
-0.6622653603553772,
|
| 1767 |
-
0.5794822573661804
|
| 1768 |
-
]
|
| 1769 |
-
},
|
| 1770 |
-
"model.layers.5.input_layernorm": {
|
| 1771 |
-
"input": [
|
| 1772 |
-
-72.35042572021484,
|
| 1773 |
-
11.107322692871094
|
| 1774 |
-
],
|
| 1775 |
-
"output": [
|
| 1776 |
-
-1.012054443359375,
|
| 1777 |
-
1.0041477680206299
|
| 1778 |
-
]
|
| 1779 |
-
},
|
| 1780 |
-
"model.layers.5.mlp.act_fn": {
|
| 1781 |
-
"input2": [
|
| 1782 |
-
3.7543460962297104e-07,
|
| 1783 |
-
0.8639066815376282
|
| 1784 |
-
],
|
| 1785 |
-
"output": [
|
| 1786 |
-
-0.2671676576137543,
|
| 1787 |
-
2.9769954681396484
|
| 1788 |
-
]
|
| 1789 |
-
},
|
| 1790 |
-
"model.layers.5.mlp.w1": {
|
| 1791 |
-
"output": [
|
| 1792 |
-
-2.161452531814575,
|
| 1793 |
-
1.832535982131958
|
| 1794 |
-
]
|
| 1795 |
-
},
|
| 1796 |
-
"model.layers.5.mlp.w2": {
|
| 1797 |
-
"input": [
|
| 1798 |
-
-0.2855253517627716,
|
| 1799 |
-
0.2660577595233917
|
| 1800 |
-
],
|
| 1801 |
-
"output": [
|
| 1802 |
-
-1.3505405187606812,
|
| 1803 |
-
0.5793709754943848
|
| 1804 |
-
]
|
| 1805 |
-
},
|
| 1806 |
-
"model.layers.5.mlp.w3": {
|
| 1807 |
-
"output": [
|
| 1808 |
-
-0.7771786451339722,
|
| 1809 |
-
0.5618791580200195
|
| 1810 |
-
]
|
| 1811 |
-
},
|
| 1812 |
-
"model.layers.5.post_attention_layernorm": {
|
| 1813 |
-
"input": [
|
| 1814 |
-
-16.259342193603516,
|
| 1815 |
-
2.4912033081054688
|
| 1816 |
-
],
|
| 1817 |
-
"output": [
|
| 1818 |
-
-0.6607040166854858,
|
| 1819 |
-
0.47767114639282227
|
| 1820 |
-
]
|
| 1821 |
-
},
|
| 1822 |
-
"model.layers.5.self_attn.k_proj": {
|
| 1823 |
-
"output": [
|
| 1824 |
-
-15.729736328125,
|
| 1825 |
-
17.695953369140625
|
| 1826 |
-
]
|
| 1827 |
-
},
|
| 1828 |
-
"model.layers.5.self_attn.o_proj": {
|
| 1829 |
-
"output": [
|
| 1830 |
-
-0.7585533261299133,
|
| 1831 |
-
0.7648529410362244
|
| 1832 |
-
]
|
| 1833 |
-
},
|
| 1834 |
-
"model.layers.5.self_attn.pv_bmm": {
|
| 1835 |
-
"input": [
|
| 1836 |
-
0.0,
|
| 1837 |
-
4.858019828796387
|
| 1838 |
-
],
|
| 1839 |
-
"input2": [
|
| 1840 |
-
-1.006867527961731,
|
| 1841 |
-
0.48587214946746826
|
| 1842 |
-
],
|
| 1843 |
-
"output": [
|
| 1844 |
-
-0.42437875270843506,
|
| 1845 |
-
0.33770984411239624
|
| 1846 |
-
]
|
| 1847 |
-
},
|
| 1848 |
-
"model.layers.5.self_attn.q_proj": {
|
| 1849 |
-
"output": [
|
| 1850 |
-
-7.287756443023682,
|
| 1851 |
-
7.699162006378174
|
| 1852 |
-
]
|
| 1853 |
-
},
|
| 1854 |
-
"model.layers.5.self_attn.qk_bmm": {
|
| 1855 |
-
"input": [
|
| 1856 |
-
-7.554513931274414,
|
| 1857 |
-
7.1508378982543945
|
| 1858 |
-
],
|
| 1859 |
-
"input2": [
|
| 1860 |
-
-18.049354553222656,
|
| 1861 |
-
16.043872833251953
|
| 1862 |
-
],
|
| 1863 |
-
"output": [
|
| 1864 |
-
-262.8944396972656,
|
| 1865 |
-
207.77316284179688
|
| 1866 |
-
]
|
| 1867 |
-
},
|
| 1868 |
-
"model.layers.5.self_attn.v_proj": {
|
| 1869 |
-
"output": [
|
| 1870 |
-
-1.0068272352218628,
|
| 1871 |
-
0.48585259914398193
|
| 1872 |
-
]
|
| 1873 |
-
},
|
| 1874 |
-
"model.layers.6.input_layernorm": {
|
| 1875 |
-
"input": [
|
| 1876 |
-
-76.28170013427734,
|
| 1877 |
-
11.689178466796875
|
| 1878 |
-
],
|
| 1879 |
-
"output": [
|
| 1880 |
-
-1.3052244186401367,
|
| 1881 |
-
1.2748703956604004
|
| 1882 |
-
]
|
| 1883 |
-
},
|
| 1884 |
-
"model.layers.6.mlp.act_fn": {
|
| 1885 |
-
"input2": [
|
| 1886 |
-
5.687860493708286e-07,
|
| 1887 |
-
0.8548686504364014
|
| 1888 |
-
],
|
| 1889 |
-
"output": [
|
| 1890 |
-
-0.268370658159256,
|
| 1891 |
-
3.5335166454315186
|
| 1892 |
-
]
|
| 1893 |
-
},
|
| 1894 |
-
"model.layers.6.mlp.w1": {
|
| 1895 |
-
"output": [
|
| 1896 |
-
-2.3736090660095215,
|
| 1897 |
-
1.772078037261963
|
| 1898 |
-
]
|
| 1899 |
-
},
|
| 1900 |
-
"model.layers.6.mlp.w2": {
|
| 1901 |
-
"input": [
|
| 1902 |
-
-0.26148250699043274,
|
| 1903 |
-
0.2762435972690582
|
| 1904 |
-
],
|
| 1905 |
-
"output": [
|
| 1906 |
-
-1.1666910648345947,
|
| 1907 |
-
0.9592397212982178
|
| 1908 |
-
]
|
| 1909 |
-
},
|
| 1910 |
-
"model.layers.6.mlp.w3": {
|
| 1911 |
-
"output": [
|
| 1912 |
-
-0.5539140701293945,
|
| 1913 |
-
0.6330446004867554
|
| 1914 |
-
]
|
| 1915 |
-
},
|
| 1916 |
-
"model.layers.6.post_attention_layernorm": {
|
| 1917 |
-
"input": [
|
| 1918 |
-
-44.39370346069336,
|
| 1919 |
-
6.7775421142578125
|
| 1920 |
-
],
|
| 1921 |
-
"output": [
|
| 1922 |
-
-0.5560799241065979,
|
| 1923 |
-
0.5263656973838806
|
| 1924 |
-
]
|
| 1925 |
-
},
|
| 1926 |
-
"model.layers.6.self_attn.k_proj": {
|
| 1927 |
-
"output": [
|
| 1928 |
-
-17.042301177978516,
|
| 1929 |
-
18.578903198242188
|
| 1930 |
-
]
|
| 1931 |
-
},
|
| 1932 |
-
"model.layers.6.self_attn.o_proj": {
|
| 1933 |
-
"output": [
|
| 1934 |
-
-0.4106226861476898,
|
| 1935 |
-
0.5218151807785034
|
| 1936 |
-
]
|
| 1937 |
-
},
|
| 1938 |
-
"model.layers.6.self_attn.pv_bmm": {
|
| 1939 |
-
"input": [
|
| 1940 |
-
0.0,
|
| 1941 |
-
10.370061874389648
|
| 1942 |
-
],
|
| 1943 |
-
"input2": [
|
| 1944 |
-
-0.6833804845809937,
|
| 1945 |
-
0.7449966669082642
|
| 1946 |
-
],
|
| 1947 |
-
"output": [
|
| 1948 |
-
-0.5550251603126526,
|
| 1949 |
-
0.47056490182876587
|
| 1950 |
-
]
|
| 1951 |
-
},
|
| 1952 |
-
"model.layers.6.self_attn.q_proj": {
|
| 1953 |
-
"output": [
|
| 1954 |
-
-7.373525619506836,
|
| 1955 |
-
8.426886558532715
|
| 1956 |
-
]
|
| 1957 |
-
},
|
| 1958 |
-
"model.layers.6.self_attn.qk_bmm": {
|
| 1959 |
-
"input": [
|
| 1960 |
-
-6.766021251678467,
|
| 1961 |
-
8.368499755859375
|
| 1962 |
-
],
|
| 1963 |
-
"input2": [
|
| 1964 |
-
-18.750553131103516,
|
| 1965 |
-
19.50057601928711
|
| 1966 |
-
],
|
| 1967 |
-
"output": [
|
| 1968 |
-
-284.78106689453125,
|
| 1969 |
-
221.37881469726562
|
| 1970 |
-
]
|
| 1971 |
-
},
|
| 1972 |
-
"model.layers.6.self_attn.v_proj": {
|
| 1973 |
-
"output": [
|
| 1974 |
-
-0.6834059953689575,
|
| 1975 |
-
0.745024561882019
|
| 1976 |
-
]
|
| 1977 |
-
},
|
| 1978 |
-
"model.layers.7.input_layernorm": {
|
| 1979 |
-
"input": [
|
| 1980 |
-
-76.0637435913086,
|
| 1981 |
-
11.614128112792969
|
| 1982 |
-
],
|
| 1983 |
-
"output": [
|
| 1984 |
-
-1.5509907007217407,
|
| 1985 |
-
1.56320321559906
|
| 1986 |
-
]
|
| 1987 |
-
},
|
| 1988 |
-
"model.layers.7.mlp.act_fn": {
|
| 1989 |
-
"input2": [
|
| 1990 |
-
-9.137278880189115e-07,
|
| 1991 |
-
0.9197782278060913
|
| 1992 |
-
],
|
| 1993 |
-
"output": [
|
| 1994 |
-
-0.22567085921764374,
|
| 1995 |
-
18.931161880493164
|
| 1996 |
-
]
|
| 1997 |
-
},
|
| 1998 |
-
"model.layers.7.mlp.w1": {
|
| 1999 |
-
"output": [
|
| 2000 |
-
-6.370095729827881,
|
| 2001 |
-
20.25897789001465
|
| 2002 |
-
]
|
| 2003 |
-
},
|
| 2004 |
-
"model.layers.7.mlp.w2": {
|
| 2005 |
-
"input": [
|
| 2006 |
-
-10.818718910217285,
|
| 2007 |
-
1.442495346069336
|
| 2008 |
-
],
|
| 2009 |
-
"output": [
|
| 2010 |
-
-68.0284194946289,
|
| 2011 |
-
5.880210876464844
|
| 2012 |
-
]
|
| 2013 |
-
},
|
| 2014 |
-
"model.layers.7.mlp.w3": {
|
| 2015 |
-
"output": [
|
| 2016 |
-
-4.026743412017822,
|
| 2017 |
-
3.9330978393554688
|
| 2018 |
-
]
|
| 2019 |
-
},
|
| 2020 |
-
"model.layers.7.post_attention_layernorm": {
|
| 2021 |
-
"input": [
|
| 2022 |
-
-44.210880279541016,
|
| 2023 |
-
6.738880157470703
|
| 2024 |
-
],
|
| 2025 |
-
"output": [
|
| 2026 |
-
-1.1832901239395142,
|
| 2027 |
-
0.6792961359024048
|
| 2028 |
-
]
|
| 2029 |
-
},
|
| 2030 |
-
"model.layers.7.self_attn.k_proj": {
|
| 2031 |
-
"output": [
|
| 2032 |
-
-17.08796501159668,
|
| 2033 |
-
17.494821548461914
|
| 2034 |
-
]
|
| 2035 |
-
},
|
| 2036 |
-
"model.layers.7.self_attn.o_proj": {
|
| 2037 |
-
"output": [
|
| 2038 |
-
-0.3788287341594696,
|
| 2039 |
-
0.7155746221542358
|
| 2040 |
-
]
|
| 2041 |
-
},
|
| 2042 |
-
"model.layers.7.self_attn.pv_bmm": {
|
| 2043 |
-
"input": [
|
| 2044 |
-
0.0,
|
| 2045 |
-
14.152711868286133
|
| 2046 |
-
],
|
| 2047 |
-
"input2": [
|
| 2048 |
-
-0.9549614191055298,
|
| 2049 |
-
0.9624807834625244
|
| 2050 |
-
],
|
| 2051 |
-
"output": [
|
| 2052 |
-
-0.523362398147583,
|
| 2053 |
-
0.712354302406311
|
| 2054 |
-
]
|
| 2055 |
-
},
|
| 2056 |
-
"model.layers.7.self_attn.q_proj": {
|
| 2057 |
-
"output": [
|
| 2058 |
-
-9.399189949035645,
|
| 2059 |
-
10.246659278869629
|
| 2060 |
-
]
|
| 2061 |
-
},
|
| 2062 |
-
"model.layers.7.self_attn.qk_bmm": {
|
| 2063 |
-
"input": [
|
| 2064 |
-
-9.251260757446289,
|
| 2065 |
-
10.74087142944336
|
| 2066 |
-
],
|
| 2067 |
-
"input2": [
|
| 2068 |
-
-17.5736083984375,
|
| 2069 |
-
16.897701263427734
|
| 2070 |
-
],
|
| 2071 |
-
"output": [
|
| 2072 |
-
-341.1612548828125,
|
| 2073 |
-
198.99151611328125
|
| 2074 |
-
]
|
| 2075 |
-
},
|
| 2076 |
-
"model.layers.7.self_attn.v_proj": {
|
| 2077 |
-
"output": [
|
| 2078 |
-
-0.9533576965332031,
|
| 2079 |
-
0.9608644247055054
|
| 2080 |
-
]
|
| 2081 |
-
},
|
| 2082 |
-
"model.layers.8.input_layernorm": {
|
| 2083 |
-
"input": [
|
| 2084 |
-
-61.41298294067383,
|
| 2085 |
-
6.890247344970703
|
| 2086 |
-
],
|
| 2087 |
-
"output": [
|
| 2088 |
-
-2.4262712001800537,
|
| 2089 |
-
2.645033597946167
|
| 2090 |
-
]
|
| 2091 |
-
},
|
| 2092 |
-
"model.layers.8.mlp.act_fn": {
|
| 2093 |
-
"input2": [
|
| 2094 |
-
2.2724009340890916e-06,
|
| 2095 |
-
0.9171198010444641
|
| 2096 |
-
],
|
| 2097 |
-
"output": [
|
| 2098 |
-
-0.2660808563232422,
|
| 2099 |
-
4.578679084777832
|
| 2100 |
-
]
|
| 2101 |
-
},
|
| 2102 |
-
"model.layers.8.mlp.w1": {
|
| 2103 |
-
"output": [
|
| 2104 |
-
-4.160639762878418,
|
| 2105 |
-
2.4291930198669434
|
| 2106 |
-
]
|
| 2107 |
-
},
|
| 2108 |
-
"model.layers.8.mlp.w2": {
|
| 2109 |
-
"input": [
|
| 2110 |
-
-0.30407947301864624,
|
| 2111 |
-
0.3113194704055786
|
| 2112 |
-
],
|
| 2113 |
-
"output": [
|
| 2114 |
-
-0.49675124883651733,
|
| 2115 |
-
0.44169193506240845
|
| 2116 |
-
]
|
| 2117 |
-
},
|
| 2118 |
-
"model.layers.8.mlp.w3": {
|
| 2119 |
-
"output": [
|
| 2120 |
-
-0.8565957546234131,
|
| 2121 |
-
0.6816571950912476
|
| 2122 |
-
]
|
| 2123 |
-
},
|
| 2124 |
-
"model.layers.8.post_attention_layernorm": {
|
| 2125 |
-
"input": [
|
| 2126 |
-
-39.070579528808594,
|
| 2127 |
-
4.379852294921875
|
| 2128 |
-
],
|
| 2129 |
-
"output": [
|
| 2130 |
-
-0.64253169298172,
|
| 2131 |
-
0.589389979839325
|
| 2132 |
-
]
|
| 2133 |
-
},
|
| 2134 |
-
"model.layers.8.self_attn.k_proj": {
|
| 2135 |
-
"output": [
|
| 2136 |
-
-23.870710372924805,
|
| 2137 |
-
24.439062118530273
|
| 2138 |
-
]
|
| 2139 |
-
},
|
| 2140 |
-
"model.layers.8.self_attn.o_proj": {
|
| 2141 |
-
"output": [
|
| 2142 |
-
-1.288500428199768,
|
| 2143 |
-
0.9605840444564819
|
| 2144 |
-
]
|
| 2145 |
-
},
|
| 2146 |
-
"model.layers.8.self_attn.pv_bmm": {
|
| 2147 |
-
"input": [
|
| 2148 |
-
-2.849586122621872e-10,
|
| 2149 |
-
5.764626502990723
|
| 2150 |
-
],
|
| 2151 |
-
"input2": [
|
| 2152 |
-
-0.7795315980911255,
|
| 2153 |
-
1.2283529043197632
|
| 2154 |
-
],
|
| 2155 |
-
"output": [
|
| 2156 |
-
-0.6425102353096008,
|
| 2157 |
-
1.029327630996704
|
| 2158 |
-
]
|
| 2159 |
-
},
|
| 2160 |
-
"model.layers.8.self_attn.q_proj": {
|
| 2161 |
-
"output": [
|
| 2162 |
-
-9.715987205505371,
|
| 2163 |
-
10.930485725402832
|
| 2164 |
-
]
|
| 2165 |
-
},
|
| 2166 |
-
"model.layers.8.self_attn.qk_bmm": {
|
| 2167 |
-
"input": [
|
| 2168 |
-
-11.523988723754883,
|
| 2169 |
-
11.433958053588867
|
| 2170 |
-
],
|
| 2171 |
-
"input2": [
|
| 2172 |
-
-23.01451873779297,
|
| 2173 |
-
28.01767349243164
|
| 2174 |
-
],
|
| 2175 |
-
"output": [
|
| 2176 |
-
-531.0772705078125,
|
| 2177 |
-
249.6875
|
| 2178 |
-
]
|
| 2179 |
-
},
|
| 2180 |
-
"model.layers.8.self_attn.v_proj": {
|
| 2181 |
-
"output": [
|
| 2182 |
-
-0.77955162525177,
|
| 2183 |
-
1.2283843755722046
|
| 2184 |
-
]
|
| 2185 |
-
},
|
| 2186 |
-
"model.layers.9.input_layernorm": {
|
| 2187 |
-
"input": [
|
| 2188 |
-
-63.642173767089844,
|
| 2189 |
-
7.1283416748046875
|
| 2190 |
-
],
|
| 2191 |
-
"output": [
|
| 2192 |
-
-1.4341191053390503,
|
| 2193 |
-
1.5881980657577515
|
| 2194 |
-
]
|
| 2195 |
-
},
|
| 2196 |
-
"model.layers.9.mlp.act_fn": {
|
| 2197 |
-
"input2": [
|
| 2198 |
-
3.249040446462459e-06,
|
| 2199 |
-
0.9275291562080383
|
| 2200 |
-
],
|
| 2201 |
-
"output": [
|
| 2202 |
-
-0.2559678554534912,
|
| 2203 |
-
6.990260124206543
|
| 2204 |
-
]
|
| 2205 |
-
},
|
| 2206 |
-
"model.layers.9.mlp.w1": {
|
| 2207 |
-
"output": [
|
| 2208 |
-
-2.845679521560669,
|
| 2209 |
-
3.5196564197540283
|
| 2210 |
-
]
|
| 2211 |
-
},
|
| 2212 |
-
"model.layers.9.mlp.w2": {
|
| 2213 |
-
"input": [
|
| 2214 |
-
-0.31340545415878296,
|
| 2215 |
-
0.35817772150039673
|
| 2216 |
-
],
|
| 2217 |
-
"output": [
|
| 2218 |
-
-1.1538662910461426,
|
| 2219 |
-
0.8241255283355713
|
| 2220 |
-
]
|
| 2221 |
-
},
|
| 2222 |
-
"model.layers.9.mlp.w3": {
|
| 2223 |
-
"output": [
|
| 2224 |
-
-0.6430490612983704,
|
| 2225 |
-
0.6687710881233215
|
| 2226 |
-
]
|
| 2227 |
-
},
|
| 2228 |
-
"model.layers.9.post_attention_layernorm": {
|
| 2229 |
-
"input": [
|
| 2230 |
-
-47.34988021850586,
|
| 2231 |
-
5.296352386474609
|
| 2232 |
-
],
|
| 2233 |
-
"output": [
|
| 2234 |
-
-0.6652911901473999,
|
| 2235 |
-
0.8494342565536499
|
| 2236 |
-
]
|
| 2237 |
-
},
|
| 2238 |
-
"model.layers.9.self_attn.k_proj": {
|
| 2239 |
-
"output": [
|
| 2240 |
-
-19.59954833984375,
|
| 2241 |
-
18.552242279052734
|
| 2242 |
-
]
|
| 2243 |
-
},
|
| 2244 |
-
"model.layers.9.self_attn.o_proj": {
|
| 2245 |
-
"output": [
|
| 2246 |
-
-0.9600111246109009,
|
| 2247 |
-
0.7467882633209229
|
| 2248 |
-
]
|
| 2249 |
-
},
|
| 2250 |
-
"model.layers.9.self_attn.pv_bmm": {
|
| 2251 |
-
"input": [
|
| 2252 |
-
0.0,
|
| 2253 |
-
10.371491432189941
|
| 2254 |
-
],
|
| 2255 |
-
"input2": [
|
| 2256 |
-
-1.1789764165878296,
|
| 2257 |
-
0.9838939905166626
|
| 2258 |
-
],
|
| 2259 |
-
"output": [
|
| 2260 |
-
-0.702292263507843,
|
| 2261 |
-
0.6048941016197205
|
| 2262 |
-
]
|
| 2263 |
-
},
|
| 2264 |
-
"model.layers.9.self_attn.q_proj": {
|
| 2265 |
-
"output": [
|
| 2266 |
-
-7.073794841766357,
|
| 2267 |
-
7.958018779754639
|
| 2268 |
-
]
|
| 2269 |
-
},
|
| 2270 |
-
"model.layers.9.self_attn.qk_bmm": {
|
| 2271 |
-
"input": [
|
| 2272 |
-
-8.201776504516602,
|
| 2273 |
-
7.064304351806641
|
| 2274 |
-
],
|
| 2275 |
-
"input2": [
|
| 2276 |
-
-19.554767608642578,
|
| 2277 |
-
18.802661895751953
|
| 2278 |
-
],
|
| 2279 |
-
"output": [
|
| 2280 |
-
-267.5766296386719,
|
| 2281 |
-
236.26300048828125
|
| 2282 |
-
]
|
| 2283 |
-
},
|
| 2284 |
-
"model.layers.9.self_attn.v_proj": {
|
| 2285 |
-
"output": [
|
| 2286 |
-
-1.1789911985397339,
|
| 2287 |
-
0.9839063882827759
|
| 2288 |
-
]
|
| 2289 |
-
}
|
| 2290 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:110dccb5a5a605efea1c6d6e9be9af17d68244fc90707f46968329510eeca00e
|
| 3 |
+
size 53168
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -1,50 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"HFForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id": 1,
|
| 9 |
-
"embd_pdrop": 0.0,
|
| 10 |
-
"eos_token_id": 2,
|
| 11 |
-
"head_dim": null,
|
| 12 |
-
"hidden_act": "silu",
|
| 13 |
-
"hidden_size": 2048,
|
| 14 |
-
"initializer_range": 0.02,
|
| 15 |
-
"intermediate_size": 5632,
|
| 16 |
-
"l2norm_as_rmsnorm": true,
|
| 17 |
-
"layer_norm_eps": 1e-05,
|
| 18 |
-
"max_position_embeddings": 2048,
|
| 19 |
-
"mlp_bias": false,
|
| 20 |
-
"model_type": "hfmodel",
|
| 21 |
-
"norm_class": "rmsnorm",
|
| 22 |
-
"normalize_embed": false,
|
| 23 |
-
"normalizie_embed": false,
|
| 24 |
-
"num_attention_heads": 32,
|
| 25 |
-
"num_experts_per_tok": 1,
|
| 26 |
-
"num_hidden_layers": 22,
|
| 27 |
-
"num_key_value_heads": 4,
|
| 28 |
-
"num_linears_per_mlp": 3,
|
| 29 |
-
"num_local_experts": 1,
|
| 30 |
-
"output_router_logits": false,
|
| 31 |
-
"parallel_residual": false,
|
| 32 |
-
"partial_rotary_factor": 1.0,
|
| 33 |
-
"pretraining_tp": 1,
|
| 34 |
-
"qk_layernorm": false,
|
| 35 |
-
"resid_pdrop": 0.0,
|
| 36 |
-
"rope_scaling": null,
|
| 37 |
-
"rope_theta": 10000.0,
|
| 38 |
-
"router_aux_loss_coef": 0.001,
|
| 39 |
-
"shared_attention_norm": false,
|
| 40 |
-
"sliding_window": null,
|
| 41 |
-
"static_causal_mask": false,
|
| 42 |
-
"tie_word_embeddings": false,
|
| 43 |
-
"torch_dtype": "float32",
|
| 44 |
-
"transformers_version": "4.41.0.dev0",
|
| 45 |
-
"use_cache": true,
|
| 46 |
-
"use_matmul_as_module": true,
|
| 47 |
-
"use_megablocks": false,
|
| 48 |
-
"use_qkv_bias_only": false,
|
| 49 |
-
"vocab_size": 32000
|
| 50 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3813577311a23b9ae7530b6b0504e7a6560aedbe813bcee72d479a6f0bead81e
|
| 3 |
+
size 1307
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
default_qcfg.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
generation_config.json
CHANGED
|
@@ -1,7 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"max_length": 2048,
|
| 5 |
-
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.41.0.dev0"
|
| 7 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56cf26bf2918fddebbfcb484144e503431a431f8b3695a502d4228b7978cd216
|
| 3 |
+
size 129
|
|
|
|
|
|
|
|
|
|
|
|
results.json
CHANGED
|
@@ -1,24 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"batch_sizes": [],
|
| 5 |
-
"bootstrap_iters": 100000,
|
| 6 |
-
"description_dict": null,
|
| 7 |
-
"device": null,
|
| 8 |
-
"limit": null,
|
| 9 |
-
"model": "llama-1.1b-e2e-w4a8-s1024-e60",
|
| 10 |
-
"model_args": null,
|
| 11 |
-
"no_cache": true,
|
| 12 |
-
"num_fewshot": 0
|
| 13 |
-
},
|
| 14 |
-
"results": {
|
| 15 |
-
"wikitext": {
|
| 16 |
-
"bits_per_byte": 0.7654894102768953,
|
| 17 |
-
"byte_perplexity": 1.6999465790529529,
|
| 18 |
-
"word_perplexity": 17.070303884500657
|
| 19 |
-
}
|
| 20 |
-
},
|
| 21 |
-
"versions": {
|
| 22 |
-
"wikitext": 1
|
| 23 |
-
}
|
| 24 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60d877bb88f14c1c0f1bcbdb5e3f5999443626766bf6ba55dc7f3f0f9d8aed4b
|
| 3 |
+
size 575
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,30 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 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 |
-
"pad_token": {
|
| 17 |
-
"content": "</s>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
-
"unk_token": {
|
| 24 |
-
"content": "<unk>",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": false,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
}
|
| 30 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82d96d7a9e6ced037f12394b7ea6a5b02e6ca87e0d11edaa8d60d9be857ce7db
|
| 3 |
+
size 551
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,44 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 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 |
-
"bos_token": "<s>",
|
| 32 |
-
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 33 |
-
"clean_up_tokenization_spaces": false,
|
| 34 |
-
"eos_token": "</s>",
|
| 35 |
-
"legacy": false,
|
| 36 |
-
"model_max_length": 2048,
|
| 37 |
-
"pad_token": "</s>",
|
| 38 |
-
"padding_side": "right",
|
| 39 |
-
"sp_model_kwargs": {},
|
| 40 |
-
"spaces_between_special_tokens": false,
|
| 41 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
-
"unk_token": "<unk>",
|
| 43 |
-
"use_default_system_prompt": false
|
| 44 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6025dc3da07c0b33ed86a1f613b1b6a7d92d27822ee1d860d86812afa66c1b64
|
| 3 |
+
size 1410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|