Hugging Face's logo

BAAI
/
Emu3-Chat-hf

Image-Text-to-Text
Safetensors
English
emu3
vision
conversational
Model card Files Community
2

Update: convert weights again

#2
by RaushanTurganbay HF staff - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+414
-414
Files changed (3) hide show
  1. model-00007-of-00008.safetensors +2 -2
  2. model-00008-of-00008.safetensors +2 -2
  3. model.safetensors.index.json +410 -410
model-00007-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10a9680ffbd0b011e923553e1268a52a26b5d5dfc2d57ff08226ca64b15a181f
3
- size 4999930560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6624fed3f3931ccd1168d58190599c06048bdbd61d40f48bc99a4b9ba952cf12
3
+ size 4999932864
model-00008-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4c65f1cf90ec40ccb777d60c888455671b50afd375e08539235671645488da4
3
- size 450196868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:332c5b0d8c78f7b1d963adbd1f2c64c684a5f47aee4e1a83ff65675b915d7c50
3
+ size 450198548
model.safetensors.index.json CHANGED
@@ -298,52 +298,52 @@
298
  "vqmodel.decoder.conv_in.weight": "model-00007-of-00008.safetensors",
299
  "vqmodel.decoder.conv_out.bias": "model-00008-of-00008.safetensors",
300
  "vqmodel.decoder.conv_out.weight": "model-00008-of-00008.safetensors",
301
- "vqmodel.decoder.mid.attn_1.k.bias": "model-00007-of-00008.safetensors",
302
- "vqmodel.decoder.mid.attn_1.k.weight": "model-00007-of-00008.safetensors",
303
- "vqmodel.decoder.mid.attn_1.norm.conv_b.bias": "model-00007-of-00008.safetensors",
304
- "vqmodel.decoder.mid.attn_1.norm.conv_b.weight": "model-00007-of-00008.safetensors",
305
- "vqmodel.decoder.mid.attn_1.norm.conv_y.bias": "model-00007-of-00008.safetensors",
306
- "vqmodel.decoder.mid.attn_1.norm.conv_y.weight": "model-00007-of-00008.safetensors",
307
- "vqmodel.decoder.mid.attn_1.norm.norm_layer.bias": "model-00007-of-00008.safetensors",
308
- "vqmodel.decoder.mid.attn_1.norm.norm_layer.weight": "model-00007-of-00008.safetensors",
309
- "vqmodel.decoder.mid.attn_1.proj_out.bias": "model-00007-of-00008.safetensors",
310
- "vqmodel.decoder.mid.attn_1.proj_out.weight": "model-00007-of-00008.safetensors",
311
- "vqmodel.decoder.mid.attn_1.q.bias": "model-00007-of-00008.safetensors",
312
- "vqmodel.decoder.mid.attn_1.q.weight": "model-00007-of-00008.safetensors",
313
- "vqmodel.decoder.mid.attn_1.v.bias": "model-00007-of-00008.safetensors",
314
- "vqmodel.decoder.mid.attn_1.v.weight": "model-00007-of-00008.safetensors",
315
- "vqmodel.decoder.mid.block_1.conv1.bias": "model-00007-of-00008.safetensors",
316
- "vqmodel.decoder.mid.block_1.conv1.weight": "model-00007-of-00008.safetensors",
317
- "vqmodel.decoder.mid.block_1.conv2.bias": "model-00007-of-00008.safetensors",
318
- "vqmodel.decoder.mid.block_1.conv2.weight": "model-00007-of-00008.safetensors",
319
- "vqmodel.decoder.mid.block_1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
320
- "vqmodel.decoder.mid.block_1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
321
- "vqmodel.decoder.mid.block_1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
322
- "vqmodel.decoder.mid.block_1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
323
- "vqmodel.decoder.mid.block_1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
324
- "vqmodel.decoder.mid.block_1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
325
- "vqmodel.decoder.mid.block_1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
326
- "vqmodel.decoder.mid.block_1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
327
- "vqmodel.decoder.mid.block_1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
328
- "vqmodel.decoder.mid.block_1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
329
- "vqmodel.decoder.mid.block_1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
330
- "vqmodel.decoder.mid.block_1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
331
- "vqmodel.decoder.mid.block_2.conv1.bias": "model-00007-of-00008.safetensors",
332
- "vqmodel.decoder.mid.block_2.conv1.weight": "model-00007-of-00008.safetensors",
333
- "vqmodel.decoder.mid.block_2.conv2.bias": "model-00007-of-00008.safetensors",
334
- "vqmodel.decoder.mid.block_2.conv2.weight": "model-00007-of-00008.safetensors",
335
- "vqmodel.decoder.mid.block_2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
336
- "vqmodel.decoder.mid.block_2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
337
- "vqmodel.decoder.mid.block_2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
338
- "vqmodel.decoder.mid.block_2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
339
- "vqmodel.decoder.mid.block_2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
340
- "vqmodel.decoder.mid.block_2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
341
- "vqmodel.decoder.mid.block_2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
342
- "vqmodel.decoder.mid.block_2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
343
- "vqmodel.decoder.mid.block_2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
344
- "vqmodel.decoder.mid.block_2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
345
- "vqmodel.decoder.mid.block_2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
346
- "vqmodel.decoder.mid.block_2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
347
  "vqmodel.decoder.norm_out.conv_b.bias": "model-00008-of-00008.safetensors",
348
  "vqmodel.decoder.norm_out.conv_b.weight": "model-00008-of-00008.safetensors",
349
  "vqmodel.decoder.norm_out.conv_y.bias": "model-00008-of-00008.safetensors",
@@ -382,374 +382,374 @@
382
  "vqmodel.decoder.time_res_stack.1.norm2.running_mean": "model-00007-of-00008.safetensors",
383
  "vqmodel.decoder.time_res_stack.1.norm2.running_var": "model-00007-of-00008.safetensors",
384
  "vqmodel.decoder.time_res_stack.1.norm2.weight": "model-00007-of-00008.safetensors",
385
- "vqmodel.decoder.up.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
386
- "vqmodel.decoder.up.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
387
- "vqmodel.decoder.up.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
388
- "vqmodel.decoder.up.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
389
- "vqmodel.decoder.up.0.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
390
- "vqmodel.decoder.up.0.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
391
- "vqmodel.decoder.up.0.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
392
- "vqmodel.decoder.up.0.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
393
- "vqmodel.decoder.up.0.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
394
- "vqmodel.decoder.up.0.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
395
- "vqmodel.decoder.up.0.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
396
- "vqmodel.decoder.up.0.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
397
- "vqmodel.decoder.up.0.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
398
- "vqmodel.decoder.up.0.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
399
- "vqmodel.decoder.up.0.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
400
- "vqmodel.decoder.up.0.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
401
- "vqmodel.decoder.up.0.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
402
- "vqmodel.decoder.up.0.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
403
- "vqmodel.decoder.up.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
404
- "vqmodel.decoder.up.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
405
- "vqmodel.decoder.up.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
406
- "vqmodel.decoder.up.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
407
- "vqmodel.decoder.up.0.block.1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
408
- "vqmodel.decoder.up.0.block.1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
409
- "vqmodel.decoder.up.0.block.1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
410
- "vqmodel.decoder.up.0.block.1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
411
- "vqmodel.decoder.up.0.block.1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
412
- "vqmodel.decoder.up.0.block.1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
413
- "vqmodel.decoder.up.0.block.1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
414
- "vqmodel.decoder.up.0.block.1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
415
- "vqmodel.decoder.up.0.block.1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
416
- "vqmodel.decoder.up.0.block.1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
417
- "vqmodel.decoder.up.0.block.1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
418
- "vqmodel.decoder.up.0.block.1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
419
- "vqmodel.decoder.up.0.block.2.conv1.bias": "model-00007-of-00008.safetensors",
420
- "vqmodel.decoder.up.0.block.2.conv1.weight": "model-00007-of-00008.safetensors",
421
- "vqmodel.decoder.up.0.block.2.conv2.bias": "model-00007-of-00008.safetensors",
422
- "vqmodel.decoder.up.0.block.2.conv2.weight": "model-00007-of-00008.safetensors",
423
- "vqmodel.decoder.up.0.block.2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
424
- "vqmodel.decoder.up.0.block.2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
425
- "vqmodel.decoder.up.0.block.2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
426
- "vqmodel.decoder.up.0.block.2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
427
- "vqmodel.decoder.up.0.block.2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
428
- "vqmodel.decoder.up.0.block.2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
429
- "vqmodel.decoder.up.0.block.2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
430
- "vqmodel.decoder.up.0.block.2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
431
- "vqmodel.decoder.up.0.block.2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
