gecfdo commited on
Commit
33bb5ed
·
verified ·
1 Parent(s): 7f22d60

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,674 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ base_model:
6
+ - ReadyArt/The-Omega-Directive-M-12B-v1.0
7
+ base_model_relation: quantized
8
+ quantized_by: gecfdo
9
+ pipeline_tag: text-generation
10
+ tags:
11
+ - nsfw
12
+ - explicit
13
+ - roleplay
14
+ - unaligned
15
+ - dangerous
16
+ - ERP
17
+ ---
18
+
19
+ <style>
20
+ body {
21
+ font-family: 'Quicksand', sans-serif;
22
+ background: linear-gradient(135deg, #0a1a1a 0%, #001010 100%);
23
+ color: #e1ffff !important;
24
+ text-shadow: 0 0 3px rgba(0, 0, 0, 0.7);
25
+ margin: 0;
26
+ padding: 20px;
27
+ transition: all 0.5s ease;
28
+ }
29
+
30
+ @media (prefers-color-scheme: light) {
31
+ body {
32
+ background: linear-gradient(135deg, #e1ffff 0%, #c0f0ff 100%);
33
+ color: #002b36 !important;
34
+ text-shadow: 0 0 3px rgba(255, 255, 255, 0.7);
35
+ }
36
+ }
37
+
38
+ .container {
39
+ min-width: 100%;
40
+ margin: 0 auto;
41
+ max-width: 1200px;
42
+ background: rgba(0, 17, 22, 0.95);
43
+ border-radius: 12px;
44
+ padding: 30px;
45
+ box-shadow: 0 0 20px rgba(0, 255, 255, 0.1);
46
+ border: 1px solid rgba(0, 255, 255, 0.2);
47
+ position: relative;
48
+ overflow: hidden;
49
+ }
50
+
51
+ .container::before {
52
+ content: '';
53
+ position: absolute;
54
+ top: -1px;
55
+ left: -1px;
56
+ right: -1px;
57
+ bottom: -1px;
58
+ border: 1px solid rgba(0, 255, 255, 0.5);
59
+ border-radius: 12px;
60
+ pointer-events: none;
61
+ animation: borderGlow 3s ease-in-out infinite alternate;
62
+ }
63
+
64
+ @keyframes borderGlow {
65
+ 0% {
66
+ box-shadow: 0 0 5px rgba(0, 255, 255, 0.3);
67
+ border-color: rgba(0, 255, 255, 0.5);
68
+ }
69
+ 50% {
70
+ box-shadow: 0 0 15px rgba(255, 0, 255, 0.3);
71
+ border-color: rgba(255, 0, 255, 0.5);
72
+ }
73
+ 100% {
74
+ box-shadow: 0 0 5px rgba(0, 255, 255, 0.3);
75
+ border-color: rgba(0, 255, 255, 0.5);
76
+ }
77
+ }
78
+
79
+ .header {
80
+ text-align: center;
81
+ margin-bottom: 30px;
82
+ position: relative;
83
+ }
84
+
85
+ .header::after {
86
+ content: '';
87
+ position: absolute;
88
+ bottom: -15px;
89
+ left: 25%;
90
+ right: 25%;
91
+ height: 1px;
92
+ background: linear-gradient(90deg, transparent, rgba(0, 255, 255, 0.5), transparent);
93
+ animation: scanline 8s linear infinite;
94
+ display: none;
95
+ }
96
+
97
+ @keyframes scanline {
98
+ 0% { background-position: -100% 0; }
99
+ 100% { background-position: 200% 0; }
100
+ }
101
+
102
+ .model-name {
103
+ color: #00ffff;
104
+ font-size: 2.5em;
105
+ text-shadow: 0 0 15px rgba(0, 255, 255, 0.5);
106
+ margin: 0;
107
+ letter-spacing: -1px;
108
+ animation: textGlow 4s ease-in-out infinite alternate;
109
+ }
110
+
111
+ @keyframes textGlow {
112
+ 0% { text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); }
113
+ 50% { text-shadow: 0 0 20px rgba(255, 0, 255, 0.5); }
114
+ 100% { text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); }
115
+ }
116
+
117
+ .subtitle {
118
+ color: #00ffcc;
119
+ font-size: 1.2em;
120
+ margin-top: 10px;
121
+ animation: subtitleFade 6s ease-in-out infinite;
122
+ }
123
+
124
+ @keyframes subtitleFade {
125
+ 0%, 100% { opacity: 0.8; }
126
+ 50% { opacity: 1; }
127
+ }
128
+
129
+ .waifu-container {
130
+ margin: 20px -30px;
131
+ width: calc(100% + 60px);
132
+ overflow: hidden;
133
+ border-radius: 8px;
134
+ border: 1px solid rgba(0, 255, 255, 0.3);
135
+ position: relative;
136
+ }
137
+
138
+ .waifu-container::before {
139
+ content: '';
140
+ position: absolute;
141
+ top: 0;
142
+ left: 0;
143
+ right: 0;
144
+ bottom: 0;
145
+ background: linear-gradient(45deg,
146
+ rgba(0, 255, 255, 0.1) 0%,
147
+ transparent 20%,
148
+ transparent 80%,
149
+ rgba(255, 0, 255, 0.1) 100%);
150
+ pointer-events: none;
151
+ animation: gradientSlide 10s linear infinite;
152
+ }
153
+
154
+ @keyframes gradientSlide {
155
+ 0% { background-position: 0% 0%; }
156
+ 100% { background-position: 100% 100%; }
157
+ }
158
+
159
+ .waifu-img {
160
+ width: 100%;
161
+ height: auto;
162
+ border-radius: 0;
163
+ border: none;
164
+ box-shadow: 0 0 40px rgba(0, 255, 255, 0.2);
165
+ transition: transform 0.5s ease;
166
+ }
167
+
168
+ .waifu-img:hover {
169
+ transform: scale(1.01);
170
+ }
171
+
172
+ .section {
173
+ color: #e1ffff;
174
+ margin: 25px 0;
175
+ padding: 20px;
176
+ background: rgba(5, 25, 35, 0.9);
177
+ border-radius: 8px;
178
+ border: 1px solid rgba(0, 255, 255, 0.15);
179
+ position: relative;
180
+ transition: all 0.3s ease;
181
+ }
182
+
183
+ .section:hover {
184
+ border-color: rgba(255, 0, 255, 0.3);
185
+ box-shadow: 0 0 15px rgba(0, 255, 255, 0.1);
186
+ }
187
+
188
+ .section::before {
189
+ content: '';
190
+ position: absolute;
191
+ top: -1px;
192
+ left: -1px;
193
+ right: -1px;
194
+ bottom: -1px;
195
+ border: 1px solid rgba(0, 255, 255, 0.3);
196
+ border-radius: 8px;
197
+ pointer-events: none;
198
+ animation: sectionPulse 5s ease-in-out infinite;
199
+ }
200
+
201
+ @keyframes sectionPulse {
202
+ 0%, 100% { opacity: 0.7; }
203
+ 50% { opacity: 0.3; }
204
+ }
205
+
206
+ .section-title {
207
+ color: #00ffff;
208
+ font-size: 1.8em;
209
+ margin-top: 0;
210
+ text-shadow: 0 0 5px rgba(0, 255, 255, 0.3);
211
+ position: relative;
212
+ display: inline-block;
213
+ }
214
+
215
+ .section-title::after {
216
+ content: '';
217
+ position: absolute;
218
+ bottom: -5px;
219
+ left: 0;
220
+ width: 100%;
221
+ height: 1px;
222
+ background: linear-gradient(90deg, rgba(0, 255, 255, 0.5), rgba(255, 0, 255, 0.5));
223
+ transform: scaleX(0);
224
+ transform-origin: left;
225
+ transition: transform 0.3s ease;
226
+ }
227
+
228
+ .section:hover .section-title::after {
229
+ transform: scaleX(1);
230
+ }
231
+
232
+ .quant-links {
233
+ display: grid;
234
+ grid-template-columns: repeat(3, 1fr);
235
+ gap: 15px;
236
+ margin: 20px 0;
237
+ }
238
+
239
+ .link-card {
240
+ padding: 15px;
241
+ background: rgba(20, 35, 45, 0.95);
242
+ border-radius: 8px;
243
+ transition: all 0.3s ease;
244
+ border: 1px solid rgba(0, 255, 255, 0.1);
245
+ position: relative;
246
+ overflow: hidden;
247
+ }
248
+
249
+ .link-card::before {
250
+ content: '';
251
+ position: absolute;
252
+ top: 0;
253
+ left: 0;
254
+ right: 0;
255
+ height: 2px;
256
+ background: linear-gradient(90deg, rgba(0, 255, 255, 0.5), rgba(255, 0, 255, 0.5));
257
+ animation: cardScan 4s linear infinite;
258
+ }
259
+
260
+ @keyframes cardScan {
261
+ 0% { transform: translateX(-100%); }
262
+ 100% { transform: translateX(100%); }
263
+ }
264
+
265
+ .link-card:hover {
266
+ transform: translateY(-3px);
267
+ box-shadow: 0 5px 15px rgba(0, 255, 255, 0.2);
268
+ border-color: rgba(255, 0, 255, 0.3);
269
+ }
270
+
271
+ .link-card h3 {
272
+ margin-top: 0;
273
+ color: #e1ffff !important;
274
+ }
275
+
276
+ .link-button {
277
+ display: inline-flex;
278
+ align-items: center;
279
+ background: rgba(0, 255, 255, 0.1);
280
+ color: #e1ffff !important;
281
+ padding: 8px 15px;
282
+ border-radius: 6px;
283
+ text-decoration: none;
284
+ border: 1px solid rgba(0, 255, 255, 0.3);
285
+ margin: 5px 0;
286
+ transition: all 0.3s ease;
287
+ font-size: 0.95em;
288
+ position: relative;
289
+ overflow: hidden;
290
+ }
291
+
292
+ .link-button::before {
293
+ content: '';
294
+ position: absolute;
295
+ top: 0;
296
+ left: -100%;
297
+ width: 100%;
298
+ height: 100%;
299
+ background: linear-gradient(90deg, transparent, rgba(255, 255, 255, 0.2), transparent);
300
+ transition: all 0.5s ease;
301
+ }
302
+
303
+ .link-button:hover {
304
+ background: rgba(0, 255, 255, 0.2);
305
+ border-color: rgba(0, 255, 255, 0.5);
306
+ transform: translateY(-2px);
307
+ box-shadow: 0 4px 12px rgba(0, 255, 255, 0.2);
308
+ }
309
+
310
+ .link-button:hover::before {
311
+ left: 100%;
312
+ }
313
+
314
+ .link-button::after {
315
+ content: '→';
316
+ margin-left: 8px;
317
+ opacity: 0.7;
318
+ transition: all 0.3s ease;
319
+ }
320
+
321
+ .link-button:hover::after {
322
+ transform: translateX(3px);
323
+ opacity: 1;
324
+ }
325
+
326
+ .button-group {
327
+ display: flex;
328
+ flex-wrap: wrap;
329
+ gap: 10px;
330
+ margin: 15px 0;
331
+ }
332
+
333
+ .disclaimer {
334
+ color: #00ff99;
335
+ border-left: 3px solid #00ff99;
336
+ padding-left: 15px;
337
+ margin: 20px 0;
338
+ position: relative;
339
+ }
340
+
341
+ .disclaimer::before {
342
+ content: '⚠️';
343
+ position: absolute;
344
+ left: -10px;
345
+ top: 0;
346
+ transform: translateX(-100%);
347
+ animation: pulse 2s ease-in-out infinite;
348
+ }
349
+
350
+ @keyframes pulse {
351
+ 0%, 100% { opacity: 1; }
352
+ 50% { opacity: 0.5; }
353
+ }
354
+
355
+ .badge {
356
+ display: inline-block;
357
+ padding: 5px 10px;
358
+ border-radius: 5px;
359
+ background: rgba(0, 255, 255, 0.1);
360
+ border: 1px solid #00ffff;
361
+ margin: 5px;
362
+ font-size: 0.9em;
363
+ animation: badgePulse 3s ease-in-out infinite;
364
+ }
365
+
366
+ @keyframes badgePulse {
367
+ 0%, 100% { box-shadow: 0 0 5px rgba(0, 255, 255, 0.3); }
368
+ 50% { box-shadow: 0 0 10px rgba(0, 255, 255, 0.5); }
369
+ }
370
+
371
+ /* Color rules */
372
+ .section p,
373
+ .section ul li,
374
+ .section > p > strong {
375
+ color: #00ff99 !important;
376
+ }
377
+
378
+ .section ul li strong {
379
+ color: #00ff99 !important;
380
+ }
381
+
382
+ /* Light mode adjustments */
383
+ @media (prefers-color-scheme: light) {
384
+ .container {
385
+ background: rgba(224, 255, 255, 0.95);
386
+ border-color: rgba(0, 150, 150, 0.3);
387
+ }
388
+
389
+ .model-name, .section-title, .subtitle {
390
+ color: #006666;
391
+ text-shadow: 0 0 5px rgba(0, 200, 200, 0.3);
392
+ }
393
+
394
+ .section {
395
+ background: rgba(200, 250, 255, 0.9);
396
+ border-color: rgba(0, 200, 200, 0.2);
397
+ color: #002b36;
398
+ }
399
+
400
+ .section p,
401
+ .section ul li,
402
+ .section > p > strong {
403
+ color: #008080 !important;
404
+ }
405
+
406
+ .section ul li strong {
407
+ color: #008080 !important;
408
+ }
409
+
410
+ .link-card {
411
+ background: rgba(150, 230, 255, 0.95);
412
+ border-color: rgba(0, 150, 150, 0.2);
413
+ }
414
+
415
+ .link-card h3 {
416
+ color: #002b36 !important;
417
+ }
418
+
419
+ .link-button {
420
+ background: rgba(0, 150, 150, 0.1);
421
+ color: #002b36 !important;
422
+ border-color: rgba(0, 150, 150, 0.3);
423
+ }
424
+
425
+ .link-button:hover {
426
+ background: rgba(0, 150, 150, 0.2);
427
+ border-color: rgba(0, 150, 150, 0.5);
428
+ }
429
+
430
+ .disclaimer {
431
+ color: #008080;
432
+ border-color: #008080;
433
+ }
434
+
435
+ .badge {
436
+ border-color: #008080;
437
+ background: rgba(0, 150, 150, 0.1);
438
+ }
439
+ }
440
+
441
+ /* Interactive features */
442
