jangq commited on
Commit
e19487b
·
verified ·
1 Parent(s): 5d3697d

config.json: per-module quant overrides + rope_parameters (metadata bug fix)

Browse files
Files changed (1) hide show
  1. config.json +1257 -2
config.json CHANGED
@@ -99,8 +99,1263 @@
99
  "vocab_size": 200064,
100
  "quantization": {
101
  "group_size": 64,
102
- "bits": 4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
  },
104
  "weight_format": "mxtq",
105
- "mxtq_bits": 4
 
 
 
 
106
  }
 
99
  "vocab_size": 200064,
100
  "quantization": {
101
  "group_size": 64,
102
+ "bits": 8,
103
+ "mode": "affine",
104
+ "model.layers.37.self_attn.o_proj": {
105
+ "bits": 8,
106
+ "group_size": 64,
107
+ "mode": "affine"
108
+ },
109
+ "model.layers.0.self_attn.o_proj": {
110
+ "bits": 8,
111
+ "group_size": 64,
112
+ "mode": "affine"
113
+ },
114
+ "model.layers.60.self_attn.o_proj": {
115
+ "bits": 8,
116
+ "group_size": 64,
117
+ "mode": "affine"
118
+ },
119
+ "model.layers.56.self_attn.v_proj": {
120
+ "bits": 8,
121
+ "group_size": 64,
122
+ "mode": "affine"
123
+ },
124
+ "model.layers.25.self_attn.o_proj": {
125
+ "bits": 8,
126
+ "group_size": 64,
127
+ "mode": "affine"
128
+ },
129
+ "model.layers.8.self_attn.k_proj": {
130
+ "bits": 8,
131
+ "group_size": 64,
132
+ "mode": "affine"
133
+ },
134
+ "model.layers.4.self_attn.o_proj": {
135
+ "bits": 8,
136
+ "group_size": 64,
137
+ "mode": "affine"
138
+ },
139
+ "model.layers.52.self_attn.v_proj": {
140
+ "bits": 8,
141
+ "group_size": 64,
142
+ "mode": "affine"
143
+ },
144
+ "model.layers.28.self_attn.k_proj": {
145
+ "bits": 8,
146
+ "group_size": 64,
147
+ "mode": "affine"
148
+ },
149
+ "model.layers.3.self_attn.v_proj": {
150
+ "bits": 8,
151
+ "group_size": 64,
152
+ "mode": "affine"
153
+ },
154
+ "model.layers.39.self_attn.q_proj": {
155
+ "bits": 8,
156
+ "group_size": 64,
157
+ "mode": "affine"
158
+ },
159
+ "model.layers.0.self_attn.v_proj": {
160
+ "bits": 8,
161
+ "group_size": 64,
162
+ "mode": "affine"
163
+ },
164
+ "model.layers.5.self_attn.v_proj": {
165
+ "bits": 8,
166
+ "group_size": 64,
167
+ "mode": "affine"
168
+ },
169
+ "model.layers.54.self_attn.k_proj": {
170
+ "bits": 8,
171
+ "group_size": 64,
172
+ "mode": "affine"
173
+ },
174
+ "model.layers.15.self_attn.q_proj": {
175
+ "bits": 8,
176
+ "group_size": 64,
177
+ "mode": "affine"
178
+ },
179
+ "model.layers.12.self_attn.q_proj": {
180
+ "bits": 8,
181
+ "group_size": 64,
182
+ "mode": "affine"
183
+ },
184
+ "model.layers.3.self_attn.q_proj": {
185
+ "bits": 8,
186
+ "group_size": 64,
187
+ "mode": "affine"
188
+ },
189
+ "model.layers.46.self_attn.k_proj": {
190
+ "bits": 8,
191
+ "group_size": 64,
192
+ "mode": "affine"
193
+ },
194
+ "model.layers.1.self_attn.k_proj": {
195
+ "bits": 8,
196
+ "group_size": 64,
197
+ "mode": "affine"
198
+ },
199
+ "model.layers.28.self_attn.v_proj": {
200
+ "bits": 8,
201
+ "group_size": 64,
202
+ "mode": "affine"
203
+ },
204
+ "model.layers.9.self_attn.o_proj": {
205
+ "bits": 8,
206
+ "group_size": 64,
207
+ "mode": "affine"
208
+ },
209
+ "model.layers.60.self_attn.v_proj": {
210
+ "bits": 8,
211
+ "group_size": 64,
212
+ "mode": "affine"
213
+ },
214
+ "model.layers.53.self_attn.k_proj": {
215
+ "bits": 8,
216
+ "group_size": 64,
217
+ "mode": "affine"
218
+ },
219
+ "model.layers.59.self_attn.v_proj": {
220
+ "bits": 8,
221
+ "group_size": 64,
222
+ "mode": "affine"
223
+ },
224
+ "model.layers.22.self_attn.o_proj": {
225
+ "bits": 8,
226
+ "group_size": 64,
227
+ "mode": "affine"
228
+ },
229
+ "model.layers.40.self_attn.o_proj": {
230
+ "bits": 8,
231
+ "group_size": 64,
232
+ "mode": "affine"
233
+ },
234
+ "model.layers.12.self_attn.v_proj": {
235
+ "bits": 8,
236
+ "group_size": 64,
237
+ "mode": "affine"
238
+ },
239
+ "model.layers.11.self_attn.o_proj": {
240