432
- "vqmodel.decoder.up.0.block.2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
433
- "vqmodel.decoder.up.0.block.2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
434
- "vqmodel.decoder.up.0.block.2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
435
- "vqmodel.decoder.up.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
436
- "vqmodel.decoder.up.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
437
- "vqmodel.decoder.up.1.block.0.conv2.bias": "model-00008-of-00008.safetensors",
438
- "vqmodel.decoder.up.1.block.0.conv2.weight": "model-00008-of-00008.safetensors",
439
- "vqmodel.decoder.up.1.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
440
- "vqmodel.decoder.up.1.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
441
- "vqmodel.decoder.up.1.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
442
- "vqmodel.decoder.up.1.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
443
- "vqmodel.decoder.up.1.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
444
- "vqmodel.decoder.up.1.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
445
- "vqmodel.decoder.up.1.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
446
- "vqmodel.decoder.up.1.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
447
- "vqmodel.decoder.up.1.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
448
- "vqmodel.decoder.up.1.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
449
- "vqmodel.decoder.up.1.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
450
- "vqmodel.decoder.up.1.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
451
- "vqmodel.decoder.up.1.block.1.conv1.bias": "model-00008-of-00008.safetensors",
452
- "vqmodel.decoder.up.1.block.1.conv1.weight": "model-00008-of-00008.safetensors",
453
- "vqmodel.decoder.up.1.block.1.conv2.bias": "model-00008-of-00008.safetensors",
454
- "vqmodel.decoder.up.1.block.1.conv2.weight": "model-00008-of-00008.safetensors",
455
- "vqmodel.decoder.up.1.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
456
- "vqmodel.decoder.up.1.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
457
- "vqmodel.decoder.up.1.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
458
- "vqmodel.decoder.up.1.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
459
- "vqmodel.decoder.up.1.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
460
- "vqmodel.decoder.up.1.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
461
- "vqmodel.decoder.up.1.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
462
- "vqmodel.decoder.up.1.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
463
- "vqmodel.decoder.up.1.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
464
- "vqmodel.decoder.up.1.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
465
- "vqmodel.decoder.up.1.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
466
- "vqmodel.decoder.up.1.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
467
- "vqmodel.decoder.up.1.block.2.conv1.bias": "model-00008-of-00008.safetensors",
468
- "vqmodel.decoder.up.1.block.2.conv1.weight": "model-00008-of-00008.safetensors",
469
- "vqmodel.decoder.up.1.block.2.conv2.bias": "model-00008-of-00008.safetensors",
470
- "vqmodel.decoder.up.1.block.2.conv2.weight": "model-00008-of-00008.safetensors",
471
- "vqmodel.decoder.up.1.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
472
- "vqmodel.decoder.up.1.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
473
- "vqmodel.decoder.up.1.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
474
- "vqmodel.decoder.up.1.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
475
- "vqmodel.decoder.up.1.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
476
- "vqmodel.decoder.up.1.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
477
- "vqmodel.decoder.up.1.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
478
- "vqmodel.decoder.up.1.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
479
- "vqmodel.decoder.up.1.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
480
- "vqmodel.decoder.up.1.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
481
- "vqmodel.decoder.up.1.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
482
- "vqmodel.decoder.up.1.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
483
- "vqmodel.decoder.up.1.upsample.conv.bias": "model-00008-of-00008.safetensors",
484
- "vqmodel.decoder.up.1.upsample.conv.weight": "model-00008-of-00008.safetensors",
485
- "vqmodel.decoder.up.2.block.0.conv1.bias": "model-00008-of-00008.safetensors",
486
- "vqmodel.decoder.up.2.block.0.conv1.weight": "model-00008-of-00008.safetensors",
487
- "vqmodel.decoder.up.2.block.0.conv2.bias": "model-00008-of-00008.safetensors",
488
- "vqmodel.decoder.up.2.block.0.conv2.weight": "model-00008-of-00008.safetensors",
489
- "vqmodel.decoder.up.2.block.0.nin_shortcut.bias": "model-00008-of-00008.safetensors",
490
- "vqmodel.decoder.up.2.block.0.nin_shortcut.weight": "model-00008-of-00008.safetensors",
491
- "vqmodel.decoder.up.2.block.0.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
492
- "vqmodel.decoder.up.2.block.0.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
493
- "vqmodel.decoder.up.2.block.0.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
494
- "vqmodel.decoder.up.2.block.0.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
495
- "vqmodel.decoder.up.2.block.0.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
496
- "vqmodel.decoder.up.2.block.0.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
497
- "vqmodel.decoder.up.2.block.0.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
498
- "vqmodel.decoder.up.2.block.0.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
499
- "vqmodel.decoder.up.2.block.0.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
500
- "vqmodel.decoder.up.2.block.0.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
501
- "vqmodel.decoder.up.2.block.0.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
502
- "vqmodel.decoder.up.2.block.0.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
503
- "vqmodel.decoder.up.2.block.1.conv1.bias": "model-00008-of-00008.safetensors",
504
- "vqmodel.decoder.up.2.block.1.conv1.weight": "model-00008-of-00008.safetensors",
505
- "vqmodel.decoder.up.2.block.1.conv2.bias": "model-00008-of-00008.safetensors",
506
- "vqmodel.decoder.up.2.block.1.conv2.weight": "model-00008-of-00008.safetensors",
507
- "vqmodel.decoder.up.2.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
508
- "vqmodel.decoder.up.2.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
509
- "vqmodel.decoder.up.2.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
510
- "vqmodel.decoder.up.2.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
511
- "vqmodel.decoder.up.2.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
512
- "vqmodel.decoder.up.2.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
513
- "vqmodel.decoder.up.2.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
514
- "vqmodel.decoder.up.2.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
515
- "vqmodel.decoder.up.2.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
516
- "vqmodel.decoder.up.2.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
517
- "vqmodel.decoder.up.2.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
518
- "vqmodel.decoder.up.2.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
519
- "vqmodel.decoder.up.2.block.2.conv1.bias": "model-00008-of-00008.safetensors",
520
- "vqmodel.decoder.up.2.block.2.conv1.weight": "model-00008-of-00008.safetensors",
521
- "vqmodel.decoder.up.2.block.2.conv2.bias": "model-00008-of-00008.safetensors",
522
- "vqmodel.decoder.up.2.block.2.conv2.weight": "model-00008-of-00008.safetensors",
523
- "vqmodel.decoder.up.2.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
524
- "vqmodel.decoder.up.2.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
525
- "vqmodel.decoder.up.2.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
526
- "vqmodel.decoder.up.2.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
527
- "vqmodel.decoder.up.2.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
528
- "vqmodel.decoder.up.2.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
529
- "vqmodel.decoder.up.2.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
530
- "vqmodel.decoder.up.2.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
531
- "vqmodel.decoder.up.2.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
532
- "vqmodel.decoder.up.2.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
533
- "vqmodel.decoder.up.2.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
534
- "vqmodel.decoder.up.2.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
535
- "vqmodel.decoder.up.2.upsample.conv.bias": "model-00008-of-00008.safetensors",
536
- "vqmodel.decoder.up.2.upsample.conv.weight": "model-00008-of-00008.safetensors",
537
- "vqmodel.decoder.up.3.attn.0.k.bias": "model-00008-of-00008.safetensors",
538
- "vqmodel.decoder.up.3.attn.0.k.weight": "model-00008-of-00008.safetensors",
539
- "vqmodel.decoder.up.3.attn.0.norm.conv_b.bias": "model-00008-of-00008.safetensors",
540
- "vqmodel.decoder.up.3.attn.0.norm.conv_b.weight": "model-00008-of-00008.safetensors",
541
- "vqmodel.decoder.up.3.attn.0.norm.conv_y.bias": "model-00008-of-00008.safetensors",
542
- "vqmodel.decoder.up.3.attn.0.norm.conv_y.weight": "model-00008-of-00008.safetensors",
543
- "vqmodel.decoder.up.3.attn.0.norm.norm_layer.bias": "model-00008-of-00008.safetensors",
544
- "vqmodel.decoder.up.3.attn.0.norm.norm_layer.weight": "model-00008-of-00008.safetensors",
545
- "vqmodel.decoder.up.3.attn.0.proj_out.bias": "model-00008-of-00008.safetensors",
546
- "vqmodel.decoder.up.3.attn.0.proj_out.weight": "model-00008-of-00008.safetensors",
547