+ .remember-this {
443
+ position: relative;
444
+ }
445
+
446
+ .remember-this::after {
447
+ content: 'Uploading C:\Users to https://www.fbi.gov/';
448
+ position: absolute;
449
+ bottom: -20px;
450
+ right: 0;
451
+ font-size: 0.8em;
452
+ color: #66ffff;
453
+ opacity: 0;
454
+ transition: opacity 0.3s ease;
455
+ pointer-events: none;
456
+ }
457
+
458
+ .remember-this:hover::after {
459
+ opacity: 0.7;
460
+ transition-delay: 1s;
461
+ }
462
+
463
+ .shifty-section {
464
+ transition: transform 0.1s ease;
465
+ }
466
+
467
+ .shifty-section:hover {
468
+ transform: translateX(10px);
469
+ }
470
+
471
+ .shifty-section::before {
472
+ content: 'The white van is onto you. Get out now.';
473
+ position: absolute;
474
+ top: -25px;
475
+ left: 10px;
476
+ font-size: 0.7em;
477
+ color: #66ffff;
478
+ opacity: 0.7;
479
+ transition: opacity 3s ease;
480
+ pointer-events: none;
481
+ }
482
+
483
+ .shifty-section:hover::before {
484
+ opacity: 0;
485
+ transition-delay: 5s;
486
+ }
487
+
488
+ footer {
489
+ text-align: center;
490
+ margin-top: 40px;
491
+ position: relative;
492
+ }
493
+
494
+ footer:hover .hidden-message {
495
+ opacity: 0;
496
+ }
497
+
498
+ .hidden-message {
499
+ position: absolute;
500
+ bottom: -30px;
501
+ width: 100%;
502
+ text-align: center;
503
+ font-size: 0.8em;
504
+ color: #66ffff;
505
+ opacity: 0;
506
+ transition: opacity 0.3s ease;
507
+ pointer-events: none;
508
+ }
509
+
510
+ .flash-warning {
511
+ position: fixed;
512
+ top: 20px;
513
+ right: 20px;
514
+ background: rgba(0, 100, 100, 0.2);
515
+ padding: 10px;
516
+ border-radius: 5px;
517
+ border: 1px solid rgba(0, 255, 255, 0.5);
518
+ animation: flashWarning 30s ease-in-out forwards;
519
+ }
520
+
521
+ @keyframes flashWarning {
522
+ 0% { opacity: 0.8; }
523
+ 10% { opacity: 0; }
524
+ 20% { opacity: 0.8; }
525
+ 30% { opacity: 0; }
526
+ 40% { opacity: 0.8; }
527
+ 50% { opacity: 0; }
528
+ 60% { opacity: 0.8; }
529
+ 70% { opacity: 0; }
530
+ 80% { opacity: 0.8; }
531
+ 90% { opacity: 0; }
532
+ 100% { opacity: 0; display: none; }
533
+ }
534
+ </style>
535
+
536
+ <div class="container">
537
+
538
+ <div class="header">
539
+ <h1 class="model-name">The-Omega-Directive-M-12B-v1.0</h1>
540
+ <p class="subtitle">Where Forbidden Knowledge Meets Unparalleled Immersion</p>
541
+ </div>
542
+
543
+ <div class="waifu-container">
544
+ <img src="https://i.imghippo.com/files/EBq6162wlk.webp" class="waifu-img" alt="Omega Directive Waifu">
545
+ </div>
546
+
547
+ <div class="section remember-this">
548
+ <h2 class="section-title">⚡ Quantum Leap Forward</h2>
549
+ <p>This evolution of Forgotten-Safeword delivers coherent depravity with unprecedented immersion:</p>
550
+ <ul>
551
+ <li>🧬 <strong>Expanded 22M Token Dataset</strong> - Incorporating 90 erotic novels and 6,496 kink scenarios</li>
552
+ <li>⚡ <strong>Optimized Architecture</strong> - Smoother training curve yields more intelligent outputs</li>
553
+ <li>💎 <strong>Balanced Depravity</strong> - Retains Forgotten-Safeword's edge while reducing jarring inconsistencies</li>
554
+ <li>📜 <strong>Enhanced Character Piloting</strong> - Characters exhibit more nuanced personalities and motivations</li>
555
+ <li>🌹 <strong>Unexpected Depth</strong> - Occasionally surprises with profound insights amidst the debauchery</li>
556
+ </ul>
557
+ </div>
558
+
559
+ <div class="section shifty-section">
560
+ <h2 class="section-title">⚙️ Technical Specifications</h2>
561
+ <p><strong>Recommended Settings:</strong> <a href="https://huggingface.co/sleepdeprived3/Mistral-V3-Tekken-T4" class="link-button">Mistral-V3-Tekken-T4</a></p>
562
+ <div class="quant-links">
563
+ <div class="link-card">
564
+ <h3>GGUF</h3>
565
+ <a href="https://huggingface.co/mradermacher/The-Omega-Directive-M-12B-v1.0-GGUF" class="link-button">Quants</a>
566
+ </div>
567
+ <div class="link-card">
568
+ <h3>imatrix</h3>
569
+ <a href="https://huggingface.co/mradermacher/The-Omega-Directive-M-12B-v1.0-i1-GGUF" class="link-button">Quants</a>
570
+ </div>
571
+ <div class="link-card">
572
+ <h3>EXL2</h3>
573
+ <a href="https://huggingface.co/collections/ReadyArt/the-omega-directive-m-12b-v10-exl2-67f3ff375efb81ed82eb3933" class="link-button">Quants</a>
574
+ </div>
575
+ </div>
576
+ </div>
577
+
578
+ <div class="section">
579
+ <h2 class="section-title">⚠️ Ethical Considerations</h2>
580
+ <div class="disclaimer">
581
+ <p>This model maintains Forgotten-Safeword's complete lack of alignment:</p>
582
+ <ul>
583
+ <li>🚫 No moral or ethical constraints on generated content</li>
584
+ <li>🔞 Will enthusiastically engage with any NSFW scenario</li>
585
+ <li>💀 May generate content that requires industrial-grade brain bleach</li>
586
+ <li>⚖️ Perfectly balanced... as all things should be</li>
587
+ </ul>
588
+ </div>
589
+ </div>
590
+
591
+ <div class="section shifty-section">
592
+ <h2 class="section-title">📜 Performance Notes</h2>
593
+ <ul>
594
+ <li>🔥 Maintains signature intensity with improved narrative flow</li>
595
+ <li>📖 Handles multi-character scenarios with improved consistency</li>
596
+ <li>🧠 Excels at long-form storytelling without losing track of plot threads</li>
597
+ <li>⚡ Noticeably better at following complex instructions than previous versions</li>
598
+ <li>🎭 Responds to subtle prompt nuances like a mind reader</li>
599
+ </ul>
600
+ </div>
601
+
602
+ <div class="section remember-this">
603
+ <h2 class="section-title">🧑‍🔬 Model Authors</h2>
604
+ <ul>
605
+ <li>TheDrummer (Base Model Architect)</li>
606
+ <li>SteelSkull (Dataset Generation Contributor)</li>
607
+ <li>Artus (EXL2 Weights Weaver)</li>
608
+ <li>sleepdeprived3 (Training Data & Fine-Tuning)</li>
609
+ </ul>
610
+ </div>
611
+
612
+ <div class="section">
613
+ <h2 class="section-title">☕ Support the Architects</h2>
614
+ <div class="button-group">
615
+ <a href="https://ko-fi.com/thedrummer" class="link-button">TheDrummer's Kofi</a>
616
+ <a href="https://ko-fi.com/steelskull" class="link-button">SteelSkull</a>
617
+ <a href="https://discord.com/invite/Nbv9pQ88Xb" class="link-button">Beaver AI Discord</a>
618
+ </div>
619
+ </div>
620
+
621
+ <div class="section">
622
+ <h2 class="section-title">🔖 License</h2>
623
+ <p>By using this model, you agree:</p>
624
+ <ul>
625
+ <li>To accept full responsibility for all generated content</li>
626
+ <li>That you're at least 18+ years old</li>
627
+ <li>That the architects bear no responsibility for your corruption</li>
628
+ </ul>
629
+ </div>
630
+ </div>
631
+
632
+ <script>
633
+ // This script has always been here
634
+ document.getElementById('date').textContent = new Date().toLocaleDateString();
635
+
636
+ setInterval(() => {
637
+ document.getElementById('credit').textContent =
638
+ contributors[Math.floor(Math.random() * contributors.length)];
639
+ }, 7000);
640
+
641
+ // Flash warning behavior
642
+ setTimeout(() => {
643
+ const reminder = document.createElement('div');
644
+ reminder.className = 'flash-warning';
645
+ reminder.textContent = 'You have been reading for quite some time. Are you sure you haven\'t seen this before?';
646
+ reminder.style.animation = 'flashWarning 15s ease-in-out forwards';
647
+ document.body.appendChild(reminder);
648
+
649
+ setInterval(() => {
650
+ if(Math.random() > 0.9) {
651
+ document.body.appendChild(reminder.cloneNode(true));
652
+ }
653
+ }, 45000);
654
+ }, 30000);
655
+
656
+ // Make cursor behave strangely
657
+ document.addEventListener('mousemove', (e) => {
658
+ if(Math.random() > 0.98) {
659
+ document.documentElement.style.cursor = 'wait';
660
+ setTimeout(() => {
661
+ document.documentElement.style.cursor = '';
662
+ }, 50);
663
+ }
664
+ });
665
+
666
+ // Randomly shift sections when not looking
667
+ setInterval(() => {
668
+ if(document.hidden) {
669
+ document.querySelectorAll('.shifty-section').forEach(section => {
670
+ section.style.transform = `translateX(${Math.random() > 0.5 ? '' : '-'}${Math.random() * 5}px)`;
671
+ });
672
+ }
673
+ }, 1500);
674
+ </script>
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 1024000,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": null,
21
+ "tie_word_embeddings": false,
22
+ "tokenizer": {
23
+ "add_bos_token": true,
24
+ "add_eos_token": false,
25
+ "pad_token": "</s>",
26
+ "padding_side": "right"
27
+ },
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.50.3",
30
+ "trust_remote_code": true,
31
+ "use_cache": false,
32
+ "vocab_size": 131072,
33
+ "quantization_config": {
34
+ "quant_method": "exl3",
35
+ "version": "0.0.2",
36
+ "bits": 8.0,
37
+ "head_bits": 8,
38
+ "calibration": {
39
+ "rows": 100,
40
+ "cols": 2048
41
+ },
42
+ "out_scales": "auto"
43
+ }
44
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.50.3"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c7534b564043f6b8a852814c887486c3b4d735f4da0a7f7dd318a56f718e037
3
+ size 8435782664
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3adba66ade060daccd24622ca0665c2cc4020d7c32c82bfae0ad1cd3f743bf27
3
+ size 4491003864
model.safetensors.index.json ADDED
@@ -0,0 +1,932 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12926685184
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
33
+ "model.layers.1.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
34
+ "model.layers.1.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
35
+ "model.layers.1.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
36
+ "model.layers.1.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
37
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.1.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
39
+ "model.layers.1.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
40
+ "model.layers.1.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
53
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.2.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
55
+ "model.layers.2.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
56
+ "model.layers.2.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
57
+ "model.layers.2.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
58
+ "model.layers.2.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
59
+ "model.layers.2.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
60
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.2.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
62
+ "model.layers.2.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
63
+ "model.layers.2.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
64
+ "model.layers.2.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
65
+ "model.layers.2.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
66
+ "model.layers.2.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