+ "bits": 8,
241
+ "group_size": 64,
242
+ "mode": "affine"
243
+ },
244
+ "model.layers.50.self_attn.q_proj": {
245
+ "bits": 8,
246
+ "group_size": 64,
247
+ "mode": "affine"
248
+ },
249
+ "model.layers.31.self_attn.v_proj": {
250
+ "bits": 8,
251
+ "group_size": 64,
252
+ "mode": "affine"
253
+ },
254
+ "model.layers.39.self_attn.o_proj": {
255
+ "bits": 8,
256
+ "group_size": 64,
257
+ "mode": "affine"
258
+ },
259
+ "model.layers.18.self_attn.v_proj": {
260
+ "bits": 8,
261
+ "group_size": 64,
262
+ "mode": "affine"
263
+ },
264
+ "model.layers.19.self_attn.q_proj": {
265
+ "bits": 8,
266
+ "group_size": 64,
267
+ "mode": "affine"
268
+ },
269
+ "model.layers.23.self_attn.v_proj": {
270
+ "bits": 8,
271
+ "group_size": 64,
272
+ "mode": "affine"
273
+ },
274
+ "model.layers.30.self_attn.o_proj": {
275
+ "bits": 8,
276
+ "group_size": 64,
277
+ "mode": "affine"
278
+ },
279
+ "model.layers.33.self_attn.v_proj": {
280
+ "bits": 8,
281
+ "group_size": 64,
282
+ "mode": "affine"
283
+ },
284
+ "model.layers.23.self_attn.q_proj": {
285
+ "bits": 8,
286
+ "group_size": 64,
287
+ "mode": "affine"
288
+ },
289
+ "model.layers.36.self_attn.v_proj": {
290
+ "bits": 8,
291
+ "group_size": 64,
292
+ "mode": "affine"
293
+ },
294
+ "model.layers.61.self_attn.v_proj": {
295
+ "bits": 8,
296
+ "group_size": 64,
297
+ "mode": "affine"
298
+ },
299
+ "model.layers.22.self_attn.q_proj": {
300
+ "bits": 8,
301
+ "group_size": 64,
302
+ "mode": "affine"
303
+ },
304
+ "model.layers.50.self_attn.k_proj": {
305
+ "bits": 8,
306
+ "group_size": 64,
307
+ "mode": "affine"
308
+ },
309
+ "model.layers.2.self_attn.o_proj": {
310
+ "bits": 8,
311
+ "group_size": 64,
312
+ "mode": "affine"
313
+ },
314
+ "model.layers.45.self_attn.k_proj": {
315
+ "bits": 8,
316
+ "group_size": 64,
317
+ "mode": "affine"
318
+ },
319
+ "model.layers.50.self_attn.o_proj": {
320
+ "bits": 8,
321
+ "group_size": 64,
322
+ "mode": "affine"
323
+ },
324
+ "model.layers.55.self_attn.q_proj": {
325
+ "bits": 8,
326
+ "group_size": 64,
327
+ "mode": "affine"
328
+ },
329
+ "model.layers.9.self_attn.v_proj": {
330
+ "bits": 8,
331
+ "group_size": 64,
332
+ "mode": "affine"
333
+ },
334
+ "model.layers.10.self_attn.q_proj": {
335
+ "bits": 8,
336
+ "group_size": 64,
337
+ "mode": "affine"
338
+ },
339
+ "model.layers.54.self_attn.o_proj": {
340
+ "bits": 8,
341
+ "group_size": 64,
342
+ "mode": "affine"
343
+ },
344
+ "model.layers.51.self_attn.v_proj": {
345
+ "bits": 8,
346
+ "group_size": 64,
347
+ "mode": "affine"
348
+ },
349
+ "model.layers.3.self_attn.o_proj": {
350
+ "bits": 8,
351
+ "group_size": 64,
352
+ "mode": "affine"
353
+ },
354
+ "model.layers.8.self_attn.v_proj": {
355
+ "bits": 8,
356
+ "group_size": 64,
357
+ "mode": "affine"
358
+ },
359
+ "model.layers.53.self_attn.v_proj": {
360
+ "bits": 8,
361
+ "group_size": 64,
362
+ "mode": "affine"
363
+ },
364
+ "model.layers.12.self_attn.k_proj": {
365
+ "bits": 8,
366
+ "group_size": 64,
367
+ "mode": "affine"
368
+ },
369
+ "model.layers.14.self_attn.k_proj": {
370
+ "bits": 8,
371
+ "group_size": 64,
372
+ "mode": "affine"
373
+ },
374
+ "model.layers.47.self_attn.k_proj": {
375
+ "bits": 8,
376
+ "group_size": 64,
377
+ "mode": "affine"
378
+ },
379
+ "model.layers.42.self_attn.v_proj": {
380
+ "bits": 8,
381
+ "group_size": 64,
382
+ "mode": "affine"
383
+ },
384
+ "model.layers.45.self_attn.v_proj": {
385
+ "bits": 8,
386
+ "group_size": 64,
387
+ "mode": "affine"
388
+ },
389
+ "model.layers.30.self_attn.k_proj": {
390
+ "bits": 8,
391
+ "group_size": 64,
392
+ "mode": "affine"
393
+ },
394
+ "model.layers.52.self_attn.o_proj": {
395
+ "bits": 8,
396
+ "group_size": 64,
397
+ "mode": "affine"
398
+ },
399
+ "model.layers.10.self_attn.o_proj": {
400
+ "bits": 8,
401
+ "group_size": 64,
402