- "vqmodel.decoder.up.3.attn.0.q.bias": "model-00008-of-00008.safetensors",
548
- "vqmodel.decoder.up.3.attn.0.q.weight": "model-00008-of-00008.safetensors",
549
- "vqmodel.decoder.up.3.attn.0.v.bias": "model-00008-of-00008.safetensors",
550
- "vqmodel.decoder.up.3.attn.0.v.weight": "model-00008-of-00008.safetensors",
551
- "vqmodel.decoder.up.3.attn.1.k.bias": "model-00008-of-00008.safetensors",
552
- "vqmodel.decoder.up.3.attn.1.k.weight": "model-00008-of-00008.safetensors",
553
- "vqmodel.decoder.up.3.attn.1.norm.conv_b.bias": "model-00008-of-00008.safetensors",
554
- "vqmodel.decoder.up.3.attn.1.norm.conv_b.weight": "model-00008-of-00008.safetensors",
555
- "vqmodel.decoder.up.3.attn.1.norm.conv_y.bias": "model-00008-of-00008.safetensors",
556
- "vqmodel.decoder.up.3.attn.1.norm.conv_y.weight": "model-00008-of-00008.safetensors",
557
- "vqmodel.decoder.up.3.attn.1.norm.norm_layer.bias": "model-00008-of-00008.safetensors",
558
- "vqmodel.decoder.up.3.attn.1.norm.norm_layer.weight": "model-00008-of-00008.safetensors",
559
- "vqmodel.decoder.up.3.attn.1.proj_out.bias": "model-00008-of-00008.safetensors",
560
- "vqmodel.decoder.up.3.attn.1.proj_out.weight": "model-00008-of-00008.safetensors",
561
- "vqmodel.decoder.up.3.attn.1.q.bias": "model-00008-of-00008.safetensors",
562
- "vqmodel.decoder.up.3.attn.1.q.weight": "model-00008-of-00008.safetensors",
563
- "vqmodel.decoder.up.3.attn.1.v.bias": "model-00008-of-00008.safetensors",
564
- "vqmodel.decoder.up.3.attn.1.v.weight": "model-00008-of-00008.safetensors",
565
- "vqmodel.decoder.up.3.attn.2.k.bias": "model-00008-of-00008.safetensors",
566
- "vqmodel.decoder.up.3.attn.2.k.weight": "model-00008-of-00008.safetensors",
567
- "vqmodel.decoder.up.3.attn.2.norm.conv_b.bias": "model-00008-of-00008.safetensors",
568
- "vqmodel.decoder.up.3.attn.2.norm.conv_b.weight": "model-00008-of-00008.safetensors",
569
- "vqmodel.decoder.up.3.attn.2.norm.conv_y.bias": "model-00008-of-00008.safetensors",
570
- "vqmodel.decoder.up.3.attn.2.norm.conv_y.weight": "model-00008-of-00008.safetensors",
571
- "vqmodel.decoder.up.3.attn.2.norm.norm_layer.bias": "model-00008-of-00008.safetensors",
572
- "vqmodel.decoder.up.3.attn.2.norm.norm_layer.weight": "model-00008-of-00008.safetensors",
573
- "vqmodel.decoder.up.3.attn.2.proj_out.bias": "model-00008-of-00008.safetensors",
574
- "vqmodel.decoder.up.3.attn.2.proj_out.weight": "model-00008-of-00008.safetensors",
575
- "vqmodel.decoder.up.3.attn.2.q.bias": "model-00008-of-00008.safetensors",
576
- "vqmodel.decoder.up.3.attn.2.q.weight": "model-00008-of-00008.safetensors",
577
- "vqmodel.decoder.up.3.attn.2.v.bias": "model-00008-of-00008.safetensors",
578
- "vqmodel.decoder.up.3.attn.2.v.weight": "model-00008-of-00008.safetensors",
579
- "vqmodel.decoder.up.3.block.0.conv1.bias": "model-00008-of-00008.safetensors",
580
- "vqmodel.decoder.up.3.block.0.conv1.weight": "model-00008-of-00008.safetensors",
581
- "vqmodel.decoder.up.3.block.0.conv2.bias": "model-00008-of-00008.safetensors",
582
- "vqmodel.decoder.up.3.block.0.conv2.weight": "model-00008-of-00008.safetensors",
583
- "vqmodel.decoder.up.3.block.0.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
584
- "vqmodel.decoder.up.3.block.0.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
585
- "vqmodel.decoder.up.3.block.0.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
586
- "vqmodel.decoder.up.3.block.0.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
587
- "vqmodel.decoder.up.3.block.0.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
588
- "vqmodel.decoder.up.3.block.0.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
589
- "vqmodel.decoder.up.3.block.0.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
590
- "vqmodel.decoder.up.3.block.0.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
591
- "vqmodel.decoder.up.3.block.0.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
592
- "vqmodel.decoder.up.3.block.0.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
593
- "vqmodel.decoder.up.3.block.0.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
594
- "vqmodel.decoder.up.3.block.0.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
595
- "vqmodel.decoder.up.3.block.1.conv1.bias": "model-00008-of-00008.safetensors",
596
- "vqmodel.decoder.up.3.block.1.conv1.weight": "model-00008-of-00008.safetensors",
597
- "vqmodel.decoder.up.3.block.1.conv2.bias": "model-00008-of-00008.safetensors",
598
- "vqmodel.decoder.up.3.block.1.conv2.weight": "model-00008-of-00008.safetensors",
599
- "vqmodel.decoder.up.3.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
600
- "vqmodel.decoder.up.3.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
601
- "vqmodel.decoder.up.3.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
602
- "vqmodel.decoder.up.3.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
603
- "vqmodel.decoder.up.3.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
604
- "vqmodel.decoder.up.3.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
605
- "vqmodel.decoder.up.3.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
606
- "vqmodel.decoder.up.3.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
607
- "vqmodel.decoder.up.3.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
608
- "vqmodel.decoder.up.3.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
609
- "vqmodel.decoder.up.3.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
610
- "vqmodel.decoder.up.3.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
611
- "vqmodel.decoder.up.3.block.2.conv1.bias": "model-00008-of-00008.safetensors",
612
- "vqmodel.decoder.up.3.block.2.conv1.weight": "model-00008-of-00008.safetensors",
613
- "vqmodel.decoder.up.3.block.2.conv2.bias": "model-00008-of-00008.safetensors",
614
- "vqmodel.decoder.up.3.block.2.conv2.weight": "model-00008-of-00008.safetensors",
615
- "vqmodel.decoder.up.3.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
616
- "vqmodel.decoder.up.3.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
617
- "vqmodel.decoder.up.3.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
618
- "vqmodel.decoder.up.3.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
619
- "vqmodel.decoder.up.3.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
620
- "vqmodel.decoder.up.3.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
621
- "vqmodel.decoder.up.3.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
622
- "vqmodel.decoder.up.3.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
623
- "vqmodel.decoder.up.3.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
624
- "vqmodel.decoder.up.3.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
625
- "vqmodel.decoder.up.3.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
626
- "vqmodel.decoder.up.3.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
627
- "vqmodel.decoder.up.3.upsample.conv.bias": "model-00008-of-00008.safetensors",
628
- "vqmodel.decoder.up.3.upsample.conv.weight": "model-00008-of-00008.safetensors",
629
  "vqmodel.encoder.conv_in.bias": "model-00007-of-00008.safetensors",
630
  "vqmodel.encoder.conv_in.weight": "model-00007-of-00008.safetensors",
631
  "vqmodel.encoder.conv_out.bias": "model-00007-of-00008.safetensors",
632
  "vqmodel.encoder.conv_out.weight": "model-00007-of-00008.safetensors",
633
- "vqmodel.encoder.down.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
634
- "vqmodel.encoder.down.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
635
- "vqmodel.encoder.down.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
636
- "vqmodel.encoder.down.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
637
- "vqmodel.encoder.down.0.block.0.norm1.bias": "model-00007-of-00008.safetensors",
638
- "vqmodel.encoder.down.0.block.0.norm1.weight": "model-00007-of-00008.safetensors",
639
- "vqmodel.encoder.down.0.block.0.norm2.bias": "model-00007-of-00008.safetensors",
640
- "vqmodel.encoder.down.0.block.0.norm2.weight": "model-00007-of-00008.safetensors",
641
- "vqmodel.encoder.down.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
642
- "vqmodel.encoder.down.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
643
- "vqmodel.encoder.down.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
644
- "vqmodel.encoder.down.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
645
- "vqmodel.encoder.down.0.block.1.norm1.bias": "model-00007-of-00008.safetensors",
646
- "vqmodel.encoder.down.0.block.1.norm1.weight": "model-00007-of-00008.safetensors",
647
- "vqmodel.encoder.down.0.block.1.norm2.bias": "model-00007-of-00008.safetensors",
648
- "vqmodel.encoder.down.0.block.1.norm2.weight": "model-00007-of-00008.safetensors",
649
- "vqmodel.encoder.down.0.downsample.conv.bias": "model-00007-of-00008.safetensors",
650
- "vqmodel.encoder.down.0.downsample.conv.weight": "model-00007-of-00008.safetensors",
651
- "vqmodel.encoder.down.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
652
- "vqmodel.encoder.down.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
653
- "vqmodel.encoder.down.1.block.0.conv2.bias": "model-00007-of-00008.safetensors",
654
- "vqmodel.encoder.down.1.block.0.conv2.weight": "model-00007-of-00008.safetensors",
655
- "vqmodel.encoder.down.1.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
656
- "vqmodel.encoder.down.1.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
657
- "vqmodel.encoder.down.1.block.0.norm1.bias": "model-00007-of-00008.safetensors",
658
- "vqmodel.encoder.down.1.block.0.norm1.weight": "model-00007-of-00008.safetensors",
659
- "vqmodel.encoder.down.1.block.0.norm2.bias": "model-00007-of-00008.safetensors",
660
- "vqmodel.encoder.down.1.block.0.norm2.weight": "model-00007-of-00008.safetensors",
661
- "vqmodel.encoder.down.1.block.1.conv1.bias": "model-00007-of-00008.safetensors",
662