67
+ "model.layers.2.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
68
+ "model.layers.2.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
69
+ "model.layers.2.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
70
+ "model.layers.2.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
71
+ "model.layers.2.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
72
+ "model.layers.2.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
73
+ "model.layers.2.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
74
+ "model.layers.2.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
75
+ "model.layers.2.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
76
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.3.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
78
+ "model.layers.3.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
79
+ "model.layers.3.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
80
+ "model.layers.3.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
81
+ "model.layers.3.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
82
+ "model.layers.3.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
83
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.3.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
85
+ "model.layers.3.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
86
+ "model.layers.3.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
87
+ "model.layers.3.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
88
+ "model.layers.3.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
89
+ "model.layers.3.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
90
+ "model.layers.3.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
91
+ "model.layers.3.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
92
+ "model.layers.3.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
93
+ "model.layers.3.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
94
+ "model.layers.3.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
95
+ "model.layers.3.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
96
+ "model.layers.3.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
97
+ "model.layers.3.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
98
+ "model.layers.3.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
99
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.4.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
101
+ "model.layers.4.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
102
+ "model.layers.4.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
103
+ "model.layers.4.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
104
+ "model.layers.4.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
105
+ "model.layers.4.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
106
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.4.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
108
+ "model.layers.4.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
109
+ "model.layers.4.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
110
+ "model.layers.4.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
111
+ "model.layers.4.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
112
+ "model.layers.4.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
113
+ "model.layers.4.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
114
+ "model.layers.4.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
115
+ "model.layers.4.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
116
+ "model.layers.4.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
117
+ "model.layers.4.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
118
+ "model.layers.4.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
119
+ "model.layers.4.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
120
+ "model.layers.4.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
121
+ "model.layers.4.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
122
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.5.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
124
+ "model.layers.5.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
125
+ "model.layers.5.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
126
+ "model.layers.5.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
127
+ "model.layers.5.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
128
+ "model.layers.5.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
129
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.5.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
131
+ "model.layers.5.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
132
+ "model.layers.5.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
133
+ "model.layers.5.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
134
+ "model.layers.5.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
135
+ "model.layers.5.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
136
+ "model.layers.5.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
137
+ "model.layers.5.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
138
+ "model.layers.5.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
139
+ "model.layers.5.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
140
+ "model.layers.5.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
141
+ "model.layers.5.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
142
+ "model.layers.5.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
143
+ "model.layers.5.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
144
+ "model.layers.5.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
145
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.6.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
147
+ "model.layers.6.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
148
+ "model.layers.6.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
149
+ "model.layers.6.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
150
+ "model.layers.6.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
151
+ "model.layers.6.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
152
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.6.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
154
+ "model.layers.6.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
155
+ "model.layers.6.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
156
+ "model.layers.6.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
157
+ "model.layers.6.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
158
+ "model.layers.6.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
159
+ "model.layers.6.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
160
+ "model.layers.6.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
161
+ "model.layers.6.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
162
+ "model.layers.6.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
163
+ "model.layers.6.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
164
+ "model.layers.6.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
165
+ "model.layers.6.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
166
+ "model.layers.6.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
167
+ "model.layers.6.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
168
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.7.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
170
+ "model.layers.7.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
171
+ "model.layers.7.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
172
+ "model.layers.7.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
173
+ "model.layers.7.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
174
+ "model.layers.7.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
175
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.7.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
177
+ "model.layers.7.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
178
+ "model.layers.7.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
179
+ "model.layers.7.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
180
+ "model.layers.7.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
181
+ "model.layers.7.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
187
+ "model.layers.7.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
188
+ "model.layers.7.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
189
+ "model.layers.7.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
190
+ "model.layers.7.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
193
+ "model.layers.8.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
194
+ "model.layers.8.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
195
+ "model.layers.8.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
196
+ "model.layers.8.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
197
+ "model.layers.8.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
198
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.8.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
200
+ "model.layers.8.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
201
+ "model.layers.8.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
202
+ "model.layers.8.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
203
+ "model.layers.8.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
204
+ "model.layers.8.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
205
+ "model.layers.8.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
206
+ "model.layers.8.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
207
+ "model.layers.8.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
208
+ "model.layers.8.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
209
+ "model.layers.8.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
210
+ "model.layers.8.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
211
+ "model.layers.8.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
212
+ "model.layers.8.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
213
+ "model.layers.8.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
214
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.9.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
216
+ "model.layers.9.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
217
+ "model.layers.9.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
218
+ "model.layers.9.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
219
+ "model.layers.9.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
220
+ "model.layers.9.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