+ "mode": "affine"
403
+ },
404
+ "model.layers.53.self_attn.q_proj": {
405
+ "bits": 8,
406
+ "group_size": 64,
407
+ "mode": "affine"
408
+ },
409
+ "model.layers.37.self_attn.k_proj": {
410
+ "bits": 8,
411
+ "group_size": 64,
412
+ "mode": "affine"
413
+ },
414
+ "model.layers.20.self_attn.q_proj": {
415
+ "bits": 8,
416
+ "group_size": 64,
417
+ "mode": "affine"
418
+ },
419
+ "model.layers.24.self_attn.k_proj": {
420
+ "bits": 8,
421
+ "group_size": 64,
422
+ "mode": "affine"
423
+ },
424
+ "model.layers.29.self_attn.v_proj": {
425
+ "bits": 8,
426
+ "group_size": 64,
427
+ "mode": "affine"
428
+ },
429
+ "model.layers.22.self_attn.v_proj": {
430
+ "bits": 8,
431
+ "group_size": 64,
432
+ "mode": "affine"
433
+ },
434
+ "model.layers.23.self_attn.o_proj": {
435
+ "bits": 8,
436
+ "group_size": 64,
437
+ "mode": "affine"
438
+ },
439
+ "model.layers.24.self_attn.v_proj": {
440
+ "bits": 8,
441
+ "group_size": 64,
442
+ "mode": "affine"
443
+ },
444
+ "model.layers.56.self_attn.o_proj": {
445
+ "bits": 8,
446
+ "group_size": 64,
447
+ "mode": "affine"
448
+ },
449
+ "model.layers.22.self_attn.k_proj": {
450
+ "bits": 8,
451
+ "group_size": 64,
452
+ "mode": "affine"
453
+ },
454
+ "model.layers.24.self_attn.q_proj": {
455
+ "bits": 8,
456
+ "group_size": 64,
457
+ "mode": "affine"
458
+ },
459
+ "model.layers.11.self_attn.k_proj": {
460
+ "bits": 8,
461
+ "group_size": 64,
462
+ "mode": "affine"
463
+ },
464
+ "model.layers.49.self_attn.k_proj": {
465
+ "bits": 8,
466
+ "group_size": 64,
467
+ "mode": "affine"
468
+ },
469
+ "model.layers.33.self_attn.o_proj": {
470
+ "bits": 8,
471
+ "group_size": 64,
472
+ "mode": "affine"
473
+ },
474
+ "model.layers.40.self_attn.v_proj": {
475
+ "bits": 8,
476
+ "group_size": 64,
477
+ "mode": "affine"
478
+ },
479
+ "model.layers.14.self_attn.q_proj": {
480
+ "bits": 8,
481
+ "group_size": 64,
482
+ "mode": "affine"
483
+ },
484
+ "model.layers.34.self_attn.k_proj": {
485
+ "bits": 8,
486
+ "group_size": 64,
487
+ "mode": "affine"
488
+ },
489
+ "model.layers.29.self_attn.q_proj": {
490
+ "bits": 8,
491
+ "group_size": 64,
492
+ "mode": "affine"
493
+ },
494
+ "model.layers.51.self_attn.k_proj": {
495
+ "bits": 8,
496
+ "group_size": 64,
497
+ "mode": "affine"
498
+ },
499
+ "model.layers.34.self_attn.v_proj": {
500
+ "bits": 8,
501
+ "group_size": 64,
502
+ "mode": "affine"
503
+ },
504
+ "model.layers.32.self_attn.o_proj": {
505
+ "bits": 8,
506
+ "group_size": 64,
507
+ "mode": "affine"
508
+ },
509
+ "model.layers.38.self_attn.k_proj": {
510
+ "bits": 8,
511
+ "group_size": 64,
512
+ "mode": "affine"
513
+ },
514
+ "model.layers.55.self_attn.o_proj": {
515
+ "bits": 8,
516
+ "group_size": 64,
517
+ "mode": "affine"
518
+ },
519
+ "model.layers.16.self_attn.q_proj": {
520
+ "bits": 8,
521
+ "group_size": 64,
522
+ "mode": "affine"
523
+ },
524
+ "model.layers.25.self_attn.v_proj": {
525
+ "bits": 8,
526
+ "group_size": 64,
527
+ "mode": "affine"
528
+ },
529
+ "model.layers.60.self_attn.k_proj": {
530
+ "bits": 8,
531
+ "group_size": 64,
532
+ "mode": "affine"
533
+ },
534
+ "model.layers.28.self_attn.q_proj": {
535
+ "bits": 8,
536
+ "group_size": 64,
537
+ "mode": "affine"
538
+ },
539
+ "model.layers.27.self_attn.k_proj": {
540
+ "bits": 8,
541
+ "group_size": 64,
542
+ "mode": "affine"
543
+ },
544
+ "model.layers.48.self_attn.k_proj": {
545
+ "bits": 8,
546
+ "group_size": 64,
547
+ "mode": "affine"
548
+ },
549
+ "model.layers.46.self_attn.o_proj": {
550
+ "bits": 8,
551
+ "group_size": 64,
552
+ "mode": "affine"
553
+ },
554
+ "model.layers.57.self_attn.q_proj": {
555
+ "bits": 8,
556
+ "group_size": 64,
557
+ "mode": "affine"
558
+ },
559
+ "model.layers.27.self_attn.o_proj": {
560
+ "bits": 8,
561
+ "group_size": 64,
562
+ "mode": "affine"
563
+ },
564