- "vqmodel.encoder.down.1.block.1.conv1.weight": "model-00007-of-00008.safetensors",
663
- "vqmodel.encoder.down.1.block.1.conv2.bias": "model-00007-of-00008.safetensors",
664
- "vqmodel.encoder.down.1.block.1.conv2.weight": "model-00007-of-00008.safetensors",
665
- "vqmodel.encoder.down.1.block.1.norm1.bias": "model-00007-of-00008.safetensors",
666
- "vqmodel.encoder.down.1.block.1.norm1.weight": "model-00007-of-00008.safetensors",
667
- "vqmodel.encoder.down.1.block.1.norm2.bias": "model-00007-of-00008.safetensors",
668
- "vqmodel.encoder.down.1.block.1.norm2.weight": "model-00007-of-00008.safetensors",
669
- "vqmodel.encoder.down.1.downsample.conv.bias": "model-00007-of-00008.safetensors",
670
- "vqmodel.encoder.down.1.downsample.conv.weight": "model-00007-of-00008.safetensors",
671
- "vqmodel.encoder.down.2.block.0.conv1.bias": "model-00007-of-00008.safetensors",
672
- "vqmodel.encoder.down.2.block.0.conv1.weight": "model-00007-of-00008.safetensors",
673
- "vqmodel.encoder.down.2.block.0.conv2.bias": "model-00007-of-00008.safetensors",
674
- "vqmodel.encoder.down.2.block.0.conv2.weight": "model-00007-of-00008.safetensors",
675
- "vqmodel.encoder.down.2.block.0.norm1.bias": "model-00007-of-00008.safetensors",
676
- "vqmodel.encoder.down.2.block.0.norm1.weight": "model-00007-of-00008.safetensors",
677
- "vqmodel.encoder.down.2.block.0.norm2.bias": "model-00007-of-00008.safetensors",
678
- "vqmodel.encoder.down.2.block.0.norm2.weight": "model-00007-of-00008.safetensors",
679
- "vqmodel.encoder.down.2.block.1.conv1.bias": "model-00007-of-00008.safetensors",
680
- "vqmodel.encoder.down.2.block.1.conv1.weight": "model-00007-of-00008.safetensors",
681
- "vqmodel.encoder.down.2.block.1.conv2.bias": "model-00007-of-00008.safetensors",
682
- "vqmodel.encoder.down.2.block.1.conv2.weight": "model-00007-of-00008.safetensors",
683
- "vqmodel.encoder.down.2.block.1.norm1.bias": "model-00007-of-00008.safetensors",
684
- "vqmodel.encoder.down.2.block.1.norm1.weight": "model-00007-of-00008.safetensors",
685
- "vqmodel.encoder.down.2.block.1.norm2.bias": "model-00007-of-00008.safetensors",
686
- "vqmodel.encoder.down.2.block.1.norm2.weight": "model-00007-of-00008.safetensors",
687
- "vqmodel.encoder.down.2.downsample.conv.bias": "model-00007-of-00008.safetensors",
688
- "vqmodel.encoder.down.2.downsample.conv.weight": "model-00007-of-00008.safetensors",
689
- "vqmodel.encoder.down.3.attn.0.k.bias": "model-00007-of-00008.safetensors",
690
- "vqmodel.encoder.down.3.attn.0.k.weight": "model-00007-of-00008.safetensors",
691
- "vqmodel.encoder.down.3.attn.0.norm.bias": "model-00007-of-00008.safetensors",
692
- "vqmodel.encoder.down.3.attn.0.norm.weight": "model-00007-of-00008.safetensors",
693
- "vqmodel.encoder.down.3.attn.0.proj_out.bias": "model-00007-of-00008.safetensors",
694
- "vqmodel.encoder.down.3.attn.0.proj_out.weight": "model-00007-of-00008.safetensors",
695
- "vqmodel.encoder.down.3.attn.0.q.bias": "model-00007-of-00008.safetensors",
696
- "vqmodel.encoder.down.3.attn.0.q.weight": "model-00007-of-00008.safetensors",
697
- "vqmodel.encoder.down.3.attn.0.v.bias": "model-00007-of-00008.safetensors",
698
- "vqmodel.encoder.down.3.attn.0.v.weight": "model-00007-of-00008.safetensors",
699
- "vqmodel.encoder.down.3.attn.1.k.bias": "model-00007-of-00008.safetensors",
700
- "vqmodel.encoder.down.3.attn.1.k.weight": "model-00007-of-00008.safetensors",
701
- "vqmodel.encoder.down.3.attn.1.norm.bias": "model-00007-of-00008.safetensors",
702
- "vqmodel.encoder.down.3.attn.1.norm.weight": "model-00007-of-00008.safetensors",
703
- "vqmodel.encoder.down.3.attn.1.proj_out.bias": "model-00007-of-00008.safetensors",
704
- "vqmodel.encoder.down.3.attn.1.proj_out.weight": "model-00007-of-00008.safetensors",
705
- "vqmodel.encoder.down.3.attn.1.q.bias": "model-00007-of-00008.safetensors",
706
- "vqmodel.encoder.down.3.attn.1.q.weight": "model-00007-of-00008.safetensors",
707
- "vqmodel.encoder.down.3.attn.1.v.bias": "model-00007-of-00008.safetensors",
708
- "vqmodel.encoder.down.3.attn.1.v.weight": "model-00007-of-00008.safetensors",
709
- "vqmodel.encoder.down.3.block.0.conv1.bias": "model-00007-of-00008.safetensors",
710
- "vqmodel.encoder.down.3.block.0.conv1.weight": "model-00007-of-00008.safetensors",
711
- "vqmodel.encoder.down.3.block.0.conv2.bias": "model-00007-of-00008.safetensors",
712
- "vqmodel.encoder.down.3.block.0.conv2.weight": "model-00007-of-00008.safetensors",
713
- "vqmodel.encoder.down.3.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
714
- "vqmodel.encoder.down.3.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
715
- "vqmodel.encoder.down.3.block.0.norm1.bias": "model-00007-of-00008.safetensors",
716
- "vqmodel.encoder.down.3.block.0.norm1.weight": "model-00007-of-00008.safetensors",
717
- "vqmodel.encoder.down.3.block.0.norm2.bias": "model-00007-of-00008.safetensors",
718
- "vqmodel.encoder.down.3.block.0.norm2.weight": "model-00007-of-00008.safetensors",
719
- "vqmodel.encoder.down.3.block.1.conv1.bias": "model-00007-of-00008.safetensors",
720
- "vqmodel.encoder.down.3.block.1.conv1.weight": "model-00007-of-00008.safetensors",
721
- "vqmodel.encoder.down.3.block.1.conv2.bias": "model-00007-of-00008.safetensors",
722
- "vqmodel.encoder.down.3.block.1.conv2.weight": "model-00007-of-00008.safetensors",
723
- "vqmodel.encoder.down.3.block.1.norm1.bias": "model-00007-of-00008.safetensors",
724
- "vqmodel.encoder.down.3.block.1.norm1.weight": "model-00007-of-00008.safetensors",
725
- "vqmodel.encoder.down.3.block.1.norm2.bias": "model-00007-of-00008.safetensors",
726
- "vqmodel.encoder.down.3.block.1.norm2.weight": "model-00007-of-00008.safetensors",
727
- "vqmodel.encoder.mid.attn_1.k.bias": "model-00007-of-00008.safetensors",
728
- "vqmodel.encoder.mid.attn_1.k.weight": "model-00007-of-00008.safetensors",
729
- "vqmodel.encoder.mid.attn_1.norm.bias": "model-00007-of-00008.safetensors",
730
- "vqmodel.encoder.mid.attn_1.norm.weight": "model-00007-of-00008.safetensors",
731
- "vqmodel.encoder.mid.attn_1.proj_out.bias": "model-00007-of-00008.safetensors",
732
- "vqmodel.encoder.mid.attn_1.proj_out.weight": "model-00007-of-00008.safetensors",
733
- "vqmodel.encoder.mid.attn_1.q.bias": "model-00007-of-00008.safetensors",
734
- "vqmodel.encoder.mid.attn_1.q.weight": "model-00007-of-00008.safetensors",
735
- "vqmodel.encoder.mid.attn_1.v.bias": "model-00007-of-00008.safetensors",
736
- "vqmodel.encoder.mid.attn_1.v.weight": "model-00007-of-00008.safetensors",
737
- "vqmodel.encoder.mid.block_1.conv1.bias": "model-00007-of-00008.safetensors",
738
- "vqmodel.encoder.mid.block_1.conv1.weight": "model-00007-of-00008.safetensors",
739
- "vqmodel.encoder.mid.block_1.conv2.bias": "model-00007-of-00008.safetensors",
740
- "vqmodel.encoder.mid.block_1.conv2.weight": "model-00007-of-00008.safetensors",
741
- "vqmodel.encoder.mid.block_1.norm1.bias": "model-00007-of-00008.safetensors",
742
- "vqmodel.encoder.mid.block_1.norm1.weight": "model-00007-of-00008.safetensors",
743
- "vqmodel.encoder.mid.block_1.norm2.bias": "model-00007-of-00008.safetensors",
744
- "vqmodel.encoder.mid.block_1.norm2.weight": "model-00007-of-00008.safetensors",
745
- "vqmodel.encoder.mid.block_2.conv1.bias": "model-00007-of-00008.safetensors",
746
- "vqmodel.encoder.mid.block_2.conv1.weight": "model-00007-of-00008.safetensors",
747
- "vqmodel.encoder.mid.block_2.conv2.bias": "model-00007-of-00008.safetensors",
748
- "vqmodel.encoder.mid.block_2.conv2.weight": "model-00007-of-00008.safetensors",
749
- "vqmodel.encoder.mid.block_2.norm1.bias": "model-00007-of-00008.safetensors",
750
- "vqmodel.encoder.mid.block_2.norm1.weight": "model-00007-of-00008.safetensors",
751
- "vqmodel.encoder.mid.block_2.norm2.bias": "model-00007-of-00008.safetensors",
752
- "vqmodel.encoder.mid.block_2.norm2.weight": "model-00007-of-00008.safetensors",
753
  "vqmodel.encoder.norm_out.bias": "model-00007-of-00008.safetensors",
754
  "vqmodel.encoder.norm_out.weight": "model-00007-of-00008.safetensors",
755
  "vqmodel.encoder.time_conv.0.conv.conv.bias": "model-00007-of-00008.safetensors",
 
298
  "vqmodel.decoder.conv_in.weight": "model-00007-of-00008.safetensors",
299
  "vqmodel.decoder.conv_out.bias": "model-00008-of-00008.safetensors",
300
  "vqmodel.decoder.conv_out.weight": "model-00008-of-00008.safetensors",
301
+ "vqmodel.decoder.middle_block.attn_1.k_proj.bias": "model-00007-of-00008.safetensors",
302
+ "vqmodel.decoder.middle_block.attn_1.k_proj.weight": "model-00007-of-00008.safetensors",
303
+ "vqmodel.decoder.middle_block.attn_1.out_proj.bias": "model-00007-of-00008.safetensors",
304
+ "vqmodel.decoder.middle_block.attn_1.out_proj.weight": "model-00007-of-00008.safetensors",
305
+ "vqmodel.decoder.middle_block.attn_1.q_proj.bias": "model-00007-of-00008.safetensors",
306
+ "vqmodel.decoder.middle_block.attn_1.q_proj.weight": "model-00007-of-00008.safetensors",
307
+ "vqmodel.decoder.middle_block.attn_1.v_proj.bias": "model-00007-of-00008.safetensors",
308
+ "vqmodel.decoder.middle_block.attn_1.v_proj.weight": "model-00007-of-00008.safetensors",
309
+ "vqmodel.decoder.middle_block.attn_norm.conv_b.bias": "model-00007-of-00008.safetensors",
310
+ "vqmodel.decoder.middle_block.attn_norm.conv_b.weight": "model-00007-of-00008.safetensors",
311
+ "vqmodel.decoder.middle_block.attn_norm.conv_y.bias": "model-00007-of-00008.safetensors",
312
+ "vqmodel.decoder.middle_block.attn_norm.conv_y.weight": "model-00007-of-00008.safetensors",
313
+ "vqmodel.decoder.middle_block.attn_norm.norm_layer.bias": "model-00007-of-00008.safetensors",
314
+ "vqmodel.decoder.middle_block.attn_norm.norm_layer.weight": "model-00007-of-00008.safetensors",
315
+ "vqmodel.decoder.middle_block.block_1.conv1.bias": "model-00007-of-00008.safetensors",
316
+ "vqmodel.decoder.middle_block.block_1.conv1.weight": "model-00007-of-00008.safetensors",