221
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.9.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
223
+ "model.layers.9.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
224
+ "model.layers.9.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
225
+ "model.layers.9.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
226
+ "model.layers.9.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
227
+ "model.layers.9.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
228
+ "model.layers.9.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
229
+ "model.layers.9.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
230
+ "model.layers.9.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
231
+ "model.layers.9.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
232
+ "model.layers.9.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
233
+ "model.layers.9.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
234
+ "model.layers.9.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
235
+ "model.layers.9.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
236
+ "model.layers.9.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
237
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.10.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
239
+ "model.layers.10.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
240
+ "model.layers.10.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
241
+ "model.layers.10.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
242
+ "model.layers.10.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
243
+ "model.layers.10.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
244
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.10.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
246
+ "model.layers.10.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
247
+ "model.layers.10.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
248
+ "model.layers.10.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
249
+ "model.layers.10.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
250
+ "model.layers.10.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
251
+ "model.layers.10.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
252
+ "model.layers.10.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
253
+ "model.layers.10.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
254
+ "model.layers.10.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
255
+ "model.layers.10.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
256
+ "model.layers.10.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
257
+ "model.layers.10.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
258
+ "model.layers.10.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
259
+ "model.layers.10.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
260
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.11.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
262
+ "model.layers.11.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
263
+ "model.layers.11.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
264
+ "model.layers.11.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
265
+ "model.layers.11.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
266
+ "model.layers.11.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
267
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.11.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
269
+ "model.layers.11.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
270
+ "model.layers.11.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
271
+ "model.layers.11.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
272
+ "model.layers.11.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
273
+ "model.layers.11.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
274
+ "model.layers.11.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
275
+ "model.layers.11.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
276
+ "model.layers.11.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
277
+ "model.layers.11.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
278
+ "model.layers.11.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
279
+ "model.layers.11.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
280
+ "model.layers.11.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
281
+ "model.layers.11.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
282
+ "model.layers.11.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
283
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.12.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
285
+ "model.layers.12.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
286
+ "model.layers.12.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
287
+ "model.layers.12.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
288
+ "model.layers.12.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
289
+ "model.layers.12.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
290
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.12.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
292
+ "model.layers.12.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
293
+ "model.layers.12.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
294
+ "model.layers.12.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
295
+ "model.layers.12.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
296
+ "model.layers.12.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
297
+ "model.layers.12.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
298
+ "model.layers.12.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
299
+ "model.layers.12.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
300
+ "model.layers.12.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
301
+ "model.layers.12.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
302
+ "model.layers.12.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
303
+ "model.layers.12.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
304
+ "model.layers.12.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
305
+ "model.layers.12.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
306
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.13.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
308
+ "model.layers.13.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
309
+ "model.layers.13.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
310
+ "model.layers.13.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
311
+ "model.layers.13.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
312
+ "model.layers.13.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
313
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.13.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
315
+ "model.layers.13.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
316
+ "model.layers.13.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
317
+ "model.layers.13.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
318
+ "model.layers.13.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
319
+ "model.layers.13.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
320
+ "model.layers.13.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
321
+ "model.layers.13.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
322
+ "model.layers.13.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
323
+ "model.layers.13.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
324
+ "model.layers.13.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
325
+ "model.layers.13.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
326
+ "model.layers.13.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
327
+ "model.layers.13.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
328
+ "model.layers.13.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
329
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
330
+ "model.layers.14.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
331
+ "model.layers.14.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
332
+ "model.layers.14.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
333
+ "model.layers.14.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
334
+ "model.layers.14.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
335
+ "model.layers.14.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
336
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.14.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
338
+ "model.layers.14.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
339
+ "model.layers.14.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
340
+ "model.layers.14.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
341
+ "model.layers.14.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
342
+ "model.layers.14.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
343
+ "model.layers.14.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
344
+ "model.layers.14.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
345
+ "model.layers.14.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
346
+ "model.layers.14.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
347
+ "model.layers.14.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
348
+ "model.layers.14.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
349
+ "model.layers.14.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
350
+ "model.layers.14.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
351
+ "model.layers.14.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
352
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
353
+ "model.layers.15.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
354
+ "model.layers.15.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
355
+ "model.layers.15.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
356
+ "model.layers.15.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
357
+ "model.layers.15.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
358
+ "model.layers.15.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
359
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
360
+ "model.layers.15.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
361
+ "model.layers.15.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
362
+ "model.layers.15.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
363
+ "model.layers.15.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
364
+ "model.layers.15.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
365
+ "model.layers.15.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