+ "model.layers.38.self_attn.q_proj": {
565
+ "bits": 8,
566
+ "group_size": 64,
567
+ "mode": "affine"
568
+ },
569
+ "model.layers.49.self_attn.o_proj": {
570
+ "bits": 8,
571
+ "group_size": 64,
572
+ "mode": "affine"
573
+ },
574
+ "model.layers.26.self_attn.o_proj": {
575
+ "bits": 8,
576
+ "group_size": 64,
577
+ "mode": "affine"
578
+ },
579
+ "model.layers.26.self_attn.v_proj": {
580
+ "bits": 8,
581
+ "group_size": 64,
582
+ "mode": "affine"
583
+ },
584
+ "model.embed_tokens": {
585
+ "bits": 8,
586
+ "group_size": 64,
587
+ "mode": "affine"
588
+ },
589
+ "model.layers.13.self_attn.o_proj": {
590
+ "bits": 8,
591
+ "group_size": 64,
592
+ "mode": "affine"
593
+ },
594
+ "model.layers.40.self_attn.k_proj": {
595
+ "bits": 8,
596
+ "group_size": 64,
597
+ "mode": "affine"
598
+ },
599
+ "model.layers.49.self_attn.q_proj": {
600
+ "bits": 8,
601
+ "group_size": 64,
602
+ "mode": "affine"
603
+ },
604
+ "model.layers.38.self_attn.v_proj": {
605
+ "bits": 8,
606
+ "group_size": 64,
607
+ "mode": "affine"
608
+ },
609
+ "model.layers.20.self_attn.k_proj": {
610
+ "bits": 8,
611
+ "group_size": 64,
612
+ "mode": "affine"
613
+ },
614
+ "model.layers.45.self_attn.q_proj": {
615
+ "bits": 8,
616
+ "group_size": 64,
617
+ "mode": "affine"
618
+ },
619
+ "model.layers.1.self_attn.v_proj": {
620
+ "bits": 8,
621
+ "group_size": 64,
622
+ "mode": "affine"
623
+ },
624
+ "model.layers.18.self_attn.o_proj": {
625
+ "bits": 8,
626
+ "group_size": 64,
627
+ "mode": "affine"
628
+ },
629
+ "model.layers.27.self_attn.v_proj": {
630
+ "bits": 8,
631
+ "group_size": 64,
632
+ "mode": "affine"
633
+ },
634
+ "model.layers.57.self_attn.k_proj": {
635
+ "bits": 8,
636
+ "group_size": 64,
637
+ "mode": "affine"
638
+ },
639
+ "model.layers.51.self_attn.q_proj": {
640
+ "bits": 8,
641
+ "group_size": 64,
642
+ "mode": "affine"
643
+ },
644
+ "model.layers.54.self_attn.q_proj": {
645
+ "bits": 8,
646
+ "group_size": 64,
647
+ "mode": "affine"
648
+ },
649
+ "model.layers.10.self_attn.k_proj": {
650
+ "bits": 8,
651
+ "group_size": 64,
652
+ "mode": "affine"
653
+ },
654
+ "model.layers.34.self_attn.o_proj": {
655
+ "bits": 8,
656
+ "group_size": 64,
657
+ "mode": "affine"
658
+ },
659
+ "model.layers.16.self_attn.o_proj": {
660
+ "bits": 8,
661
+ "group_size": 64,
662
+ "mode": "affine"
663
+ },
664
+ "model.layers.52.self_attn.k_proj": {
665
+ "bits": 8,
666
+ "group_size": 64,
667
+ "mode": "affine"
668
+ },
669
+ "model.layers.58.self_attn.k_proj": {
670
+ "bits": 8,
671
+ "group_size": 64,
672
+ "mode": "affine"
673
+ },
674
+ "model.layers.36.self_attn.o_proj": {
675
+ "bits": 8,
676
+ "group_size": 64,
677
+ "mode": "affine"
678
+ },
679
+ "model.layers.17.self_attn.k_proj": {
680
+ "bits": 8,
681
+ "group_size": 64,
682
+ "mode": "affine"
683
+ },
684
+ "model.layers.6.self_attn.q_proj": {
685
+ "bits": 8,
686
+ "group_size": 64,
687
+ "mode": "affine"
688
+ },
689
+ "model.layers.36.self_attn.k_proj": {
690
+ "bits": 8,
691
+ "group_size": 64,
692
+ "mode": "affine"
693
+ },
694
+ "model.layers.26.self_attn.k_proj": {
695
+ "bits": 8,
696
+ "group_size": 64,
697
+ "mode": "affine"
698
+ },
699
+ "model.layers.26.self_attn.q_proj": {
700
+ "bits": 8,
701
+ "group_size": 64,
702
+ "mode": "affine"
703
+ },
704
+ "model.layers.11.self_attn.v_proj": {
705
+ "bits": 8,
706
+ "group_size": 64,
707
+ "mode": "affine"
708
+ },
709
+ "model.layers.24.self_attn.o_proj": {
710
+ "bits": 8,
711
+ "group_size": 64,
712
+ "mode": "affine"
713
+ },
714
+ "model.layers.33.self_attn.k_proj": {
715
+ "bits": 8,
716
+ "group_size": 64,
717
+ "mode": "affine"
718
+ },
719
+ "model.layers.19.self_attn.o_proj": {
720
+ "bits": 8,
721
+ "group_size": 64,
722
+ "mode": "affine"
723
+ },
724
+ "model.layers.20.self_attn.v_proj": {
725
+ "bits": 8,
726