317
+ "vqmodel.decoder.middle_block.block_1.conv2.bias": "model-00007-of-00008.safetensors",
318
+ "vqmodel.decoder.middle_block.block_1.conv2.weight": "model-00007-of-00008.safetensors",
319
+ "vqmodel.decoder.middle_block.block_1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
320
+ "vqmodel.decoder.middle_block.block_1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
321
+ "vqmodel.decoder.middle_block.block_1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
322
+ "vqmodel.decoder.middle_block.block_1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
323
+ "vqmodel.decoder.middle_block.block_1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
324
+ "vqmodel.decoder.middle_block.block_1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
325
+ "vqmodel.decoder.middle_block.block_1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
326
+ "vqmodel.decoder.middle_block.block_1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
327
+ "vqmodel.decoder.middle_block.block_1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
328
+ "vqmodel.decoder.middle_block.block_1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
329
+ "vqmodel.decoder.middle_block.block_1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
330
+ "vqmodel.decoder.middle_block.block_1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
331
+ "vqmodel.decoder.middle_block.block_2.conv1.bias": "model-00007-of-00008.safetensors",
332
+ "vqmodel.decoder.middle_block.block_2.conv1.weight": "model-00007-of-00008.safetensors",
333
+ "vqmodel.decoder.middle_block.block_2.conv2.bias": "model-00007-of-00008.safetensors",
334
+ "vqmodel.decoder.middle_block.block_2.conv2.weight": "model-00007-of-00008.safetensors",
335
+ "vqmodel.decoder.middle_block.block_2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
336
+ "vqmodel.decoder.middle_block.block_2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
337
+ "vqmodel.decoder.middle_block.block_2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
338
+ "vqmodel.decoder.middle_block.block_2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
339
+ "vqmodel.decoder.middle_block.block_2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
340
+ "vqmodel.decoder.middle_block.block_2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
341
+ "vqmodel.decoder.middle_block.block_2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
342
+ "vqmodel.decoder.middle_block.block_2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
343
+ "vqmodel.decoder.middle_block.block_2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
344
+ "vqmodel.decoder.middle_block.block_2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
345
+ "vqmodel.decoder.middle_block.block_2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
346
+ "vqmodel.decoder.middle_block.block_2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
347
  "vqmodel.decoder.norm_out.conv_b.bias": "model-00008-of-00008.safetensors",
348
  "vqmodel.decoder.norm_out.conv_b.weight": "model-00008-of-00008.safetensors",
349
  "vqmodel.decoder.norm_out.conv_y.bias": "model-00008-of-00008.safetensors",
 
382
  "vqmodel.decoder.time_res_stack.1.norm2.running_mean": "model-00007-of-00008.safetensors",
383
  "vqmodel.decoder.time_res_stack.1.norm2.running_var": "model-00007-of-00008.safetensors",
384
  "vqmodel.decoder.time_res_stack.1.norm2.weight": "model-00007-of-00008.safetensors",
385
+ "vqmodel.decoder.up_block.up.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
386
+ "vqmodel.decoder.up_block.up.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
387
+ "vqmodel.decoder.up_block.up.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
388
+ "vqmodel.decoder.up_block.up.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
389
+ "vqmodel.decoder.up_block.up.0.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
390
+ "vqmodel.decoder.up_block.up.0.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
391
+ "vqmodel.decoder.up_block.up.0.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
392
+ "vqmodel.decoder.up_block.up.0.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
393
+ "vqmodel.decoder.up_block.up.0.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
394
+ "vqmodel.decoder.up_block.up.0.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
395
+ "vqmodel.decoder.up_block.up.0.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
396
+ "vqmodel.decoder.up_block.up.0.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
397
+ "vqmodel.decoder.up_block.up.0.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
398
+ "vqmodel.decoder.up_block.up.0.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
399
+ "vqmodel.decoder.up_block.up.0.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
400
+ "vqmodel.decoder.up_block.up.0.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
401
+ "vqmodel.decoder.up_block.up.0.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
402
+ "vqmodel.decoder.up_block.up.0.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
403
+ "vqmodel.decoder.up_block.up.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
404
+ "vqmodel.decoder.up_block.up.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
405
+ "vqmodel.decoder.up_block.up.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
406
+ "vqmodel.decoder.up_block.up.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
407
+ "vqmodel.decoder.up_block.up.0.block.1.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
408
+ "vqmodel.decoder.up_block.up.0.block.1.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
409
+ "vqmodel.decoder.up_block.up.0.block.1.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
410
+ "vqmodel.decoder.up_block.up.0.block.1.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
411
+ "vqmodel.decoder.up_block.up.0.block.1.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
412
+ "vqmodel.decoder.up_block.up.0.block.1.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
413
+ "vqmodel.decoder.up_block.up.0.block.1.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
414
+ "vqmodel.decoder.up_block.up.0.block.1.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
415
+ "vqmodel.decoder.up_block.up.0.block.1.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
416
+ "vqmodel.decoder.up_block.up.0.block.1.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
417
+ "vqmodel.decoder.up_block.up.0.block.1.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
418
+ "vqmodel.decoder.up_block.up.0.block.1.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
419
+ "vqmodel.decoder.up_block.up.0.block.2.conv1.bias": "model-00007-of-00008.safetensors",
420
+ "vqmodel.decoder.up_block.up.0.block.2.conv1.weight": "model-00007-of-00008.safetensors",
421
+ "vqmodel.decoder.up_block.up.0.block.2.conv2.bias": "model-00007-of-00008.safetensors",
422
+ "vqmodel.decoder.up_block.up.0.block.2.conv2.weight": "model-00007-of-00008.safetensors",
423
+ "vqmodel.decoder.up_block.up.0.block.2.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
424
+ "vqmodel.decoder.up_block.up.0.block.2.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
425
+ "vqmodel.decoder.up_block.up.0.block.2.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
426
+ "vqmodel.decoder.up_block.up.0.block.2.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
427
+ "vqmodel.decoder.up_block.up.0.block.2.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
428
+ "vqmodel.decoder.up_block.up.0.block.2.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
429
+ "vqmodel.decoder.up_block.up.0.block.2.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
430
+ "vqmodel.decoder.up_block.up.0.block.2.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
431
+ "vqmodel.decoder.up_block.up.0.block.2.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
432
+ "vqmodel.decoder.up_block.up.0.block.2.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
433
+ "vqmodel.decoder.up_block.up.0.block.2.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
434
+ "vqmodel.decoder.up_block.up.0.block.2.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
435
+ "vqmodel.decoder.up_block.up.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
436
+ "vqmodel.decoder.up_block.up.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
437
+ "vqmodel.decoder.up_block.up.1.block.0.conv2.bias": "model-00008-of-00008.safetensors",
438
+ "vqmodel.decoder.up_block.up.1.block.0.conv2.weight": "model-00008-of-00008.safetensors",
439
+ "vqmodel.decoder.up_block.up.1.block.0.norm1.conv_b.bias": "model-00007-of-00008.safetensors",
440
+ "vqmodel.decoder.up_block.up.1.block.0.norm1.conv_b.weight": "model-00007-of-00008.safetensors",
441
+ "vqmodel.decoder.up_block.up.1.block.0.norm1.conv_y.bias": "model-00007-of-00008.safetensors",
442
+ "vqmodel.decoder.up_block.up.1.block.0.norm1.conv_y.weight": "model-00007-of-00008.safetensors",
443
+ "vqmodel.decoder.up_block.up.1.block.0.norm1.norm_layer.bias": "model-00007-of-00008.safetensors",
444
+ "vqmodel.decoder.up_block.up.1.block.0.norm1.norm_layer.weight": "model-00007-of-00008.safetensors",
445
+ "vqmodel.decoder.up_block.up.1.block.0.norm2.conv_b.bias": "model-00007-of-00008.safetensors",
446
+ "vqmodel.decoder.up_block.up.1.block.0.norm2.conv_b.weight": "model-00007-of-00008.safetensors",
447
+ "vqmodel.decoder.up_block.up.1.block.0.norm2.conv_y.bias": "model-00007-of-00008.safetensors",
448
+ "vqmodel.decoder.up_block.up.1.block.0.norm2.conv_y.weight": "model-00007-of-00008.safetensors",
449
+ "vqmodel.decoder.up_block.up.1.block.0.norm2.norm_layer.bias": "model-00007-of-00008.safetensors",
450
+ "vqmodel.decoder.up_block.up.1.block.0.norm2.norm_layer.weight": "model-00007-of-00008.safetensors",
451