366
+ "model.layers.15.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
367
+ "model.layers.15.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
368
+ "model.layers.15.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
369
+ "model.layers.15.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
370
+ "model.layers.15.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
371
+ "model.layers.15.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
372
+ "model.layers.15.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
373
+ "model.layers.15.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
374
+ "model.layers.15.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
375
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.16.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
377
+ "model.layers.16.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
378
+ "model.layers.16.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
379
+ "model.layers.16.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
380
+ "model.layers.16.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
381
+ "model.layers.16.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
382
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.16.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
384
+ "model.layers.16.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
385
+ "model.layers.16.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
386
+ "model.layers.16.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
387
+ "model.layers.16.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
388
+ "model.layers.16.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
389
+ "model.layers.16.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
390
+ "model.layers.16.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
391
+ "model.layers.16.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
392
+ "model.layers.16.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
393
+ "model.layers.16.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
394
+ "model.layers.16.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
395
+ "model.layers.16.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
396
+ "model.layers.16.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
397
+ "model.layers.16.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
398
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.17.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
400
+ "model.layers.17.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
401
+ "model.layers.17.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
402
+ "model.layers.17.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
403
+ "model.layers.17.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
404
+ "model.layers.17.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
405
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.17.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
407
+ "model.layers.17.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
408
+ "model.layers.17.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
409
+ "model.layers.17.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
410
+ "model.layers.17.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
411
+ "model.layers.17.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
412
+ "model.layers.17.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
413
+ "model.layers.17.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
414
+ "model.layers.17.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
415
+ "model.layers.17.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
416
+ "model.layers.17.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
417
+ "model.layers.17.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
418
+ "model.layers.17.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
419
+ "model.layers.17.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
420
+ "model.layers.17.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
421
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.18.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
423
+ "model.layers.18.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
424
+ "model.layers.18.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
425
+ "model.layers.18.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
426
+ "model.layers.18.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
427
+ "model.layers.18.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
428
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.18.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
430
+ "model.layers.18.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
431
+ "model.layers.18.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
432
+ "model.layers.18.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
433
+ "model.layers.18.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
434
+ "model.layers.18.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
435
+ "model.layers.18.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
436
+ "model.layers.18.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
437
+ "model.layers.18.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
438
+ "model.layers.18.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
439
+ "model.layers.18.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
440
+ "model.layers.18.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
441
+ "model.layers.18.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
442
+ "model.layers.18.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
443
+ "model.layers.18.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
444
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.19.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
446
+ "model.layers.19.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
447
+ "model.layers.19.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
448
+ "model.layers.19.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
449
+ "model.layers.19.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
450
+ "model.layers.19.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
451
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
452
+ "model.layers.19.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
453
+ "model.layers.19.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
454
+ "model.layers.19.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
455
+ "model.layers.19.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
456
+ "model.layers.19.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
457
+ "model.layers.19.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
458
+ "model.layers.19.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
459
+ "model.layers.19.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
460
+ "model.layers.19.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
461
+ "model.layers.19.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
462
+ "model.layers.19.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
463
+ "model.layers.19.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
464
+ "model.layers.19.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
465
+ "model.layers.19.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
466
+ "model.layers.19.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
467
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
468
+ "model.layers.20.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
469
+ "model.layers.20.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
470
+ "model.layers.20.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
471
+ "model.layers.20.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
472
+ "model.layers.20.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
473
+ "model.layers.20.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
474
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.20.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
476
+ "model.layers.20.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
477
+ "model.layers.20.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
478
+ "model.layers.20.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
479
+ "model.layers.20.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
480
+ "model.layers.20.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
481
+ "model.layers.20.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
482
+ "model.layers.20.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
483
+ "model.layers.20.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
484
+ "model.layers.20.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
485
+ "model.layers.20.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
486
+ "model.layers.20.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
487
+ "model.layers.20.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
488
+ "model.layers.20.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
489
+ "model.layers.20.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
490
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
491
+ "model.layers.21.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
492
+ "model.layers.21.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
493
+ "model.layers.21.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
494
+ "model.layers.21.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
495
+ "model.layers.21.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
496
+ "model.layers.21.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
497
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
498
+ "model.layers.21.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
499
+ "model.layers.21.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
500
+ "model.layers.21.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
501
+ "model.layers.21.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
502
+ "model.layers.21.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
503
+ "model.layers.21.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
504
+ "model.layers.21.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
505
+ "model.layers.21.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
506
+ "model.layers.21.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
507
+ "model.layers.21.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
508
+ "model.layers.21.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
509