+ "group_size": 64,
727
+ "mode": "affine"
728
+ },
729
+ "model.layers.7.self_attn.q_proj": {
730
+ "bits": 8,
731
+ "group_size": 64,
732
+ "mode": "affine"
733
+ },
734
+ "model.layers.61.self_attn.k_proj": {
735
+ "bits": 8,
736
+ "group_size": 64,
737
+ "mode": "affine"
738
+ },
739
+ "model.layers.13.self_attn.k_proj": {
740
+ "bits": 8,
741
+ "group_size": 64,
742
+ "mode": "affine"
743
+ },
744
+ "model.layers.59.self_attn.q_proj": {
745
+ "bits": 8,
746
+ "group_size": 64,
747
+ "mode": "affine"
748
+ },
749
+ "model.layers.8.self_attn.q_proj": {
750
+ "bits": 8,
751
+ "group_size": 64,
752
+ "mode": "affine"
753
+ },
754
+ "model.layers.42.self_attn.k_proj": {
755
+ "bits": 8,
756
+ "group_size": 64,
757
+ "mode": "affine"
758
+ },
759
+ "model.layers.0.self_attn.k_proj": {
760
+ "bits": 8,
761
+ "group_size": 64,
762
+ "mode": "affine"
763
+ },
764
+ "model.layers.14.self_attn.o_proj": {
765
+ "bits": 8,
766
+ "group_size": 64,
767
+ "mode": "affine"
768
+ },
769
+ "model.layers.39.self_attn.v_proj": {
770
+ "bits": 8,
771
+ "group_size": 64,
772
+ "mode": "affine"
773
+ },
774
+ "model.layers.51.self_attn.o_proj": {
775
+ "bits": 8,
776
+ "group_size": 64,
777
+ "mode": "affine"
778
+ },
779
+ "model.layers.18.self_attn.k_proj": {
780
+ "bits": 8,
781
+ "group_size": 64,
782
+ "mode": "affine"
783
+ },
784
+ "model.layers.59.self_attn.k_proj": {
785
+ "bits": 8,
786
+ "group_size": 64,
787
+ "mode": "affine"
788
+ },
789
+ "model.layers.2.self_attn.k_proj": {
790
+ "bits": 8,
791
+ "group_size": 64,
792
+ "mode": "affine"
793
+ },
794
+ "model.layers.34.self_attn.q_proj": {
795
+ "bits": 8,
796
+ "group_size": 64,
797
+ "mode": "affine"
798
+ },
799
+ "model.layers.44.self_attn.k_proj": {
800
+ "bits": 8,
801
+ "group_size": 64,
802
+ "mode": "affine"
803
+ },
804
+ "model.layers.56.self_attn.q_proj": {
805
+ "bits": 8,
806
+ "group_size": 64,
807
+ "mode": "affine"
808
+ },
809
+ "model.layers.13.self_attn.q_proj": {
810
+ "bits": 8,
811
+ "group_size": 64,
812
+ "mode": "affine"
813
+ },
814
+ "model.layers.31.self_attn.k_proj": {
815
+ "bits": 8,
816
+ "group_size": 64,
817
+ "mode": "affine"
818
+ },
819
+ "model.layers.41.self_attn.o_proj": {
820
+ "bits": 8,
821
+ "group_size": 64,
822
+ "mode": "affine"
823
+ },
824
+ "model.layers.48.self_attn.o_proj": {
825
+ "bits": 8,
826
+ "group_size": 64,
827
+ "mode": "affine"
828
+ },
829
+ "model.layers.15.self_attn.v_proj": {
830
+ "bits": 8,
831
+ "group_size": 64,
832
+ "mode": "affine"
833
+ },
834
+ "model.layers.58.self_attn.q_proj": {
835
+ "bits": 8,
836
+ "group_size": 64,
837
+ "mode": "affine"
838
+ },
839
+ "model.layers.47.self_attn.o_proj": {
840
+ "bits": 8,
841
+ "group_size": 64,
842
+ "mode": "affine"
843
+ },
844
+ "model.layers.35.self_attn.q_proj": {
845
+ "bits": 8,
846
+ "group_size": 64,
847
+ "mode": "affine"
848
+ },
849
+ "model.layers.25.self_attn.k_proj": {
850
+ "bits": 8,
851
+ "group_size": 64,
852
+ "mode": "affine"
853
+ },
854
+ "lm_head": {
855
+ "bits": 8,
856
+ "group_size": 64,
857
+ "mode": "affine"
858
+ },
859
+ "model.layers.0.self_attn.q_proj": {
860
+ "bits": 8,
861
+ "group_size": 64,
862
+ "mode": "affine"
863
+ },
864
+ "model.layers.3.self_attn.k_proj": {
865
+ "bits": 8,
866
+ "group_size": 64,
867
+ "mode": "affine"
868
+ },
869
+ "model.layers.16.self_attn.k_proj": {
870
+ "bits": 8,
871
+ "group_size": 64,
872
+ "mode": "affine"
873
+ },
874
+ "model.layers.17.self_attn.q_proj": {
875
+ "bits": 8,
876
+ "group_size": 64,
877
+ "mode": "affine"
878
+ },
879
+ "model.layers.27.self_attn.q_proj": {
880
+ "bits": 8,
881
+ "group_size": 64,
882
+ "mode": "affine"
883
+ },
884
+ "model.layers.21.self_attn.q_proj": {
885
+ "bits": 8,
886
+ "group_size": 64,
887
+ "mode": "affine"
888
+ },
889
+ "model.layers.7.self_attn.v_proj": {
890
+ "bits": 8,
891
+ "group_size": 64,
892
+ "mode": "affine"
893
+ },
894
+ "model.layers.59.self_attn.o_proj": {
895
+ "bits": 8,
896
+ "group_size": 64,
897
+ "mode": "affine"
898
+ },
899
+ "model.layers.25.self_attn.q_proj": {
900
+ "bits": 8,
901
+ "group_size": 64,
902
+ "mode": "affine"
903
+ },
904
+ "model.layers.57.self_attn.v_proj": {
905
+ "bits": 8,
906
+ "group_size": 64,
907
+ "mode": "affine"
908
+ },
909
+ "model.layers.19.self_attn.k_proj": {
910
+ "bits": 8,
911
+ "group_size": 64,
912
+ "mode": "affine"
913
+ },
914
+ "model.layers.44.self_attn.v_proj": {
915
+ "bits": 8,
916
+ "group_size": 64,
917
+ "mode": "affine"
918
+ },
919
+ "model.layers.42.self_attn.q_proj": {
920
+ "bits": 8,
921
+ "group_size": 64,
922
+ "mode": "affine"
923
+ },
924
+ "model.layers.10.self_attn.v_proj": {
925
+ "bits": 8,
926
+ "group_size": 64,
927
+ "mode": "affine"
928
+ },
929
+ "model.layers.60.self_attn.q_proj": {
930
+ "bits": 8,
931
+ "group_size": 64,
932
+ "mode": "affine"
933
+ },
934
+ "model.layers.41.self_attn.k_proj": {
935
+ "bits": 8,
936
+ "group_size": 64,
937
+ "mode": "affine"
938
+ },
939
+ "model.layers.32.self_attn.k_proj": {
940
+ "bits": 8,
941
+ "group_size": 64,
942
+ "mode": "affine"
943
+ },
944
+ "model.layers.5.self_attn.q_proj": {
945
+ "bits": 8,
946
+ "group_size": 64,
947
+ "mode": "affine"
948
+ },
949
+ "model.layers.35.self_attn.v_proj": {
950
+ "bits": 8,
951
+ "group_size": 64,
952
+ "mode": "affine"
953
+ },
954
+ "model.layers.35.self_attn.o_proj": {
955
+ "bits": 8,
956
+ "group_size": 64,
957
+ "mode": "affine"
958
+ },
959
+ "model.layers.19.self_attn.v_proj": {
960
+ "bits": 8,
961
+ "group_size": 64,
962
+ "mode": "affine"
963
+ },
964
+ "model.layers.15.self_attn.k_proj": {
965
+ "bits": 8,
966
+ "group_size": 64,
967
+ "mode": "affine"
968
+ },
969
+ "model.layers.1.self_attn.o_proj": {
970
+ "bits": 8,
971
+ "group_size": 64,
972
+ "mode": "affine"
973
+ },
974
+ "model.layers.9.self_attn.k_proj": {
975
+ "bits": 8,
976
+ "group_size": 64,
977
+ "mode": "affine"
978
+ },
979
+ "model.layers.50.self_attn.v_proj": {
980
+ "bits": 8,
981
+ "group_size": 64,
982
+ "mode": "affine"
983
+ },
984
+ "model.layers.6.self_attn.o_proj": {
985
+ "bits": 8,
986
+ "group_size": 64,
987
+ "mode": "affine"
988
+ },
989
+ "model.layers.47.self_attn.q_proj": {
990
+ "bits": 8,
991
+ "group_size": 64,
992
+ "mode": "affine"
993
+ },
994
+ "model.layers.46.self_attn.v_proj": {
995
+ "bits": 8,
996
+ "group_size": 64,
997
+ "mode": "affine"
998
+ },
999
+ "model.layers.16.self_attn.v_proj": {
1000
+ "bits": 8,
1001
+ "group_size": 64,
1002
+ "mode": "affine"
1003
+ },
1004
+ "model.layers.47.self_attn.v_proj": {
1005
+ "bits": 8,
1006
+ "group_size": 64,
1007
+ "mode": "affine"
1008
+ },
1009
+ "model.layers.30.self_attn.q_proj": {
1010
+ "bits": 8,
1011
+ "group_size": 64,
1012
+ "mode": "affine"
1013
+ },
1014
+ "model.layers.37.self_attn.q_proj": {
1015
+ "bits": 8,
1016
+ "group_size": 64,
1017
+ "mode": "affine"
1018
+ },
1019
+ "model.layers.17.self_attn.v_proj": {
1020
+ "bits": 8,
1021
+ "group_size": 64,
1022
+ "mode": "affine"
1023
+ },
1024
+ "model.layers.53.self_attn.o_proj": {
1025
+ "bits": 8,
1026
+ "group_size": 64,
1027
+ "mode": "affine"
1028
+ },
1029
+ "model.layers.52.self_attn.q_proj": {
1030
+ "bits": 8,
1031
+ "group_size": 64,
1032
+ "mode": "affine"
1033
+ },
1034
+ "model.layers.11.self_attn.q_proj": {
1035
+ "bits": 8,
1036
+ "group_size": 64,
1037
+ "mode": "affine"
1038
+ },
1039
+ "model.layers.61.self_attn.q_proj": {
1040
+ "bits": 8,
1041
+ "group_size": 64,
1042
+ "mode": "affine"
1043
+ },
1044
+ "model.layers.21.self_attn.v_proj": {
1045
+ "bits": 8,
1046
+ "group_size": 64,
1047
+ "mode": "affine"
1048
+ },
1049
+ "model.layers.54.self_attn.v_proj": {
1050
+ "bits": 8,
1051
+ "group_size": 64,
1052
+ "mode": "affine"
1053
+ },
1054
+ "model.layers.45.self_attn.o_proj": {
1055
+ "bits": 8,
1056
+ "group_size": 64,
1057
+ "mode": "affine"
1058
+ },
1059
+ "model.layers.18.self_attn.q_proj": {
1060
+ "bits": 8,
1061
+ "group_size": 64,
1062
+ "mode": "affine"
1063
+ },
1064
+ "model.layers.36.self_attn.q_proj": {
1065
+ "bits": 8,
1066
+ "group_size": 64,
1067
+ "mode": "affine"
1068
+ },
1069
+ "model.layers.4.self_attn.k_proj": {
1070
+ "bits": 8,
1071
+ "group_size": 64,
1072
+ "mode": "affine"
1073
+ },
1074
+ "model.layers.1.self_attn.q_proj": {
1075
+ "bits": 8,
1076
+ "group_size": 64,
1077
+ "mode": "affine"
1078
+ },
1079
+ "model.layers.40.self_attn.q_proj": {
1080
+ "bits": 8,
1081
+ "group_size": 64,
1082
+ "mode": "affine"
1083
+ },
1084
+ "model.layers.41.self_attn.v_proj": {
1085
+ "bits": 8,
1086
+ "group_size": 64,
1087
+ "mode": "affine"
1088
+ },
1089
+ "model.layers.8.self_attn.o_proj": {
1090
+ "bits": 8,
1091
+ "group_size": 64,
1092
+ "mode": "affine"
1093
+ },
1094
+ "model.layers.48.self_attn.v_proj": {
1095
+ "bits": 8,
1096
+ "group_size": 64,
1097
+ "mode": "affine"
1098
+ },
1099
+ "model.layers.41.self_attn.q_proj": {
1100
+ "bits": 8,
1101
+ "group_size": 64,
1102
+ "mode": "affine"
1103
+ },
1104
+ "model.layers.20.self_attn.o_proj": {
1105
+ "bits": 8,
1106
+ "group_size": 64,
1107
+ "mode": "affine"
1108
+ },
1109
+ "model.layers.55.self_attn.v_proj": {
1110
+ "bits": 8,
1111
+ "group_size": 64,
1112
+ "mode": "affine"
1113
+ },
1114
+ "model.layers.58.self_attn.o_proj": {
1115
+ "bits": 8,
1116
+ "group_size": 64,
1117
+ "mode": "affine"
1118
+ },
1119
+ "model.layers.35.self_attn.k_proj": {
1120
+ "bits": 8,
1121
+ "group_size": 64,
1122
+ "mode": "affine"
1123
+ },
1124
+ "model.layers.6.self_attn.k_proj": {
1125
+ "bits": 8,
1126
+ "group_size": 64,
1127
+ "mode": "affine"
1128
+ },
1129
+ "model.layers.17.self_attn.o_proj": {
1130
+ "bits": 8,
1131
+ "group_size": 64,
1132
+ "mode": "affine"
1133
+ },
1134
+ "model.layers.55.self_attn.k_proj": {
1135
+ "bits": 8,
1136
+ "group_size": 64,
1137
+ "mode": "affine"
1138
+ },
1139
+ "model.layers.7.self_attn.o_proj": {
1140
+ "bits": 8,
1141
+ "group_size": 64,
1142
+ "mode": "affine"
1143
+ },
1144
+ "model.layers.39.self_attn.k_proj": {
1145
+ "bits": 8,
1146
+ "group_size": 64,
1147
+ "mode": "affine"
1148
+ },
1149
+ "model.layers.6.self_attn.v_proj": {
1150
+ "bits": 8,
1151
+ "group_size": 64,
1152
+ "mode": "affine"
1153
+ },
1154
+ "model.layers.29.self_attn.k_proj": {
1155
+ "bits": 8,
1156
+ "group_size": 64,
1157
+ "mode": "affine"
1158
+ },
1159
+ "model.layers.28.self_attn.o_proj": {
1160
+ "bits": 8,
1161
+ "group_size": 64,
1162
+ "mode": "affine"
1163
+ },
1164
+ "model.layers.13.self_attn.v_proj": {
1165
+ "bits": 8,
1166
+ "group_size": 64,
1167
+ "mode": "affine"
1168
+ },
1169
+ "model.layers.4.self_attn.v_proj": {
1170
+ "bits": 8,
1171
+ "group_size": 64,
1172
+ "mode": "affine"
1173
+ },
1174
+ "model.layers.31.self_attn.o_proj": {
1175
+ "bits": 8,
1176
+ "group_size": 64,
1177
+ "mode": "affine"
1178
+ },
1179
+ "model.layers.44.self_attn.o_proj": {
1180
+ "bits": 8,
1181
+ "group_size": 64,
1182
+ "mode": "affine"
1183
+ },
1184
+ "model.layers.43.self_attn.k_proj": {
1185
+ "bits": 8,
1186
+ "group_size": 64,
1187
+ "mode": "affine"
1188
+ },
1189
+ "model.layers.32.self_attn.q_proj": {
1190
+ "bits": 8,
1191
+ "group_size": 64,
1192
+ "mode": "affine"
1193
+ },
1194
+ "model.layers.43.self_attn.o_proj": {
1195
+ "bits": 8,
1196
+ "group_size": 64,
1197
+ "mode": "affine"
1198
+ },
1199
+ "model.layers.43.self_attn.v_proj": {
1200
+ "bits": 8,
1201
+ "group_size": 64,
1202
+ "mode": "affine"
1203
+ },
1204
+ "model.layers.15.self_attn.o_proj": {
1205
+ "bits": 8,
1206
+ "group_size": 64,
1207
+ "mode": "affine"
1208
+ },
1209
+ "model.layers.44.self_attn.q_proj": {
1210
+ "bits": 8,
1211
+ "group_size": 64,
1212
+ "mode": "affine"
1213
+ },
1214
+ "model.layers.33.self_attn.q_proj": {
1215
+ "bits": 8,
1216
+ "group_size": 64,
1217
+ "mode": "affine"
1218
+ },
1219
+ "model.layers.21.self_attn.k_proj": {
1220
+ "bits": 8,
1221
+ "group_size": 64,
1222
+ "mode": "affine"
1223
+ },
1224
+ "model.layers.32.self_attn.v_proj": {
1225
+ "bits": 8,
1226
+ "group_size": 64,
1227
+ "mode": "affine"
1228
+ },
1229
+ "model.layers.42.self_attn.o_proj": {
1230
+ "bits": 8,
1231
+ "group_size": 64,
1232
+ "mode": "affine"
1233
+ },
1234
+ "model.layers.49.self_attn.v_proj": {
1235
+ "bits": 8,
1236
+ "group_size": 64,
1237
+ "mode": "affine"
1238
+ },
1239
+ "model.layers.12.self_attn.o_proj": {
1240
+ "bits": 8,
1241
+ "group_size": 64,
1242
+ "mode": "affine"
1243
+ },
1244
+ "model.layers.38.self_attn.o_proj": {
1245
+ "bits": 8,
1246
+ "group_size": 64,
1247
+ "mode": "affine"
1248
+ },
1249
+ "model.layers.48.self_attn.q_proj": {
1250
+ "bits": 8,
1251
+ "group_size": 64,
1252
+ "mode": "affine"
1253
+ },
1254
+ "model.layers.5.self_attn.o_proj": {
1255
+ "bits": 8,
1256
+ "group_size": 64,
1257
+ "mode": "affine"
1258
+ },
1259
+ "model.layers.21.self_attn.o_proj": {
1260
+ "bits": 8,
1261
+ "group_size": 64,
1262
+ "mode": "affine"
1263
+ },
1264
+ "model.layers.57.self_attn.o_proj": {
1265
+ "bits": 8,
1266
+ "group_size": 64,
1267
+ "mode": "affine"
1268
+ },
1269
+ "model.layers.56.self_attn.k_proj": {
1270
+ "bits": 8,
1271
+ "group_size": 64,
1272
+ "mode": "affine"
1273
+ },
1274
+ "model.layers.9.self_attn.q_proj": {
1275
+ "bits": 8,
1276
+ "group_size": 64,
1277
+ "mode": "affine"
1278
+ },
1279
+ "model.layers.58.self_attn.v_proj": {
1280
+ "bits": 8,
1281
+ "group_size": 64,
1282
+ "mode": "affine"
1283
+ },
1284
+ "model.layers.29.self_attn.o_proj": {
1285
+ "bits": 8,
1286
+ "group_size": 64,
1287
+ "mode": "affine"
1288
+ },
1289
+ "model.layers.23.self_attn.k_proj": {
1290
+ "bits": 8,
1291
+ "group_size": 64,
1292
+ "mode": "affine"
1293
+ },
1294
+ "model.layers.37.self_attn.v_proj": {
1295
+ "bits": 8,
1296
+ "group_size": 64,
1297
+ "mode": "affine"
1298
+ },
1299
+ "model.layers.30.self_attn.v_proj": {
1300
+ "bits": 8,
1301
+ "group_size": 64,
1302
+ "mode": "affine"
1303
+ },
1304
+ "model.layers.5.self_attn.k_proj": {
1305
+ "bits": 8,
1306
+ "group_size": 64,
1307
+ "mode": "affine"
1308
+ },
1309
+ "model.layers.14.self_attn.v_proj": {
1310
+ "bits": 8,
1311
+ "group_size": 64,
1312
+ "mode": "affine"
1313
+ },
1314
+ "model.layers.7.self_attn.k_proj": {
1315
+ "bits": 8,
1316
+ "group_size": 64,
1317
+ "mode": "affine"
1318
+ },
1319
+ "model.layers.2.self_attn.v_proj": {
1320
+ "bits": 8,
1321
+ "group_size": 64,
1322
+ "mode": "affine"
1323
+ },
1324
+ "model.layers.2.self_attn.q_proj": {
1325
+ "bits": 8,
1326
+ "group_size": 64,
1327
+ "mode": "affine"
1328
+ },
1329
+ "model.layers.46.self_attn.q_proj": {
1330
+ "bits": 8,
1331
+ "group_size": 64,
1332
+ "mode": "affine"
1333
+ },
1334
+ "model.layers.31.self_attn.q_proj": {
1335
+ "bits": 8,
1336
+ "group_size": 64,
1337
+ "mode": "affine"
1338
+ },
1339
+ "model.layers.61.self_attn.o_proj": {
1340
+ "bits": 8,
1341
+ "group_size": 64,
1342
+ "mode": "affine"
1343
+ },
1344
+ "model.layers.4.self_attn.q_proj": {
1345
+ "bits": 8,
1346
+ "group_size": 64,
1347
+ "mode": "affine"
1348
+ },
1349
+ "model.layers.43.self_attn.q_proj": {
1350
+ "bits": 8,
1351
+ "group_size": 64,
1352
+ "mode": "affine"
1353
+ }
1354
  },
1355
  "weight_format": "mxtq",
1356
+ "mxtq_bits": 4,
1357
+ "rope_parameters": {
1358
+ "rope_type": "default",
1359
+ "rope_theta": 5000000.0
1360
+ }
1361
  }