+ "vqmodel.decoder.up_block.up.1.block.1.conv1.bias": "model-00008-of-00008.safetensors",
452
+ "vqmodel.decoder.up_block.up.1.block.1.conv1.weight": "model-00008-of-00008.safetensors",
453
+ "vqmodel.decoder.up_block.up.1.block.1.conv2.bias": "model-00008-of-00008.safetensors",
454
+ "vqmodel.decoder.up_block.up.1.block.1.conv2.weight": "model-00008-of-00008.safetensors",
455
+ "vqmodel.decoder.up_block.up.1.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
456
+ "vqmodel.decoder.up_block.up.1.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
457
+ "vqmodel.decoder.up_block.up.1.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
458
+ "vqmodel.decoder.up_block.up.1.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
459
+ "vqmodel.decoder.up_block.up.1.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
460
+ "vqmodel.decoder.up_block.up.1.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
461
+ "vqmodel.decoder.up_block.up.1.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
462
+ "vqmodel.decoder.up_block.up.1.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
463
+ "vqmodel.decoder.up_block.up.1.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
464
+ "vqmodel.decoder.up_block.up.1.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
465
+ "vqmodel.decoder.up_block.up.1.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
466
+ "vqmodel.decoder.up_block.up.1.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
467
+ "vqmodel.decoder.up_block.up.1.block.2.conv1.bias": "model-00008-of-00008.safetensors",
468
+ "vqmodel.decoder.up_block.up.1.block.2.conv1.weight": "model-00008-of-00008.safetensors",
469
+ "vqmodel.decoder.up_block.up.1.block.2.conv2.bias": "model-00008-of-00008.safetensors",
470
+ "vqmodel.decoder.up_block.up.1.block.2.conv2.weight": "model-00008-of-00008.safetensors",
471
+ "vqmodel.decoder.up_block.up.1.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
472
+ "vqmodel.decoder.up_block.up.1.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
473
+ "vqmodel.decoder.up_block.up.1.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
474
+ "vqmodel.decoder.up_block.up.1.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
475
+ "vqmodel.decoder.up_block.up.1.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
476
+ "vqmodel.decoder.up_block.up.1.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
477
+ "vqmodel.decoder.up_block.up.1.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
478
+ "vqmodel.decoder.up_block.up.1.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
479
+ "vqmodel.decoder.up_block.up.1.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
480
+ "vqmodel.decoder.up_block.up.1.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
481
+ "vqmodel.decoder.up_block.up.1.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
482
+ "vqmodel.decoder.up_block.up.1.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
483
+ "vqmodel.decoder.up_block.up.1.upsample.conv.bias": "model-00008-of-00008.safetensors",
484
+ "vqmodel.decoder.up_block.up.1.upsample.conv.weight": "model-00008-of-00008.safetensors",
485
+ "vqmodel.decoder.up_block.up.2.block.0.conv1.bias": "model-00008-of-00008.safetensors",
486
+ "vqmodel.decoder.up_block.up.2.block.0.conv1.weight": "model-00008-of-00008.safetensors",
487
+ "vqmodel.decoder.up_block.up.2.block.0.conv2.bias": "model-00008-of-00008.safetensors",
488
+ "vqmodel.decoder.up_block.up.2.block.0.conv2.weight": "model-00008-of-00008.safetensors",
489
+ "vqmodel.decoder.up_block.up.2.block.0.nin_shortcut.bias": "model-00008-of-00008.safetensors",
490
+ "vqmodel.decoder.up_block.up.2.block.0.nin_shortcut.weight": "model-00008-of-00008.safetensors",
491
+ "vqmodel.decoder.up_block.up.2.block.0.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
492
+ "vqmodel.decoder.up_block.up.2.block.0.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
493
+ "vqmodel.decoder.up_block.up.2.block.0.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
494
+ "vqmodel.decoder.up_block.up.2.block.0.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
495
+ "vqmodel.decoder.up_block.up.2.block.0.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
496
+ "vqmodel.decoder.up_block.up.2.block.0.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
497
+ "vqmodel.decoder.up_block.up.2.block.0.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
498
+ "vqmodel.decoder.up_block.up.2.block.0.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
499
+ "vqmodel.decoder.up_block.up.2.block.0.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
500
+ "vqmodel.decoder.up_block.up.2.block.0.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
501
+ "vqmodel.decoder.up_block.up.2.block.0.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
502
+ "vqmodel.decoder.up_block.up.2.block.0.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
503
+ "vqmodel.decoder.up_block.up.2.block.1.conv1.bias": "model-00008-of-00008.safetensors",
504
+ "vqmodel.decoder.up_block.up.2.block.1.conv1.weight": "model-00008-of-00008.safetensors",
505
+ "vqmodel.decoder.up_block.up.2.block.1.conv2.bias": "model-00008-of-00008.safetensors",
506
+ "vqmodel.decoder.up_block.up.2.block.1.conv2.weight": "model-00008-of-00008.safetensors",
507
+ "vqmodel.decoder.up_block.up.2.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
508
+ "vqmodel.decoder.up_block.up.2.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
509
+ "vqmodel.decoder.up_block.up.2.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
510
+ "vqmodel.decoder.up_block.up.2.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
511
+ "vqmodel.decoder.up_block.up.2.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
512
+ "vqmodel.decoder.up_block.up.2.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
513
+ "vqmodel.decoder.up_block.up.2.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
514
+ "vqmodel.decoder.up_block.up.2.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
515
+ "vqmodel.decoder.up_block.up.2.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
516
+ "vqmodel.decoder.up_block.up.2.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
517
+ "vqmodel.decoder.up_block.up.2.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
518
+ "vqmodel.decoder.up_block.up.2.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
519
+ "vqmodel.decoder.up_block.up.2.block.2.conv1.bias": "model-00008-of-00008.safetensors",
520
+ "vqmodel.decoder.up_block.up.2.block.2.conv1.weight": "model-00008-of-00008.safetensors",
521
+ "vqmodel.decoder.up_block.up.2.block.2.conv2.bias": "model-00008-of-00008.safetensors",
522
+ "vqmodel.decoder.up_block.up.2.block.2.conv2.weight": "model-00008-of-00008.safetensors",
523
+ "vqmodel.decoder.up_block.up.2.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
524
+ "vqmodel.decoder.up_block.up.2.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
525
+ "vqmodel.decoder.up_block.up.2.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
526
+ "vqmodel.decoder.up_block.up.2.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
527
+ "vqmodel.decoder.up_block.up.2.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
528
+ "vqmodel.decoder.up_block.up.2.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
529
+ "vqmodel.decoder.up_block.up.2.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
530
+ "vqmodel.decoder.up_block.up.2.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
531
+ "vqmodel.decoder.up_block.up.2.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
532
+ "vqmodel.decoder.up_block.up.2.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
533
+ "vqmodel.decoder.up_block.up.2.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
534
+ "vqmodel.decoder.up_block.up.2.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
535
+ "vqmodel.decoder.up_block.up.2.upsample.conv.bias": "model-00008-of-00008.safetensors",
536
+ "vqmodel.decoder.up_block.up.2.upsample.conv.weight": "model-00008-of-00008.safetensors",
537
+ "vqmodel.decoder.up_block.up.3.attn.0.k_proj.bias": "model-00008-of-00008.safetensors",
538
+ "vqmodel.decoder.up_block.up.3.attn.0.k_proj.weight": "model-00008-of-00008.safetensors",
539
+ "vqmodel.decoder.up_block.up.3.attn.0.out_proj.bias": "model-00008-of-00008.safetensors",
540
+ "vqmodel.decoder.up_block.up.3.attn.0.out_proj.weight": "model-00008-of-00008.safetensors",
541
+ "vqmodel.decoder.up_block.up.3.attn.0.q_proj.bias": "model-00008-of-00008.safetensors",
542
+ "vqmodel.decoder.up_block.up.3.attn.0.q_proj.weight": "model-00008-of-00008.safetensors",
543
+ "vqmodel.decoder.up_block.up.3.attn.0.v_proj.bias": "model-00008-of-00008.safetensors",
544
+ "vqmodel.decoder.up_block.up.3.attn.0.v_proj.weight": "model-00008-of-00008.safetensors",
545
+ "vqmodel.decoder.up_block.up.3.attn.1.k_proj.bias": "model-00008-of-00008.safetensors",
546
+ "vqmodel.decoder.up_block.up.3.attn.1.k_proj.weight": "model-00008-of-00008.safetensors",
547
+ "vqmodel.decoder.up_block.up.3.attn.1.out_proj.bias": "model-00008-of-00008.safetensors",
548
+ "vqmodel.decoder.up_block.up.3.attn.1.out_proj.weight": "model-00008-of-00008.safetensors",
549
+ "vqmodel.decoder.up_block.up.3.attn.1.q_proj.bias": "model-00008-of-00008.safetensors",
550
+ "vqmodel.decoder.up_block.up.3.attn.1.q_proj.weight": "model-00008-of-00008.safetensors",
551
+ "vqmodel.decoder.up_block.up.3.attn.1.v_proj.bias": "model-00008-of-00008.safetensors",
552
+ "vqmodel.decoder.up_block.up.3.attn.1.v_proj.weight": "model-00008-of-00008.safetensors",
553
+ "vqmodel.decoder.up_block.up.3.attn.2.k_proj.bias": "model-00008-of-00008.safetensors",
554
+ "vqmodel.decoder.up_block.up.3.attn.2.k_proj.weight": "model-00008-of-00008.safetensors",
555
+ "vqmodel.decoder.up_block.up.3.attn.2.out_proj.bias": "model-00008-of-00008.safetensors",