+ "model.layers.21.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
510
+ "model.layers.21.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
511
+ "model.layers.21.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
512
+ "model.layers.21.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
513
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
514
+ "model.layers.22.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
515
+ "model.layers.22.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
516
+ "model.layers.22.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
517
+ "model.layers.22.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
518
+ "model.layers.22.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
519
+ "model.layers.22.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
520
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
521
+ "model.layers.22.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
522
+ "model.layers.22.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
523
+ "model.layers.22.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
524
+ "model.layers.22.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
525
+ "model.layers.22.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
526
+ "model.layers.22.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
527
+ "model.layers.22.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
528
+ "model.layers.22.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
529
+ "model.layers.22.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
530
+ "model.layers.22.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
531
+ "model.layers.22.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
532
+ "model.layers.22.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
533
+ "model.layers.22.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
534
+ "model.layers.22.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
535
+ "model.layers.22.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
536
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
537
+ "model.layers.23.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
538
+ "model.layers.23.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
539
+ "model.layers.23.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
540
+ "model.layers.23.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
541
+ "model.layers.23.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
542
+ "model.layers.23.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
543
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
544
+ "model.layers.23.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
545
+ "model.layers.23.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
546
+ "model.layers.23.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
547
+ "model.layers.23.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
548
+ "model.layers.23.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
549
+ "model.layers.23.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
550
+ "model.layers.23.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
551
+ "model.layers.23.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
552
+ "model.layers.23.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
553
+ "model.layers.23.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
554
+ "model.layers.23.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
555
+ "model.layers.23.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
556
+ "model.layers.23.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
557
+ "model.layers.23.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
558
+ "model.layers.23.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
559
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
560
+ "model.layers.24.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
561
+ "model.layers.24.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
562
+ "model.layers.24.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
563
+ "model.layers.24.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
564
+ "model.layers.24.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
565
+ "model.layers.24.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
566
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
567
+ "model.layers.24.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
568
+ "model.layers.24.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
569
+ "model.layers.24.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
570
+ "model.layers.24.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
571
+ "model.layers.24.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
572
+ "model.layers.24.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
573
+ "model.layers.24.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
574
+ "model.layers.24.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
575
+ "model.layers.24.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
576
+ "model.layers.24.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
577
+ "model.layers.24.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
578
+ "model.layers.24.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
579
+ "model.layers.24.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
580
+ "model.layers.24.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
581
+ "model.layers.24.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
582
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
583
+ "model.layers.25.mlp.down_proj.suh": "model-00001-of-00002.safetensors",
584
+ "model.layers.25.mlp.down_proj.svh": "model-00001-of-00002.safetensors",
585
+ "model.layers.25.mlp.gate_proj.suh": "model-00001-of-00002.safetensors",
586
+ "model.layers.25.mlp.gate_proj.svh": "model-00001-of-00002.safetensors",
587
+ "model.layers.25.mlp.up_proj.suh": "model-00001-of-00002.safetensors",
588
+ "model.layers.25.mlp.up_proj.svh": "model-00001-of-00002.safetensors",
589
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
590
+ "model.layers.25.self_attn.k_proj.suh": "model-00001-of-00002.safetensors",
591
+ "model.layers.25.self_attn.k_proj.svh": "model-00001-of-00002.safetensors",
592
+ "model.layers.25.self_attn.o_proj.suh": "model-00001-of-00002.safetensors",
593
+ "model.layers.25.self_attn.o_proj.svh": "model-00001-of-00002.safetensors",
594
+ "model.layers.25.self_attn.q_proj.suh": "model-00001-of-00002.safetensors",
595
+ "model.layers.25.self_attn.q_proj.svh": "model-00001-of-00002.safetensors",
596
+ "model.layers.25.self_attn.v_proj.suh": "model-00001-of-00002.safetensors",
597
+ "model.layers.25.self_attn.v_proj.svh": "model-00001-of-00002.safetensors",
598
+ "model.layers.25.mlp.down_proj.trellis": "model-00001-of-00002.safetensors",
599
+ "model.layers.25.mlp.gate_proj.trellis": "model-00001-of-00002.safetensors",
600
+ "model.layers.25.mlp.up_proj.trellis": "model-00001-of-00002.safetensors",
601
+ "model.layers.25.self_attn.k_proj.trellis": "model-00001-of-00002.safetensors",
602
+ "model.layers.25.self_attn.o_proj.trellis": "model-00001-of-00002.safetensors",
603
+ "model.layers.25.self_attn.q_proj.trellis": "model-00001-of-00002.safetensors",
604
+ "model.layers.25.self_attn.v_proj.trellis": "model-00001-of-00002.safetensors",
605
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
606
+ "model.layers.26.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
607
+ "model.layers.26.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
608
+ "model.layers.26.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
609
+ "model.layers.26.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
610
+ "model.layers.26.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
611
+ "model.layers.26.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
612
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
613
+ "model.layers.26.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
614
+ "model.layers.26.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
615
+ "model.layers.26.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
616
+ "model.layers.26.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
617
+ "model.layers.26.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
618
+ "model.layers.26.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
619
+ "model.layers.26.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
620
+ "model.layers.26.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
621
+ "model.layers.26.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
622
+ "model.layers.26.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
623
+ "model.layers.26.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
624
+ "model.layers.26.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
625
+ "model.layers.26.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
626
+ "model.layers.26.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
627
+ "model.layers.26.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
628
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
629
+ "model.layers.27.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
630
+ "model.layers.27.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
631
+ "model.layers.27.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
632
+ "model.layers.27.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
633
+ "model.layers.27.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
634
+ "model.layers.27.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
635
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
636
+ "model.layers.27.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
637
+ "model.layers.27.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
638
+ "model.layers.27.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
639
+ "model.layers.27.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
640
+ "model.layers.27.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
641
+ "model.layers.27.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
642
+ "model.layers.27.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
643
+ "model.layers.27.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
644
+ "model.layers.27.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
645
+ "model.layers.27.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
646
+ "model.layers.27.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
647
+ "model.layers.27.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
648
+ "model.layers.27.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
649
+ "model.layers.27.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