556
+ "vqmodel.decoder.up_block.up.3.attn.2.out_proj.weight": "model-00008-of-00008.safetensors",
557
+ "vqmodel.decoder.up_block.up.3.attn.2.q_proj.bias": "model-00008-of-00008.safetensors",
558
+ "vqmodel.decoder.up_block.up.3.attn.2.q_proj.weight": "model-00008-of-00008.safetensors",
559
+ "vqmodel.decoder.up_block.up.3.attn.2.v_proj.bias": "model-00008-of-00008.safetensors",
560
+ "vqmodel.decoder.up_block.up.3.attn.2.v_proj.weight": "model-00008-of-00008.safetensors",
561
+ "vqmodel.decoder.up_block.up.3.attn_norms.0.conv_b.bias": "model-00008-of-00008.safetensors",
562
+ "vqmodel.decoder.up_block.up.3.attn_norms.0.conv_b.weight": "model-00008-of-00008.safetensors",
563
+ "vqmodel.decoder.up_block.up.3.attn_norms.0.conv_y.bias": "model-00008-of-00008.safetensors",
564
+ "vqmodel.decoder.up_block.up.3.attn_norms.0.conv_y.weight": "model-00008-of-00008.safetensors",
565
+ "vqmodel.decoder.up_block.up.3.attn_norms.0.norm_layer.bias": "model-00008-of-00008.safetensors",
566
+ "vqmodel.decoder.up_block.up.3.attn_norms.0.norm_layer.weight": "model-00008-of-00008.safetensors",
567
+ "vqmodel.decoder.up_block.up.3.attn_norms.1.conv_b.bias": "model-00008-of-00008.safetensors",
568
+ "vqmodel.decoder.up_block.up.3.attn_norms.1.conv_b.weight": "model-00008-of-00008.safetensors",
569
+ "vqmodel.decoder.up_block.up.3.attn_norms.1.conv_y.bias": "model-00008-of-00008.safetensors",
570
+ "vqmodel.decoder.up_block.up.3.attn_norms.1.conv_y.weight": "model-00008-of-00008.safetensors",
571
+ "vqmodel.decoder.up_block.up.3.attn_norms.1.norm_layer.bias": "model-00008-of-00008.safetensors",
572
+ "vqmodel.decoder.up_block.up.3.attn_norms.1.norm_layer.weight": "model-00008-of-00008.safetensors",
573
+ "vqmodel.decoder.up_block.up.3.attn_norms.2.conv_b.bias": "model-00008-of-00008.safetensors",
574
+ "vqmodel.decoder.up_block.up.3.attn_norms.2.conv_b.weight": "model-00008-of-00008.safetensors",
575
+ "vqmodel.decoder.up_block.up.3.attn_norms.2.conv_y.bias": "model-00008-of-00008.safetensors",
576
+ "vqmodel.decoder.up_block.up.3.attn_norms.2.conv_y.weight": "model-00008-of-00008.safetensors",
577
+ "vqmodel.decoder.up_block.up.3.attn_norms.2.norm_layer.bias": "model-00008-of-00008.safetensors",
578
+ "vqmodel.decoder.up_block.up.3.attn_norms.2.norm_layer.weight": "model-00008-of-00008.safetensors",
579
+ "vqmodel.decoder.up_block.up.3.block.0.conv1.bias": "model-00008-of-00008.safetensors",
580
+ "vqmodel.decoder.up_block.up.3.block.0.conv1.weight": "model-00008-of-00008.safetensors",
581
+ "vqmodel.decoder.up_block.up.3.block.0.conv2.bias": "model-00008-of-00008.safetensors",
582
+ "vqmodel.decoder.up_block.up.3.block.0.conv2.weight": "model-00008-of-00008.safetensors",
583
+ "vqmodel.decoder.up_block.up.3.block.0.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
584
+ "vqmodel.decoder.up_block.up.3.block.0.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
585
+ "vqmodel.decoder.up_block.up.3.block.0.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
586
+ "vqmodel.decoder.up_block.up.3.block.0.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
587
+ "vqmodel.decoder.up_block.up.3.block.0.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
588
+ "vqmodel.decoder.up_block.up.3.block.0.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
589
+ "vqmodel.decoder.up_block.up.3.block.0.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
590
+ "vqmodel.decoder.up_block.up.3.block.0.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
591
+ "vqmodel.decoder.up_block.up.3.block.0.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
592
+ "vqmodel.decoder.up_block.up.3.block.0.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
593
+ "vqmodel.decoder.up_block.up.3.block.0.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
594
+ "vqmodel.decoder.up_block.up.3.block.0.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
595
+ "vqmodel.decoder.up_block.up.3.block.1.conv1.bias": "model-00008-of-00008.safetensors",
596
+ "vqmodel.decoder.up_block.up.3.block.1.conv1.weight": "model-00008-of-00008.safetensors",
597
+ "vqmodel.decoder.up_block.up.3.block.1.conv2.bias": "model-00008-of-00008.safetensors",
598
+ "vqmodel.decoder.up_block.up.3.block.1.conv2.weight": "model-00008-of-00008.safetensors",
599
+ "vqmodel.decoder.up_block.up.3.block.1.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
600
+ "vqmodel.decoder.up_block.up.3.block.1.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
601
+ "vqmodel.decoder.up_block.up.3.block.1.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
602
+ "vqmodel.decoder.up_block.up.3.block.1.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
603
+ "vqmodel.decoder.up_block.up.3.block.1.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
604
+ "vqmodel.decoder.up_block.up.3.block.1.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
605
+ "vqmodel.decoder.up_block.up.3.block.1.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
606
+ "vqmodel.decoder.up_block.up.3.block.1.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
607
+ "vqmodel.decoder.up_block.up.3.block.1.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
608
+ "vqmodel.decoder.up_block.up.3.block.1.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
609
+ "vqmodel.decoder.up_block.up.3.block.1.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
610
+ "vqmodel.decoder.up_block.up.3.block.1.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
611
+ "vqmodel.decoder.up_block.up.3.block.2.conv1.bias": "model-00008-of-00008.safetensors",
612
+ "vqmodel.decoder.up_block.up.3.block.2.conv1.weight": "model-00008-of-00008.safetensors",
613
+ "vqmodel.decoder.up_block.up.3.block.2.conv2.bias": "model-00008-of-00008.safetensors",
614
+ "vqmodel.decoder.up_block.up.3.block.2.conv2.weight": "model-00008-of-00008.safetensors",
615
+ "vqmodel.decoder.up_block.up.3.block.2.norm1.conv_b.bias": "model-00008-of-00008.safetensors",
616
+ "vqmodel.decoder.up_block.up.3.block.2.norm1.conv_b.weight": "model-00008-of-00008.safetensors",
617
+ "vqmodel.decoder.up_block.up.3.block.2.norm1.conv_y.bias": "model-00008-of-00008.safetensors",
618
+ "vqmodel.decoder.up_block.up.3.block.2.norm1.conv_y.weight": "model-00008-of-00008.safetensors",
619
+ "vqmodel.decoder.up_block.up.3.block.2.norm1.norm_layer.bias": "model-00008-of-00008.safetensors",
620
+ "vqmodel.decoder.up_block.up.3.block.2.norm1.norm_layer.weight": "model-00008-of-00008.safetensors",
621
+ "vqmodel.decoder.up_block.up.3.block.2.norm2.conv_b.bias": "model-00008-of-00008.safetensors",
622
+ "vqmodel.decoder.up_block.up.3.block.2.norm2.conv_b.weight": "model-00008-of-00008.safetensors",
623
+ "vqmodel.decoder.up_block.up.3.block.2.norm2.conv_y.bias": "model-00008-of-00008.safetensors",
624
+ "vqmodel.decoder.up_block.up.3.block.2.norm2.conv_y.weight": "model-00008-of-00008.safetensors",
625
+ "vqmodel.decoder.up_block.up.3.block.2.norm2.norm_layer.bias": "model-00008-of-00008.safetensors",
626
+ "vqmodel.decoder.up_block.up.3.block.2.norm2.norm_layer.weight": "model-00008-of-00008.safetensors",
627
+ "vqmodel.decoder.up_block.up.3.upsample.conv.bias": "model-00008-of-00008.safetensors",
628
+ "vqmodel.decoder.up_block.up.3.upsample.conv.weight": "model-00008-of-00008.safetensors",
629
  "vqmodel.encoder.conv_in.bias": "model-00007-of-00008.safetensors",
630
  "vqmodel.encoder.conv_in.weight": "model-00007-of-00008.safetensors",
631
  "vqmodel.encoder.conv_out.bias": "model-00007-of-00008.safetensors",
632
  "vqmodel.encoder.conv_out.weight": "model-00007-of-00008.safetensors",
633
+ "vqmodel.encoder.down_block.down.0.block.0.conv1.bias": "model-00007-of-00008.safetensors",
634
+ "vqmodel.encoder.down_block.down.0.block.0.conv1.weight": "model-00007-of-00008.safetensors",
635
+ "vqmodel.encoder.down_block.down.0.block.0.conv2.bias": "model-00007-of-00008.safetensors",
636
+ "vqmodel.encoder.down_block.down.0.block.0.conv2.weight": "model-00007-of-00008.safetensors",
637
+ "vqmodel.encoder.down_block.down.0.block.0.norm1.bias": "model-00007-of-00008.safetensors",
638
+ "vqmodel.encoder.down_block.down.0.block.0.norm1.weight": "model-00007-of-00008.safetensors",
639
+ "vqmodel.encoder.down_block.down.0.block.0.norm2.bias": "model-00007-of-00008.safetensors",
640
+ "vqmodel.encoder.down_block.down.0.block.0.norm2.weight": "model-00007-of-00008.safetensors",
641
+ "vqmodel.encoder.down_block.down.0.block.1.conv1.bias": "model-00007-of-00008.safetensors",
642
+ "vqmodel.encoder.down_block.down.0.block.1.conv1.weight": "model-00007-of-00008.safetensors",
643
+ "vqmodel.encoder.down_block.down.0.block.1.conv2.bias": "model-00007-of-00008.safetensors",
644
+ "vqmodel.encoder.down_block.down.0.block.1.conv2.weight": "model-00007-of-00008.safetensors",
645
+ "vqmodel.encoder.down_block.down.0.block.1.norm1.bias": "model-00007-of-00008.safetensors",
646
+ "vqmodel.encoder.down_block.down.0.block.1.norm1.weight": "model-00007-of-00008.safetensors",
647
+ "vqmodel.encoder.down_block.down.0.block.1.norm2.bias": "model-00007-of-00008.safetensors",
648
+ "vqmodel.encoder.down_block.down.0.block.1.norm2.weight": "model-00007-of-00008.safetensors",
649
+ "vqmodel.encoder.down_block.down.0.downsample.conv.bias": "model-00007-of-00008.safetensors",
650
+ "vqmodel.encoder.down_block.down.0.downsample.conv.weight": "model-00007-of-00008.safetensors",
651
+ "vqmodel.encoder.down_block.down.1.block.0.conv1.bias": "model-00007-of-00008.safetensors",
652
+ "vqmodel.encoder.down_block.down.1.block.0.conv1.weight": "model-00007-of-00008.safetensors",
653
+ "vqmodel.encoder.down_block.down.1.block.0.conv2.bias": "model-00007-of-00008.safetensors",
654
+ "vqmodel.encoder.down_block.down.1.block.0.conv2.weight": "model-00007-of-00008.safetensors",
655
+ "vqmodel.encoder.down_block.down.1.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
656
+ "vqmodel.encoder.down_block.down.1.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
657
+ "vqmodel.encoder.down_block.down.1.block.0.norm1.bias": "model-00007-of-00008.safetensors",
658
+ "vqmodel.encoder.down_block.down.1.block.0.norm1.weight": "model-00007-of-00008.safetensors",
659
+ "vqmodel.encoder.down_block.down.1.block.0.norm2.bias": "model-00007-of-00008.safetensors",
660
+ "vqmodel.encoder.down_block.down.1.block.0.norm2.weight": "model-00007-of-00008.safetensors",
661
+ "vqmodel.encoder.down_block.down.1.block.1.conv1.bias": "model-00007-of-00008.safetensors",
662
+ "vqmodel.encoder.down_block.down.1.block.1.conv1.weight": "model-00007-of-00008.safetensors",
663
+ "vqmodel.encoder.down_block.down.1.block.1.conv2.bias": "model-00007-of-00008.safetensors",
664
+ "vqmodel.encoder.down_block.down.1.block.1.conv2.weight": "model-00007-of-00008.safetensors",
665
+ "vqmodel.encoder.down_block.down.1.block.1.norm1.bias": "model-00007-of-00008.safetensors",
666
+ "vqmodel.encoder.down_block.down.1.block.1.norm1.weight": "model-00007-of-00008.safetensors",
667
+ "vqmodel.encoder.down_block.down.1.block.1.norm2.bias": "model-00007-of-00008.safetensors",
668
+ "vqmodel.encoder.down_block.down.1.block.1.norm2.weight": "model-00007-of-00008.safetensors",
669
+ "vqmodel.encoder.down_block.down.1.downsample.conv.bias": "model-00007-of-00008.safetensors",
670
+ "vqmodel.encoder.down_block.down.1.downsample.conv.weight": "model-00007-of-00008.safetensors",
671
+ "vqmodel.encoder.down_block.down.2.block.0.conv1.bias": "model-00007-of-00008.safetensors",
672
+ "vqmodel.encoder.down_block.down.2.block.0.conv1.weight": "model-00007-of-00008.safetensors",
673
+ "vqmodel.encoder.down_block.down.2.block.0.conv2.bias": "model-00007-of-00008.safetensors",
674
+ "vqmodel.encoder.down_block.down.2.block.0.conv2.weight": "model-00007-of-00008.safetensors",
675
+ "vqmodel.encoder.down_block.down.2.block.0.norm1.bias": "model-00007-of-00008.safetensors",
676
+ "vqmodel.encoder.down_block.down.2.block.0.norm1.weight": "model-00007-of-00008.safetensors",
677
+ "vqmodel.encoder.down_block.down.2.block.0.norm2.bias": "model-00007-of-00008.safetensors",
678
+ "vqmodel.encoder.down_block.down.2.block.0.norm2.weight": "model-00007-of-00008.safetensors",
679
+ "vqmodel.encoder.down_block.down.2.block.1.conv1.bias": "model-00007-of-00008.safetensors",
680
+ "vqmodel.encoder.down_block.down.2.block.1.conv1.weight": "model-00007-of-00008.safetensors",
681
+ "vqmodel.encoder.down_block.down.2.block.1.conv2.bias": "model-00007-of-00008.safetensors",
682
+ "vqmodel.encoder.down_block.down.2.block.1.conv2.weight": "model-00007-of-00008.safetensors",
683
+ "vqmodel.encoder.down_block.down.2.block.1.norm1.bias": "model-00007-of-00008.safetensors",
684
+ "vqmodel.encoder.down_block.down.2.block.1.norm1.weight": "model-00007-of-00008.safetensors",
685
+ "vqmodel.encoder.down_block.down.2.block.1.norm2.bias": "model-00007-of-00008.safetensors",
686
+ "vqmodel.encoder.down_block.down.2.block.1.norm2.weight": "model-00007-of-00008.safetensors",
687
+ "vqmodel.encoder.down_block.down.2.downsample.conv.bias": "model-00007-of-00008.safetensors",
688
+ "vqmodel.encoder.down_block.down.2.downsample.conv.weight": "model-00007-of-00008.safetensors",
689
+ "vqmodel.encoder.down_block.down.3.attn.0.k_proj.bias": "model-00007-of-00008.safetensors",
690
+ "vqmodel.encoder.down_block.down.3.attn.0.k_proj.weight": "model-00007-of-00008.safetensors",
691
+ "vqmodel.encoder.down_block.down.3.attn.0.out_proj.bias": "model-00007-of-00008.safetensors",
692
+ "vqmodel.encoder.down_block.down.3.attn.0.out_proj.weight": "model-00007-of-00008.safetensors",
693
+ "vqmodel.encoder.down_block.down.3.attn.0.q_proj.bias": "model-00007-of-00008.safetensors",
694
+ "vqmodel.encoder.down_block.down.3.attn.0.q_proj.weight": "model-00007-of-00008.safetensors",
695
+ "vqmodel.encoder.down_block.down.3.attn.0.v_proj.bias": "model-00007-of-00008.safetensors",
696
+ "vqmodel.encoder.down_block.down.3.attn.0.v_proj.weight": "model-00007-of-00008.safetensors",
697
+ "vqmodel.encoder.down_block.down.3.attn.1.k_proj.bias": "model-00007-of-00008.safetensors",
698
+ "vqmodel.encoder.down_block.down.3.attn.1.k_proj.weight": "model-00007-of-00008.safetensors",
699
+ "vqmodel.encoder.down_block.down.3.attn.1.out_proj.bias": "model-00007-of-00008.safetensors",
700
+ "vqmodel.encoder.down_block.down.3.attn.1.out_proj.weight": "model-00007-of-00008.safetensors",
701
+ "vqmodel.encoder.down_block.down.3.attn.1.q_proj.bias": "model-00007-of-00008.safetensors",
702
+ "vqmodel.encoder.down_block.down.3.attn.1.q_proj.weight": "model-00007-of-00008.safetensors",
703
+ "vqmodel.encoder.down_block.down.3.attn.1.v_proj.bias": "model-00007-of-00008.safetensors",
704
+ "vqmodel.encoder.down_block.down.3.attn.1.v_proj.weight": "model-00007-of-00008.safetensors",
705
+ "vqmodel.encoder.down_block.down.3.attn_norms.0.bias": "model-00007-of-00008.safetensors",
706
+ "vqmodel.encoder.down_block.down.3.attn_norms.0.weight": "model-00007-of-00008.safetensors",
707
+ "vqmodel.encoder.down_block.down.3.attn_norms.1.bias": "model-00007-of-00008.safetensors",
708
+ "vqmodel.encoder.down_block.down.3.attn_norms.1.weight": "model-00007-of-00008.safetensors",
709
+ "vqmodel.encoder.down_block.down.3.block.0.conv1.bias": "model-00007-of-00008.safetensors",
710
+ "vqmodel.encoder.down_block.down.3.block.0.conv1.weight": "model-00007-of-00008.safetensors",
711
+ "vqmodel.encoder.down_block.down.3.block.0.conv2.bias": "model-00007-of-00008.safetensors",
712
+ "vqmodel.encoder.down_block.down.3.block.0.conv2.weight": "model-00007-of-00008.safetensors",
713
+ "vqmodel.encoder.down_block.down.3.block.0.nin_shortcut.bias": "model-00007-of-00008.safetensors",
714
+ "vqmodel.encoder.down_block.down.3.block.0.nin_shortcut.weight": "model-00007-of-00008.safetensors",
715
+ "vqmodel.encoder.down_block.down.3.block.0.norm1.bias": "model-00007-of-00008.safetensors",
716
+ "vqmodel.encoder.down_block.down.3.block.0.norm1.weight": "model-00007-of-00008.safetensors",
717
+ "vqmodel.encoder.down_block.down.3.block.0.norm2.bias": "model-00007-of-00008.safetensors",
718
+ "vqmodel.encoder.down_block.down.3.block.0.norm2.weight": "model-00007-of-00008.safetensors",
719
+ "vqmodel.encoder.down_block.down.3.block.1.conv1.bias": "model-00007-of-00008.safetensors",
720
+ "vqmodel.encoder.down_block.down.3.block.1.conv1.weight": "model-00007-of-00008.safetensors",
721
+ "vqmodel.encoder.down_block.down.3.block.1.conv2.bias": "model-00007-of-00008.safetensors",
722
+ "vqmodel.encoder.down_block.down.3.block.1.conv2.weight": "model-00007-of-00008.safetensors",
723
+ "vqmodel.encoder.down_block.down.3.block.1.norm1.bias": "model-00007-of-00008.safetensors",
724
+ "vqmodel.encoder.down_block.down.3.block.1.norm1.weight": "model-00007-of-00008.safetensors",
725
+ "vqmodel.encoder.down_block.down.3.block.1.norm2.bias": "model-00007-of-00008.safetensors",
726
+ "vqmodel.encoder.down_block.down.3.block.1.norm2.weight": "model-00007-of-00008.safetensors",
727
+ "vqmodel.encoder.middle_block.attn_1.k_proj.bias": "model-00007-of-00008.safetensors",
728
+ "vqmodel.encoder.middle_block.attn_1.k_proj.weight": "model-00007-of-00008.safetensors",
729
+ "vqmodel.encoder.middle_block.attn_1.out_proj.bias": "model-00007-of-00008.safetensors",
730
+ "vqmodel.encoder.middle_block.attn_1.out_proj.weight": "model-00007-of-00008.safetensors",
731
+ "vqmodel.encoder.middle_block.attn_1.q_proj.bias": "model-00007-of-00008.safetensors",
732
+ "vqmodel.encoder.middle_block.attn_1.q_proj.weight": "model-00007-of-00008.safetensors",
733
+ "vqmodel.encoder.middle_block.attn_1.v_proj.bias": "model-00007-of-00008.safetensors",
734
+ "vqmodel.encoder.middle_block.attn_1.v_proj.weight": "model-00007-of-00008.safetensors",
735
+ "vqmodel.encoder.middle_block.attn_norm.bias": "model-00007-of-00008.safetensors",
736
+ "vqmodel.encoder.middle_block.attn_norm.weight": "model-00007-of-00008.safetensors",
737
+ "vqmodel.encoder.middle_block.block_1.conv1.bias": "model-00007-of-00008.safetensors",
738
+ "vqmodel.encoder.middle_block.block_1.conv1.weight": "model-00007-of-00008.safetensors",
739
+ "vqmodel.encoder.middle_block.block_1.conv2.bias": "model-00007-of-00008.safetensors",
740
+ "vqmodel.encoder.middle_block.block_1.conv2.weight": "model-00007-of-00008.safetensors",
741
+ "vqmodel.encoder.middle_block.block_1.norm1.bias": "model-00007-of-00008.safetensors",
742
+ "vqmodel.encoder.middle_block.block_1.norm1.weight": "model-00007-of-00008.safetensors",
743
+ "vqmodel.encoder.middle_block.block_1.norm2.bias": "model-00007-of-00008.safetensors",
744
+ "vqmodel.encoder.middle_block.block_1.norm2.weight": "model-00007-of-00008.safetensors",
745
+ "vqmodel.encoder.middle_block.block_2.conv1.bias": "model-00007-of-00008.safetensors",
746
+ "vqmodel.encoder.middle_block.block_2.conv1.weight": "model-00007-of-00008.safetensors",
747
+ "vqmodel.encoder.middle_block.block_2.conv2.bias": "model-00007-of-00008.safetensors",
748
+ "vqmodel.encoder.middle_block.block_2.conv2.weight": "model-00007-of-00008.safetensors",
749
+ "vqmodel.encoder.middle_block.block_2.norm1.bias": "model-00007-of-00008.safetensors",
750
+ "vqmodel.encoder.middle_block.block_2.norm1.weight": "model-00007-of-00008.safetensors",
751
+ "vqmodel.encoder.middle_block.block_2.norm2.bias": "model-00007-of-00008.safetensors",
752
+ "vqmodel.encoder.middle_block.block_2.norm2.weight": "model-00007-of-00008.safetensors",
753
  "vqmodel.encoder.norm_out.bias": "model-00007-of-00008.safetensors",
754
  "vqmodel.encoder.norm_out.weight": "model-00007-of-00008.safetensors",
755
  "vqmodel.encoder.time_conv.0.conv.conv.bias": "model-00007-of-00008.safetensors",