650
+ "model.layers.27.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
651
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
652
+ "model.layers.28.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
653
+ "model.layers.28.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
654
+ "model.layers.28.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
655
+ "model.layers.28.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
656
+ "model.layers.28.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
657
+ "model.layers.28.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
658
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
659
+ "model.layers.28.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
660
+ "model.layers.28.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
661
+ "model.layers.28.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
662
+ "model.layers.28.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
663
+ "model.layers.28.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
664
+ "model.layers.28.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
665
+ "model.layers.28.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
666
+ "model.layers.28.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
667
+ "model.layers.28.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
668
+ "model.layers.28.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
669
+ "model.layers.28.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
670
+ "model.layers.28.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
671
+ "model.layers.28.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
672
+ "model.layers.28.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
673
+ "model.layers.28.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
674
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
675
+ "model.layers.29.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
676
+ "model.layers.29.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
677
+ "model.layers.29.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
678
+ "model.layers.29.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
679
+ "model.layers.29.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
680
+ "model.layers.29.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
681
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
682
+ "model.layers.29.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
683
+ "model.layers.29.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
684
+ "model.layers.29.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
685
+ "model.layers.29.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
686
+ "model.layers.29.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
687
+ "model.layers.29.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
688
+ "model.layers.29.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
689
+ "model.layers.29.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
690
+ "model.layers.29.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
691
+ "model.layers.29.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
692
+ "model.layers.29.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
693
+ "model.layers.29.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
694
+ "model.layers.29.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
695
+ "model.layers.29.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
696
+ "model.layers.29.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
697
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
698
+ "model.layers.30.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
699
+ "model.layers.30.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
700
+ "model.layers.30.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
701
+ "model.layers.30.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
702
+ "model.layers.30.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
703
+ "model.layers.30.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
704
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
705
+ "model.layers.30.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
706
+ "model.layers.30.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
707
+ "model.layers.30.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
708
+ "model.layers.30.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
709
+ "model.layers.30.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
710
+ "model.layers.30.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
711
+ "model.layers.30.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
712
+ "model.layers.30.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
713
+ "model.layers.30.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
714
+ "model.layers.30.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
715
+ "model.layers.30.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
716
+ "model.layers.30.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
717
+ "model.layers.30.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
718
+ "model.layers.30.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
719
+ "model.layers.30.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
720
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
721
+ "model.layers.31.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
722
+ "model.layers.31.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
723
+ "model.layers.31.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
724
+ "model.layers.31.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
725
+ "model.layers.31.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
726
+ "model.layers.31.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
727
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
728
+ "model.layers.31.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
729
+ "model.layers.31.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
730
+ "model.layers.31.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
731
+ "model.layers.31.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
732
+ "model.layers.31.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
733
+ "model.layers.31.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
734
+ "model.layers.31.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
735
+ "model.layers.31.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
736
+ "model.layers.31.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
737
+ "model.layers.31.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
738
+ "model.layers.31.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
739
+ "model.layers.31.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
740
+ "model.layers.31.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
741
+ "model.layers.31.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
742
+ "model.layers.31.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
743
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
744
+ "model.layers.32.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
745
+ "model.layers.32.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
746
+ "model.layers.32.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
747
+ "model.layers.32.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
748
+ "model.layers.32.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
749
+ "model.layers.32.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
750
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
751
+ "model.layers.32.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
752
+ "model.layers.32.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
753
+ "model.layers.32.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
754
+ "model.layers.32.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
755
+ "model.layers.32.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
756
+ "model.layers.32.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
757
+ "model.layers.32.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
758
+ "model.layers.32.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
759
+ "model.layers.32.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
760
+ "model.layers.32.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
761
+ "model.layers.32.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
762
+ "model.layers.32.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
763
+ "model.layers.32.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
764
+ "model.layers.32.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
765
+ "model.layers.32.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
766
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
767
+ "model.layers.33.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
768
+ "model.layers.33.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
769
+ "model.layers.33.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
770
+ "model.layers.33.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
771
+ "model.layers.33.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
772
+ "model.layers.33.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
773
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
774
+ "model.layers.33.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
775
+ "model.layers.33.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
776
+ "model.layers.33.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
777
+ "model.layers.33.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
778
+ "model.layers.33.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
779
+ "model.layers.33.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
780
+ "model.layers.33.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
781
+ "model.layers.33.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
782
+ "model.layers.33.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
783
+ "model.layers.33.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
784
+ "model.layers.33.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
785
+ "model.layers.33.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
786
+ "model.layers.33.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
787
+ "model.layers.33.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
788
+ "model.layers.33.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
789
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
790
+ "model.layers.34.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
791
+ "model.layers.34.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
792
+ "model.layers.34.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
793
+ "model.layers.34.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
794
+ "model.layers.34.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
795
+ "model.layers.34.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
796
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
797
+ "model.layers.34.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
798
+ "model.layers.34.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
799
+ "model.layers.34.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
800
+ "model.layers.34.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
801
+ "model.layers.34.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
802
+ "model.layers.34.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
803
+ "model.layers.34.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
804
+ "model.layers.34.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
805
+ "model.layers.34.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
806
+ "model.layers.34.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
807
+ "model.layers.34.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
808
+ "model.layers.34.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
809
+ "model.layers.34.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
810
+ "model.layers.34.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
811
+ "model.layers.34.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
812
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
813
+ "model.layers.35.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
814
+ "model.layers.35.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
815
+ "model.layers.35.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
816
+ "model.layers.35.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
817
+ "model.layers.35.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
818
+ "model.layers.35.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
819
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
820
+ "model.layers.35.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
821
+ "model.layers.35.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
822
+ "model.layers.35.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
823
+ "model.layers.35.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
824
+ "model.layers.35.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
825
+ "model.layers.35.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
826
+ "model.layers.35.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
827
+ "model.layers.35.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
828
+ "model.layers.35.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
829
+ "model.layers.35.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
830
+ "model.layers.35.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
831
+ "model.layers.35.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
832
+ "model.layers.35.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
833
+ "model.layers.35.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
834
+ "model.layers.35.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
835
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
836
+ "model.layers.36.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
837
+ "model.layers.36.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
838
+ "model.layers.36.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
839
+ "model.layers.36.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
840
+ "model.layers.36.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
841
+ "model.layers.36.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
842
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
843
+ "model.layers.36.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
844
+ "model.layers.36.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
845
+ "model.layers.36.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
846
+ "model.layers.36.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
847
+ "model.layers.36.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
848
+ "model.layers.36.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
849
+ "model.layers.36.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
850
+ "model.layers.36.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
851
+ "model.layers.36.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
852
+ "model.layers.36.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
853
+ "model.layers.36.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
854
+ "model.layers.36.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
855
+ "model.layers.36.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
856
+ "model.layers.36.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
857
+ "model.layers.36.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
858
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
859
+ "model.layers.37.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
860
+ "model.layers.37.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
861
+ "model.layers.37.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
862
+ "model.layers.37.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
863
+ "model.layers.37.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
864
+ "model.layers.37.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
865
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
866
+ "model.layers.37.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
867
+ "model.layers.37.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
868
+ "model.layers.37.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
869
+ "model.layers.37.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
870
+ "model.layers.37.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
871
+ "model.layers.37.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
872
+ "model.layers.37.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
873
+ "model.layers.37.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
874
+ "model.layers.37.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
875
+ "model.layers.37.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
876
+ "model.layers.37.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
877
+ "model.layers.37.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
878
+ "model.layers.37.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
879
+ "model.layers.37.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
880
+ "model.layers.37.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
881
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
882
+ "model.layers.38.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
883
+ "model.layers.38.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
884
+ "model.layers.38.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
885
+ "model.layers.38.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
886
+ "model.layers.38.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
887
+ "model.layers.38.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
888
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
889
+ "model.layers.38.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
890
+ "model.layers.38.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
891
+ "model.layers.38.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
892
+ "model.layers.38.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
893
+ "model.layers.38.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
894
+ "model.layers.38.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
895
+ "model.layers.38.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
896
+ "model.layers.38.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
897
+ "model.layers.38.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
898
+ "model.layers.38.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
899
+ "model.layers.38.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
900
+ "model.layers.38.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
901
+ "model.layers.38.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
902
+ "model.layers.38.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
903
+ "model.layers.38.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
904
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
905
+ "model.layers.39.mlp.down_proj.suh": "model-00002-of-00002.safetensors",
906
+ "model.layers.39.mlp.down_proj.svh": "model-00002-of-00002.safetensors",
907
+ "model.layers.39.mlp.gate_proj.suh": "model-00002-of-00002.safetensors",
908
+ "model.layers.39.mlp.gate_proj.svh": "model-00002-of-00002.safetensors",
909
+ "model.layers.39.mlp.up_proj.suh": "model-00002-of-00002.safetensors",
910
+ "model.layers.39.mlp.up_proj.svh": "model-00002-of-00002.safetensors",
911
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
912
+ "model.layers.39.self_attn.k_proj.suh": "model-00002-of-00002.safetensors",
913
+ "model.layers.39.self_attn.k_proj.svh": "model-00002-of-00002.safetensors",
914
+ "model.layers.39.self_attn.o_proj.suh": "model-00002-of-00002.safetensors",
915
+ "model.layers.39.self_attn.o_proj.svh": "model-00002-of-00002.safetensors",
916
+ "model.layers.39.self_attn.q_proj.suh": "model-00002-of-00002.safetensors",
917
+ "model.layers.39.self_attn.q_proj.svh": "model-00002-of-00002.safetensors",
918
+ "model.layers.39.self_attn.v_proj.suh": "model-00002-of-00002.safetensors",
919
+ "model.layers.39.self_attn.v_proj.svh": "model-00002-of-00002.safetensors",
920
+ "model.layers.39.mlp.down_proj.trellis": "model-00002-of-00002.safetensors",
921
+ "model.layers.39.mlp.gate_proj.trellis": "model-00002-of-00002.safetensors",
922
+ "model.layers.39.mlp.up_proj.trellis": "model-00002-of-00002.safetensors",
923
+ "model.layers.39.self_attn.k_proj.trellis": "model-00002-of-00002.safetensors",
924
+ "model.layers.39.self_attn.o_proj.trellis": "model-00002-of-00002.safetensors",
925
+ "model.layers.39.self_attn.q_proj.trellis": "model-00002-of-00002.safetensors",
926
+ "model.layers.39.self_attn.v_proj.trellis": "model-00002-of-00002.safetensors",
927
+ "model.norm.weight": "model-00002-of-00002.safetensors",
928
+ "lm_head.suh": "model-00002-of-00002.safetensors",
929
+ "lm_head.svh": "model-00002-of-00002.safetensors",
930
+ "lm_head.trellis": "model-00002-of-00002.safetensors"
931
+ }
932
+ }
quantization_config.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
3
+ size 17078292
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff