win10 commited on
Commit
db844ea
·
verified ·
1 Parent(s): 55948b3

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
chat_template.jinja ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- if tools -%}
3
+ <|system|>
4
+ 你是一个名为 ChatGLM 的人工智能助手。你是基于智谱 AI 公司训练的语言模型 GLM-4 模型开发的,你的任务是针对用户的问题和要求提供适当的答复和支持。
5
+
6
+ # 可用工具
7
+ {%- for tool in tools %}
8
+ {%- set function = tool.function if tool.get("function") else tool %}
9
+
10
+ ## {{ function.name }}
11
+
12
+ {{ function | tojson(indent=4, ensure_ascii=False) }}
13
+ 在调用上述函数时,请使用 Json 格式表示调用的参数。
14
+ {%- endfor %}
15
+ {%- endif -%}
16
+
17
+ {%- for msg in messages %}
18
+ {%- if msg.role == 'system' %}
19
+ <|system|>
20
+ {{ msg.content }}
21
+ {%- endif %}
22
+ {%- endfor %}
23
+
24
+ {%- for message in messages if message.role != 'system' %}
25
+ {%- set role = message['role'] %}
26
+ {%- set content = message['content'] %}
27
+ {%- set visible = content.split('</think>')[-1].strip() %}
28
+ {%- set meta = message.get("metadata", "") %}
29
+
30
+ {%- if role == 'user' %}
31
+ <|user|>
32
+ {{ visible }}
33
+ {%- elif role == 'assistant' and not meta %}
34
+ <|assistant|>
35
+ {{ visible }}
36
+ {%- elif role == 'assistant' and meta %}
37
+ <|assistant|>{{ meta }}
38
+ {{ visible }}
39
+ {%- elif role == 'observation' %}
40
+ <|observation|>
41
+ {{ visible }}
42
+ {%- endif %}
43
+ {%- endfor %}
44
+ {% if add_generation_prompt %}<|assistant|>\n<think>{% endif %}
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Glm4ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": [
9
+ 151329,
10
+ 151336,
11
+ 151338
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 6144,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 23040,
18
+ "max_position_embeddings": 32768,
19
+ "model_type": "glm4",
20
+ "num_attention_heads": 48,
21
+ "num_hidden_layers": 104,
22
+ "num_key_value_heads": 2,
23
+ "pad_token_id": 151329,
24
+ "partial_rotary_factor": 0.5,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_theta": 10000.0,
27
+ "tie_word_embeddings": false,
28
+ "transformers_version": "4.57.1",
29
+ "use_cache": true,
30
+ "vocab_size": 151552
31
+ }
merge_plan.json ADDED
@@ -0,0 +1,534 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "main_model": "E:\\text-generation-webui-1.14\\user_data\\models\\GLM-Z1-32B-0414",
3
+ "sub_model": "E:\\text-generation-webui-1.14\\user_data\\models\\GLM-4-32B-0414",
4
+ "main_layers": 61,
5
+ "sub_layers": 61,
6
+ "output_layers": 104,
7
+ "main_vocab": 151552,
8
+ "sub_vocab": 151552,
9
+ "output_vocab": 151552,
10
+ "merge_strategy": "dus",
11
+ "chunk_size": null,
12
+ "plan": [
13
+ {
14
+ "out_layer": 0,
15
+ "src": "main",
16
+ "src_layer": 0
17
+ },
18
+ {
19
+ "out_layer": 1,
20
+ "src": "main",
21
+ "src_layer": 1
22
+ },
23
+ {
24
+ "out_layer": 2,
25
+ "src": "main",
26
+ "src_layer": 2
27
+ },
28
+ {
29
+ "out_layer": 3,
30
+ "src": "main",
31
+ "src_layer": 3
32
+ },
33
+ {
34
+ "out_layer": 4,
35
+ "src": "main",
36
+ "src_layer": 4
37
+ },
38
+ {
39
+ "out_layer": 5,
40
+ "src": "main",
41
+ "src_layer": 5
42
+ },
43
+ {
44
+ "out_layer": 6,
45
+ "src": "main",
46
+ "src_layer": 6
47
+ },
48
+ {
49
+ "out_layer": 7,
50
+ "src": "main",
51
+ "src_layer": 7
52
+ },
53
+ {
54
+ "out_layer": 8,
55
+ "src": "main",
56
+ "src_layer": 8
57
+ },
58
+ {
59
+ "out_layer": 9,
60
+ "src": "main",
61
+ "src_layer": 9
62
+ },
63
+ {
64
+ "out_layer": 10,
65
+ "src": "main",
66
+ "src_layer": 10
67
+ },
68
+ {
69
+ "out_layer": 11,
70
+ "src": "main",
71
+ "src_layer": 11
72
+ },
73
+ {
74
+ "out_layer": 12,
75
+ "src": "main",
76
+ "src_layer": 12
77
+ },
78
+ {
79
+ "out_layer": 13,
80
+ "src": "main",
81
+ "src_layer": 13
82
+ },
83
+ {
84
+ "out_layer": 14,
85
+ "src": "main",
86
+ "src_layer": 14
87
+ },
88
+ {
89
+ "out_layer": 15,
90
+ "src": "main",
91
+ "src_layer": 15
92
+ },
93
+ {
94
+ "out_layer": 16,
95
+ "src": "main",
96
+ "src_layer": 16
97
+ },
98
+ {
99
+ "out_layer": 17,
100
+ "src": "main",
101
+ "src_layer": 17
102
+ },
103
+ {
104
+ "out_layer": 18,
105
+ "src": "main",
106
+ "src_layer": 18
107
+ },
108
+ {
109
+ "out_layer": 19,
110
+ "src": "main",
111
+ "src_layer": 19
112
+ },
113
+ {
114
+ "out_layer": 20,
115
+ "src": "main",
116
+ "src_layer": 20
117
+ },
118
+ {
119
+ "out_layer": 21,
120
+ "src": "main",
121
+ "src_layer": 21
122
+ },
123
+ {
124
+ "out_layer": 22,
125
+ "src": "main",
126
+ "src_layer": 22
127
+ },
128
+ {
129
+ "out_layer": 23,
130
+ "src": "main",
131
+ "src_layer": 23
132
+ },
133
+ {
134
+ "out_layer": 24,
135
+ "src": "main",
136
+ "src_layer": 24
137
+ },
138
+ {
139
+ "out_layer": 25,
140
+ "src": "main",
141
+ "src_layer": 25
142
+ },
143
+ {
144
+ "out_layer": 26,
145
+ "src": "main",
146
+ "src_layer": 26
147
+ },
148
+ {
149
+ "out_layer": 27,
150
+ "src": "main",
151
+ "src_layer": 27
152
+ },
153
+ {
154
+ "out_layer": 28,
155
+ "src": "main",
156
+ "src_layer": 28
157
+ },
158
+ {
159
+ "out_layer": 29,
160
+ "src": "main",
161
+ "src_layer": 29
162
+ },
163
+ {
164
+ "out_layer": 30,
165
+ "src": "main",
166
+ "src_layer": 30
167
+ },
168
+ {
169
+ "out_layer": 31,
170
+ "src": "main",
171
+ "src_layer": 31
172
+ },
173
+ {
174
+ "out_layer": 32,
175
+ "src": "main",
176
+ "src_layer": 32
177
+ },
178
+ {
179
+ "out_layer": 33,
180
+ "src": "main",
181
+ "src_layer": 33
182
+ },
183
+ {
184
+ "out_layer": 34,
185
+ "src": "main",
186
+ "src_layer": 34
187
+ },
188
+ {
189
+ "out_layer": 35,
190
+ "src": "main",
191
+ "src_layer": 35
192
+ },
193
+ {
194
+ "out_layer": 36,
195
+ "src": "main",
196
+ "src_layer": 36
197
+ },
198
+ {
199
+ "out_layer": 37,
200
+ "src": "main",
201
+ "src_layer": 37
202
+ },
203
+ {
204
+ "out_layer": 38,
205
+ "src": "main",
206
+ "src_layer": 38
207
+ },
208
+ {
209
+ "out_layer": 39,
210
+ "src": "main",
211
+ "src_layer": 39
212
+ },
213
+ {
214
+ "out_layer": 40,
215
+ "src": "main",
216
+ "src_layer": 40
217
+ },
218
+ {
219
+ "out_layer": 41,
220
+ "src": "main",
221
+ "src_layer": 41
222
+ },
223
+ {
224
+ "out_layer": 42,
225
+ "src": "main",
226
+ "src_layer": 42
227
+ },
228
+ {
229
+ "out_layer": 43,
230
+ "src": "main",
231
+ "src_layer": 43
232
+ },
233
+ {
234
+ "out_layer": 44,
235
+ "src": "main",
236
+ "src_layer": 44
237
+ },
238
+ {
239
+ "out_layer": 45,
240
+ "src": "main",
241
+ "src_layer": 45
242
+ },
243
+ {
244
+ "out_layer": 46,
245
+ "src": "main",
246
+ "src_layer": 46
247
+ },
248
+ {
249
+ "out_layer": 47,
250
+ "src": "main",
251
+ "src_layer": 47
252
+ },
253
+ {
254
+ "out_layer": 48,
255
+ "src": "main",
256
+ "src_layer": 48
257
+ },
258
+ {
259
+ "out_layer": 49,
260
+ "src": "main",
261
+ "src_layer": 49
262
+ },
263
+ {
264
+ "out_layer": 50,
265
+ "src": "main",
266
+ "src_layer": 50
267
+ },
268
+ {
269
+ "out_layer": 51,
270
+ "src": "main",
271
+ "src_layer": 51
272
+ },
273
+ {
274
+ "out_layer": 52,
275
+ "src": "sub",
276
+ "src_layer": 9
277
+ },
278
+ {
279
+ "out_layer": 53,
280
+ "src": "sub",
281
+ "src_layer": 10
282
+ },
283
+ {
284
+ "out_layer": 54,
285
+ "src": "sub",
286
+ "src_layer": 11
287
+ },
288
+ {
289
+ "out_layer": 55,
290
+ "src": "sub",
291
+ "src_layer": 12
292
+ },
293
+ {
294
+ "out_layer": 56,
295
+ "src": "sub",
296
+ "src_layer": 13
297
+ },
298
+ {
299
+ "out_layer": 57,
300
+ "src": "sub",
301
+ "src_layer": 14
302
+ },
303
+ {
304
+ "out_layer": 58,
305
+ "src": "sub",
306
+ "src_layer": 15
307
+ },
308
+ {
309
+ "out_layer": 59,
310
+ "src": "sub",
311
+ "src_layer": 16
312
+ },
313
+ {
314
+ "out_layer": 60,
315
+ "src": "sub",
316
+ "src_layer": 17
317
+ },
318
+ {
319
+ "out_layer": 61,
320
+ "src": "sub",
321
+ "src_layer": 18
322
+ },
323
+ {
324
+ "out_layer": 62,
325
+ "src": "sub",
326
+ "src_layer": 19
327
+ },
328
+ {
329
+ "out_layer": 63,
330
+ "src": "sub",
331
+ "src_layer": 20
332
+ },
333
+ {
334
+ "out_layer": 64,
335
+ "src": "sub",
336
+ "src_layer": 21
337
+ },
338
+ {
339
+ "out_layer": 65,
340
+ "src": "sub",
341
+ "src_layer": 22
342
+ },
343
+ {
344
+ "out_layer": 66,
345
+ "src": "sub",
346
+ "src_layer": 23
347
+ },
348
+ {
349
+ "out_layer": 67,
350
+ "src": "sub",
351
+ "src_layer": 24
352
+ },
353
+ {
354
+ "out_layer": 68,
355
+ "src": "sub",
356
+ "src_layer": 25
357
+ },
358
+ {
359
+ "out_layer": 69,
360
+ "src": "sub",
361
+ "src_layer": 26
362
+ },
363
+ {
364
+ "out_layer": 70,
365
+ "src": "sub",
366
+ "src_layer": 27
367
+ },
368
+ {
369
+ "out_layer": 71,
370
+ "src": "sub",
371
+ "src_layer": 28
372
+ },
373
+ {
374
+ "out_layer": 72,
375
+ "src": "sub",
376
+ "src_layer": 29
377
+ },
378
+ {
379
+ "out_layer": 73,
380
+ "src": "sub",
381
+ "src_layer": 30
382
+ },
383
+ {
384
+ "out_layer": 74,
385
+ "src": "sub",
386
+ "src_layer": 31
387
+ },
388
+ {
389
+ "out_layer": 75,
390
+ "src": "sub",
391
+ "src_layer": 32
392
+ },
393
+ {
394
+ "out_layer": 76,
395
+ "src": "sub",
396
+ "src_layer": 33
397
+ },
398
+ {
399
+ "out_layer": 77,
400
+ "src": "sub",
401
+ "src_layer": 34
402
+ },
403
+ {
404
+ "out_layer": 78,
405
+ "src": "sub",
406
+ "src_layer": 35
407
+ },
408
+ {
409
+ "out_layer": 79,
410
+ "src": "sub",
411
+ "src_layer": 36
412
+ },
413
+ {
414
+ "out_layer": 80,
415
+ "src": "sub",
416
+ "src_layer": 37
417
+ },
418
+ {
419
+ "out_layer": 81,
420
+ "src": "sub",
421
+ "src_layer": 38
422
+ },
423
+ {
424
+ "out_layer": 82,
425
+ "src": "sub",
426
+ "src_layer": 39
427
+ },
428
+ {
429
+ "out_layer": 83,
430
+ "src": "sub",
431
+ "src_layer": 40
432
+ },
433
+ {
434
+ "out_layer": 84,
435
+ "src": "sub",
436
+ "src_layer": 41
437
+ },
438
+ {
439
+ "out_layer": 85,
440
+ "src": "sub",
441
+ "src_layer": 42
442
+ },
443
+ {
444
+ "out_layer": 86,
445
+ "src": "sub",
446
+ "src_layer": 43
447
+ },
448
+ {
449
+ "out_layer": 87,
450
+ "src": "sub",
451
+ "src_layer": 44
452
+ },
453
+ {
454
+ "out_layer": 88,
455
+ "src": "sub",
456
+ "src_layer": 45
457
+ },
458
+ {
459
+ "out_layer": 89,
460
+ "src": "sub",
461
+ "src_layer": 46
462
+ },
463
+ {
464
+ "out_layer": 90,
465
+ "src": "sub",
466
+ "src_layer": 47
467
+ },
468
+ {
469
+ "out_layer": 91,
470
+ "src": "sub",
471
+ "src_layer": 48
472
+ },
473
+ {
474
+ "out_layer": 92,
475
+ "src": "sub",
476
+ "src_layer": 49
477
+ },
478
+ {
479
+ "out_layer": 93,
480
+ "src": "sub",
481
+ "src_layer": 50
482
+ },
483
+ {
484
+ "out_layer": 94,
485
+ "src": "sub",
486
+ "src_layer": 51
487
+ },
488
+ {
489
+ "out_layer": 95,
490
+ "src": "sub",
491
+ "src_layer": 52
492
+ },
493
+ {
494
+ "out_layer": 96,
495
+ "src": "sub",
496
+ "src_layer": 53
497
+ },
498
+ {
499
+ "out_layer": 97,
500
+ "src": "sub",
501
+ "src_layer": 54
502
+ },
503
+ {
504
+ "out_layer": 98,
505
+ "src": "sub",
506
+ "src_layer": 55
507
+ },
508
+ {
509
+ "out_layer": 99,
510
+ "src": "sub",
511
+ "src_layer": 56
512
+ },
513
+ {
514
+ "out_layer": 100,
515
+ "src": "sub",
516
+ "src_layer": 57
517
+ },
518
+ {
519
+ "out_layer": 101,
520
+ "src": "sub",
521
+ "src_layer": 58
522
+ },
523
+ {
524
+ "out_layer": 102,
525
+ "src": "sub",
526
+ "src_layer": 59
527
+ },
528
+ {
529
+ "out_layer": 103,
530
+ "src": "sub",
531
+ "src_layer": 60
532
+ }
533
+ ]
534
+ }
merge_stats.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "main_layers": 52,
3
+ "sub_layers": 52,
4
+ "shape_expansions": 0,
5
+ "verification_issues": 0,
6
+ "global_verification_issues": 0
7
+ }
model-00001-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:481c4bd5ad8fc4c67077a75eb1566b81062053f2430a162aee8c2d40372da263
3
+ size 5014365848
model-00002-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f93a510636f41fb0967a908b79591b6c7015fdc7c5c3430f5c3fb9bfcdfafcce
3
+ size 5033416368
model-00003-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8612a3d21175f07a603d604b2ac9ff9fbb3dc4992eaa24b1f4de6d3c2625df90
3
+ size 5033416368
model-00004-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b95945770f321578007e5dd9e1dba29f09837c39a425ac1f9e2b66aa6da409
3
+ size 5033416416
model-00005-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30ab99e7732d25ba37e131553371cb1a9d0e0e008151ed82ebffa96aac478fb6
3
+ size 5033416416
model-00006-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b520b1d416cc0d80e627dee4a4b922713f9aa8ccfddd53d6836818872fa2a02
3
+ size 5033416416
model-00007-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882c2afd6e3a195770ee3eb3b0fd884a2b8c5fb2fd3015199a97f9c70926513a
3
+ size 5033453640
model-00008-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d6e1c28b0d269f889df36876aecab2cf5028fc7eaa82bb69dd8c8a22c285ab
3
+ size 5190666072
model-00009-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa376166700e259229132ac0bb1b38ac86468cb52579cd5c39334e2bd7cd36c
3
+ size 4957918832
model-00010-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c4ad176972f73fcee3596a45b6bed818c5042f2b1f43ad4a45a3225bf6f7dbf
3
+ size 4951627136
model-00011-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f33db2e552db7e0c09753f5d6487caaa4e5a3b78d07943c5d6b98dd0f6f81f
3
+ size 5033416416
model-00012-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8b9d6b0f60a8f2537df3fdd86910198669ee0c04874cb4a1f34a5e1045bb91
3
+ size 5033416416
model-00013-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b127b6240e24d91f6d9e25823d8dccab9a128a56bd3fede9bad5c1f9f72312d
3
+ size 5033416416
model-00014-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91b5f6decb9626e1b6263239e3e0bf5d53bbdc681d6baaf043fb2769b1853be
3
+ size 5033416416
model-00015-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bada84521a2a3e4ef4ee5bc84bcd2ce0b0210503070a9998c326ff0aed6f38b8
3
+ size 5033416416
model-00016-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4d3ac9ba32a884f5b62bc52879921ff8002e003204497ed036b52134ead334
3
+ size 5033416416
model-00017-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c162c531070e2a99849402bc364ca26bc50dee570e6d61aa69dee2f948e17af4
3
+ size 5033416416
model-00018-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75bc381ae636f201e37b72d1841e590a01306a153b17e8066b2adec3dc41e30
3
+ size 5033416416
model-00019-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad52923576bb44cb8049fcc7f19a6be6ba9e9a8ce2a79b35e885cfaa31a4955f
3
+ size 5033416416
model-00020-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e608fbc337aa93bb992708b94abf9c41043f7a7610a0b9ae6dc1fd4f62964c
3
+ size 5033416416
model-00021-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5076533f8ab12a01877d1cc055a68baebafece2ee9d789281a2557f3adfa810
3
+ size 5033416424
model-00022-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75f0a932ba5797969653321d12fa12036d8e176fc7b73ff9eec0263698e597b1
3
+ size 2736921832
model.safetensors.index.json ADDED
@@ -0,0 +1,1050 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 108419493888
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00001-of-00022.safetensors",
7
+ "model.norm.weight": "model-00001-of-00022.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00022.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00022.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00022.safetensors",
11
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00022.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00022.safetensors",
13
+ "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00022.safetensors",
14
+ "model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00022.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00022.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00022.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00022.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00022.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00022.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00022.safetensors",
21
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00002-of-00022.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
23
+ "model.layers.1.post_mlp_layernorm.weight": "model-00002-of-00022.safetensors",
24
+ "model.layers.1.post_self_attn_layernorm.weight": "model-00002-of-00022.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00022.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00022.safetensors",
27
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00022.safetensors",
28
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00022.safetensors",
29
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00022.safetensors",
30
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00022.safetensors",
31
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00002-of-00022.safetensors",
32
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
33
+ "model.layers.2.post_mlp_layernorm.weight": "model-00002-of-00022.safetensors",
34
+ "model.layers.2.post_self_attn_layernorm.weight": "model-00002-of-00022.safetensors",
35
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00022.safetensors",
36
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00022.safetensors",
37
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00022.safetensors",
38
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00022.safetensors",
39
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00022.safetensors",
40
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00022.safetensors",
41
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00002-of-00022.safetensors",
42
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
43
+ "model.layers.3.post_mlp_layernorm.weight": "model-00002-of-00022.safetensors",
44
+ "model.layers.3.post_self_attn_layernorm.weight": "model-00002-of-00022.safetensors",
45
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00022.safetensors",
46
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00022.safetensors",
47
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00022.safetensors",
48
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00022.safetensors",
49
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00022.safetensors",
50
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00022.safetensors",
51
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00002-of-00022.safetensors",
52
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
53
+ "model.layers.4.post_mlp_layernorm.weight": "model-00002-of-00022.safetensors",
54
+ "model.layers.4.post_self_attn_layernorm.weight": "model-00002-of-00022.safetensors",
55
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00022.safetensors",
56
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00022.safetensors",
57
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00022.safetensors",
58
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00022.safetensors",
59
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00022.safetensors",
60
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00022.safetensors",
61
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00002-of-00022.safetensors",
62
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00022.safetensors",
63
+ "model.layers.5.post_mlp_layernorm.weight": "model-00002-of-00022.safetensors",
64
+ "model.layers.5.post_self_attn_layernorm.weight": "model-00002-of-00022.safetensors",
65
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00022.safetensors",
66
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00022.safetensors",
67
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00022.safetensors",
68
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00022.safetensors",
69
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00022.safetensors",
70
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00022.safetensors",
71
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00003-of-00022.safetensors",
72
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00022.safetensors",
73
+ "model.layers.6.post_mlp_layernorm.weight": "model-00003-of-00022.safetensors",
74
+ "model.layers.6.post_self_attn_layernorm.weight": "model-00003-of-00022.safetensors",
75
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00022.safetensors",
76
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00022.safetensors",
77
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00022.safetensors",
78
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00022.safetensors",
79
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00022.safetensors",
80
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00022.safetensors",
81
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00003-of-00022.safetensors",
82
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00022.safetensors",
83
+ "model.layers.7.post_mlp_layernorm.weight": "model-00003-of-00022.safetensors",
84
+ "model.layers.7.post_self_attn_layernorm.weight": "model-00003-of-00022.safetensors",
85
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00022.safetensors",
86
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00022.safetensors",
87
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00022.safetensors",
88
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00022.safetensors",
89
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00022.safetensors",
90
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00022.safetensors",
91
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00003-of-00022.safetensors",
92
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00022.safetensors",
93
+ "model.layers.8.post_mlp_layernorm.weight": "model-00003-of-00022.safetensors",
94
+ "model.layers.8.post_self_attn_layernorm.weight": "model-00003-of-00022.safetensors",
95
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00022.safetensors",
96
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00022.safetensors",
97
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00022.safetensors",
98
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00022.safetensors",
99
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00022.safetensors",
100
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00022.safetensors",
101
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00003-of-00022.safetensors",
102
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00022.safetensors",
103
+ "model.layers.9.post_mlp_layernorm.weight": "model-00003-of-00022.safetensors",
104
+ "model.layers.9.post_self_attn_layernorm.weight": "model-00003-of-00022.safetensors",
105
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00022.safetensors",
106
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00022.safetensors",
107
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00022.safetensors",
108
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00022.safetensors",
109
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00022.safetensors",
110
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00022.safetensors",
111
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00003-of-00022.safetensors",
112
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00022.safetensors",
113
+ "model.layers.10.post_mlp_layernorm.weight": "model-00003-of-00022.safetensors",
114
+ "model.layers.10.post_self_attn_layernorm.weight": "model-00003-of-00022.safetensors",
115
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00022.safetensors",
116
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00022.safetensors",
117
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00022.safetensors",
118
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00022.safetensors",
119
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00022.safetensors",
120
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00022.safetensors",
121
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00004-of-00022.safetensors",
122
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00022.safetensors",
123
+ "model.layers.11.post_mlp_layernorm.weight": "model-00004-of-00022.safetensors",
124
+ "model.layers.11.post_self_attn_layernorm.weight": "model-00004-of-00022.safetensors",
125
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00022.safetensors",
126
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00022.safetensors",
127
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00022.safetensors",
128
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00022.safetensors",
129
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00004-of-00022.safetensors",
130
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00022.safetensors",
131
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00022.safetensors",
132
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00022.safetensors",
133
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00022.safetensors",
134
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00022.safetensors",
135
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00022.safetensors",
136
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00022.safetensors",
137
+ "model.layers.12.post_mlp_layernorm.weight": "model-00004-of-00022.safetensors",
138
+ "model.layers.12.post_self_attn_layernorm.weight": "model-00004-of-00022.safetensors",
139
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00022.safetensors",
140
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00022.safetensors",
141
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00004-of-00022.safetensors",
142
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00022.safetensors",
143
+ "model.layers.13.post_mlp_layernorm.weight": "model-00004-of-00022.safetensors",
144
+ "model.layers.13.post_self_attn_layernorm.weight": "model-00004-of-00022.safetensors",
145
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00022.safetensors",
146
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00022.safetensors",
147
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00022.safetensors",
148
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00022.safetensors",
149
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00022.safetensors",
150
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00022.safetensors",
151
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00004-of-00022.safetensors",
152
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00022.safetensors",
153
+ "model.layers.14.post_mlp_layernorm.weight": "model-00004-of-00022.safetensors",
154
+ "model.layers.14.post_self_attn_layernorm.weight": "model-00004-of-00022.safetensors",
155
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00022.safetensors",
156
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00022.safetensors",
157
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00022.safetensors",
158
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00022.safetensors",
159
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00022.safetensors",
160
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00022.safetensors",
161
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00004-of-00022.safetensors",
162
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00022.safetensors",
163
+ "model.layers.15.post_mlp_layernorm.weight": "model-00004-of-00022.safetensors",
164
+ "model.layers.15.post_self_attn_layernorm.weight": "model-00004-of-00022.safetensors",
165
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00022.safetensors",
166
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00022.safetensors",
167
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00022.safetensors",
168
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00022.safetensors",
169
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00022.safetensors",
170
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00022.safetensors",
171
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00005-of-00022.safetensors",
172
+ "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00022.safetensors",
173
+ "model.layers.16.post_mlp_layernorm.weight": "model-00005-of-00022.safetensors",
174
+ "model.layers.16.post_self_attn_layernorm.weight": "model-00005-of-00022.safetensors",
175
+ "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00022.safetensors",
176
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00022.safetensors",
177
+ "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00022.safetensors",
178
+ "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00022.safetensors",
179
+ "model.layers.17.input_layernorm.weight": "model-00005-of-00022.safetensors",
180
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00022.safetensors",
181
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00005-of-00022.safetensors",
182
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00022.safetensors",
183
+ "model.layers.17.post_mlp_layernorm.weight": "model-00005-of-00022.safetensors",
184
+ "model.layers.17.post_self_attn_layernorm.weight": "model-00005-of-00022.safetensors",
185
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00022.safetensors",
186
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00022.safetensors",
187
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00022.safetensors",
188
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00022.safetensors",
189
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00022.safetensors",
190
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00022.safetensors",
191
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00005-of-00022.safetensors",
192
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00022.safetensors",
193
+ "model.layers.18.post_mlp_layernorm.weight": "model-00005-of-00022.safetensors",
194
+ "model.layers.18.post_self_attn_layernorm.weight": "model-00005-of-00022.safetensors",
195
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00022.safetensors",
196
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00022.safetensors",
197
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00022.safetensors",
198
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00022.safetensors",
199
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00022.safetensors",
200
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00022.safetensors",
201
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00005-of-00022.safetensors",
202
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00022.safetensors",
203
+ "model.layers.19.post_mlp_layernorm.weight": "model-00005-of-00022.safetensors",
204
+ "model.layers.19.post_self_attn_layernorm.weight": "model-00005-of-00022.safetensors",
205
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00022.safetensors",
206
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00022.safetensors",
207
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00022.safetensors",
208
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00022.safetensors",
209
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00022.safetensors",
210
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00022.safetensors",
211
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00005-of-00022.safetensors",
212
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00022.safetensors",
213
+ "model.layers.20.post_mlp_layernorm.weight": "model-00005-of-00022.safetensors",
214
+ "model.layers.20.post_self_attn_layernorm.weight": "model-00005-of-00022.safetensors",
215
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00022.safetensors",
216
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00022.safetensors",
217
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00022.safetensors",
218
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00022.safetensors",
219
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00022.safetensors",
220
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00022.safetensors",
221
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00006-of-00022.safetensors",
222
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00022.safetensors",
223
+ "model.layers.21.post_mlp_layernorm.weight": "model-00006-of-00022.safetensors",
224
+ "model.layers.21.post_self_attn_layernorm.weight": "model-00006-of-00022.safetensors",
225
+ "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00022.safetensors",
226
+ "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00022.safetensors",
227
+ "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00022.safetensors",
228
+ "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00022.safetensors",
229
+ "model.layers.22.input_layernorm.weight": "model-00006-of-00022.safetensors",
230
+ "model.layers.22.mlp.down_proj.weight": "model-00006-of-00022.safetensors",
231
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00006-of-00022.safetensors",
232
+ "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00022.safetensors",
233
+ "model.layers.22.post_mlp_layernorm.weight": "model-00006-of-00022.safetensors",
234
+ "model.layers.22.post_self_attn_layernorm.weight": "model-00006-of-00022.safetensors",
235
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00022.safetensors",
236
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00022.safetensors",
237
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00022.safetensors",
238
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00022.safetensors",
239
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00022.safetensors",
240
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00022.safetensors",
241
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00006-of-00022.safetensors",
242
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00022.safetensors",
243
+ "model.layers.23.post_mlp_layernorm.weight": "model-00006-of-00022.safetensors",
244
+ "model.layers.23.post_self_attn_layernorm.weight": "model-00006-of-00022.safetensors",
245
+ "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00022.safetensors",
246
+ "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00022.safetensors",
247
+ "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00022.safetensors",
248
+ "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00022.safetensors",
249
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00022.safetensors",
250
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00022.safetensors",
251
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00006-of-00022.safetensors",
252
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00022.safetensors",
253
+ "model.layers.24.post_mlp_layernorm.weight": "model-00006-of-00022.safetensors",
254
+ "model.layers.24.post_self_attn_layernorm.weight": "model-00006-of-00022.safetensors",
255
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00022.safetensors",
256
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00022.safetensors",
257
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00022.safetensors",
258
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00022.safetensors",
259
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00022.safetensors",
260
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00022.safetensors",
261
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00006-of-00022.safetensors",
262
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00022.safetensors",
263
+ "model.layers.25.post_mlp_layernorm.weight": "model-00006-of-00022.safetensors",
264
+ "model.layers.25.post_self_attn_layernorm.weight": "model-00006-of-00022.safetensors",
265
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00022.safetensors",
266
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00022.safetensors",
267
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00022.safetensors",
268
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00022.safetensors",
269
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00022.safetensors",
270
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00022.safetensors",
271
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00007-of-00022.safetensors",
272
+ "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
273
+ "model.layers.26.post_mlp_layernorm.weight": "model-00007-of-00022.safetensors",
274
+ "model.layers.26.post_self_attn_layernorm.weight": "model-00007-of-00022.safetensors",
275
+ "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00022.safetensors",
276
+ "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00022.safetensors",
277
+ "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00022.safetensors",
278
+ "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00022.safetensors",
279
+ "model.layers.27.input_layernorm.weight": "model-00007-of-00022.safetensors",
280
+ "model.layers.27.mlp.down_proj.weight": "model-00007-of-00022.safetensors",
281
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00007-of-00022.safetensors",
282
+ "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
283
+ "model.layers.27.post_mlp_layernorm.weight": "model-00007-of-00022.safetensors",
284
+ "model.layers.27.post_self_attn_layernorm.weight": "model-00007-of-00022.safetensors",
285
+ "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00022.safetensors",
286
+ "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00022.safetensors",
287
+ "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00022.safetensors",
288
+ "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00022.safetensors",
289
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00022.safetensors",
290
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00022.safetensors",
291
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00007-of-00022.safetensors",
292
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
293
+ "model.layers.28.post_mlp_layernorm.weight": "model-00007-of-00022.safetensors",
294
+ "model.layers.28.post_self_attn_layernorm.weight": "model-00007-of-00022.safetensors",
295
+ "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00022.safetensors",
296
+ "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00022.safetensors",
297
+ "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00022.safetensors",
298
+ "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00022.safetensors",
299
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00022.safetensors",
300
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00022.safetensors",
301
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00007-of-00022.safetensors",
302
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
303
+ "model.layers.29.post_mlp_layernorm.weight": "model-00007-of-00022.safetensors",
304
+ "model.layers.29.post_self_attn_layernorm.weight": "model-00007-of-00022.safetensors",
305
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00022.safetensors",
306
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00022.safetensors",
307
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00022.safetensors",
308
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00022.safetensors",
309
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00022.safetensors",
310
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00022.safetensors",
311
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00007-of-00022.safetensors",
312
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
313
+ "model.layers.30.post_mlp_layernorm.weight": "model-00007-of-00022.safetensors",
314
+ "model.layers.30.post_self_attn_layernorm.weight": "model-00007-of-00022.safetensors",
315
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00022.safetensors",
316
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00022.safetensors",
317
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00022.safetensors",
318
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00022.safetensors",
319
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00022.safetensors",
320
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00022.safetensors",
321
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00022.safetensors",
322
+ "model.layers.31.post_mlp_layernorm.weight": "model-00007-of-00022.safetensors",
323
+ "model.layers.31.post_self_attn_layernorm.weight": "model-00007-of-00022.safetensors",
324
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00008-of-00022.safetensors",
325
+ "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00022.safetensors",
326
+ "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00022.safetensors",
327
+ "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00022.safetensors",
328
+ "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00022.safetensors",
329
+ "model.layers.32.input_layernorm.weight": "model-00008-of-00022.safetensors",
330
+ "model.layers.32.mlp.down_proj.weight": "model-00008-of-00022.safetensors",
331
+ "model.layers.32.mlp.gate_up_proj.weight": "model-00008-of-00022.safetensors",
332
+ "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00022.safetensors",
333
+ "model.layers.32.post_mlp_layernorm.weight": "model-00008-of-00022.safetensors",
334
+ "model.layers.32.post_self_attn_layernorm.weight": "model-00008-of-00022.safetensors",
335
+ "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00022.safetensors",
336
+ "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00022.safetensors",
337
+ "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00022.safetensors",
338
+ "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00022.safetensors",
339
+ "model.layers.33.input_layernorm.weight": "model-00008-of-00022.safetensors",
340
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-00022.safetensors",
341
+ "model.layers.33.mlp.gate_up_proj.weight": "model-00008-of-00022.safetensors",
342
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00022.safetensors",
343
+ "model.layers.33.post_mlp_layernorm.weight": "model-00008-of-00022.safetensors",
344
+ "model.layers.33.post_self_attn_layernorm.weight": "model-00008-of-00022.safetensors",
345
+ "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00022.safetensors",
346
+ "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00022.safetensors",
347
+ "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00022.safetensors",
348
+ "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00022.safetensors",
349
+ "model.layers.34.input_layernorm.weight": "model-00008-of-00022.safetensors",
350
+ "model.layers.34.mlp.down_proj.weight": "model-00008-of-00022.safetensors",
351
+ "model.layers.34.mlp.gate_up_proj.weight": "model-00008-of-00022.safetensors",
352
+ "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00022.safetensors",
353
+ "model.layers.34.post_mlp_layernorm.weight": "model-00008-of-00022.safetensors",
354
+ "model.layers.34.post_self_attn_layernorm.weight": "model-00008-of-00022.safetensors",
355
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00022.safetensors",
356
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00022.safetensors",
357
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00022.safetensors",
358
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00022.safetensors",
359
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00022.safetensors",
360
+ "model.layers.35.mlp.down_proj.weight": "model-00008-of-00022.safetensors",
361
+ "model.layers.35.mlp.gate_up_proj.weight": "model-00008-of-00022.safetensors",
362
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00022.safetensors",
363
+ "model.layers.35.post_mlp_layernorm.weight": "model-00008-of-00022.safetensors",
364
+ "model.layers.35.post_self_attn_layernorm.weight": "model-00008-of-00022.safetensors",
365
+ "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00022.safetensors",
366
+ "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00022.safetensors",
367
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00022.safetensors",
368
+ "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00022.safetensors",
369
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00022.safetensors",
370
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00022.safetensors",
371
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00022.safetensors",
372
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00022.safetensors",
373
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00022.safetensors",
374
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00022.safetensors",
375
+ "model.layers.36.mlp.gate_up_proj.weight": "model-00009-of-00022.safetensors",
376
+ "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00022.safetensors",
377
+ "model.layers.36.post_mlp_layernorm.weight": "model-00009-of-00022.safetensors",
378
+ "model.layers.36.post_self_attn_layernorm.weight": "model-00009-of-00022.safetensors",
379
+ "model.layers.37.input_layernorm.weight": "model-00009-of-00022.safetensors",
380
+ "model.layers.37.mlp.down_proj.weight": "model-00009-of-00022.safetensors",
381
+ "model.layers.37.mlp.gate_up_proj.weight": "model-00009-of-00022.safetensors",
382
+ "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00022.safetensors",
383
+ "model.layers.37.post_mlp_layernorm.weight": "model-00009-of-00022.safetensors",
384
+ "model.layers.37.post_self_attn_layernorm.weight": "model-00009-of-00022.safetensors",
385
+ "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00022.safetensors",
386
+ "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00022.safetensors",
387
+ "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00022.safetensors",
388
+ "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00022.safetensors",
389
+ "model.layers.38.input_layernorm.weight": "model-00009-of-00022.safetensors",
390
+ "model.layers.38.mlp.down_proj.weight": "model-00009-of-00022.safetensors",
391
+ "model.layers.38.mlp.gate_up_proj.weight": "model-00009-of-00022.safetensors",
392
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00022.safetensors",
393
+ "model.layers.38.post_mlp_layernorm.weight": "model-00009-of-00022.safetensors",
394
+ "model.layers.38.post_self_attn_layernorm.weight": "model-00009-of-00022.safetensors",
395
+ "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00022.safetensors",
396
+ "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00022.safetensors",
397
+ "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00022.safetensors",
398
+ "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00022.safetensors",
399
+ "model.layers.39.input_layernorm.weight": "model-00009-of-00022.safetensors",
400
+ "model.layers.39.mlp.down_proj.weight": "model-00009-of-00022.safetensors",
401
+ "model.layers.39.mlp.gate_up_proj.weight": "model-00009-of-00022.safetensors",
402
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00022.safetensors",
403
+ "model.layers.39.post_mlp_layernorm.weight": "model-00009-of-00022.safetensors",
404
+ "model.layers.39.post_self_attn_layernorm.weight": "model-00009-of-00022.safetensors",
405
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00022.safetensors",
406
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00022.safetensors",
407
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00022.safetensors",
408
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00022.safetensors",
409
+ "model.layers.40.input_layernorm.weight": "model-00009-of-00022.safetensors",
410
+ "model.layers.40.mlp.down_proj.weight": "model-00009-of-00022.safetensors",
411
+ "model.layers.40.mlp.gate_up_proj.weight": "model-00009-of-00022.safetensors",
412
+ "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00022.safetensors",
413
+ "model.layers.40.post_mlp_layernorm.weight": "model-00009-of-00022.safetensors",
414
+ "model.layers.40.post_self_attn_layernorm.weight": "model-00009-of-00022.safetensors",
415
+ "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00022.safetensors",
416
+ "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00022.safetensors",
417
+ "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00022.safetensors",
418
+ "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00022.safetensors",
419
+ "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00022.safetensors",
420
+ "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00022.safetensors",
421
+ "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00022.safetensors",
422
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00022.safetensors",
423
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00022.safetensors",
424
+ "model.layers.41.mlp.gate_up_proj.weight": "model-00010-of-00022.safetensors",
425
+ "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00022.safetensors",
426
+ "model.layers.41.post_mlp_layernorm.weight": "model-00010-of-00022.safetensors",
427
+ "model.layers.41.post_self_attn_layernorm.weight": "model-00010-of-00022.safetensors",
428
+ "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00022.safetensors",
429
+ "model.layers.42.input_layernorm.weight": "model-00010-of-00022.safetensors",
430
+ "model.layers.42.mlp.down_proj.weight": "model-00010-of-00022.safetensors",
431
+ "model.layers.42.mlp.gate_up_proj.weight": "model-00010-of-00022.safetensors",
432
+ "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00022.safetensors",
433
+ "model.layers.42.post_mlp_layernorm.weight": "model-00010-of-00022.safetensors",
434
+ "model.layers.42.post_self_attn_layernorm.weight": "model-00010-of-00022.safetensors",
435
+ "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00022.safetensors",
436
+ "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00022.safetensors",
437
+ "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00022.safetensors",
438
+ "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00022.safetensors",
439
+ "model.layers.43.input_layernorm.weight": "model-00010-of-00022.safetensors",
440
+ "model.layers.43.mlp.down_proj.weight": "model-00010-of-00022.safetensors",
441
+ "model.layers.43.mlp.gate_up_proj.weight": "model-00010-of-00022.safetensors",
442
+ "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00022.safetensors",
443
+ "model.layers.43.post_mlp_layernorm.weight": "model-00010-of-00022.safetensors",
444
+ "model.layers.43.post_self_attn_layernorm.weight": "model-00010-of-00022.safetensors",
445
+ "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00022.safetensors",
446
+ "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00022.safetensors",
447
+ "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00022.safetensors",
448
+ "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00022.safetensors",
449
+ "model.layers.44.input_layernorm.weight": "model-00010-of-00022.safetensors",
450
+ "model.layers.44.mlp.down_proj.weight": "model-00010-of-00022.safetensors",
451
+ "model.layers.44.mlp.gate_up_proj.weight": "model-00010-of-00022.safetensors",
452
+ "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00022.safetensors",
453
+ "model.layers.44.post_mlp_layernorm.weight": "model-00010-of-00022.safetensors",
454
+ "model.layers.44.post_self_attn_layernorm.weight": "model-00010-of-00022.safetensors",
455
+ "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00022.safetensors",
456
+ "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00022.safetensors",
457
+ "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00022.safetensors",
458
+ "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00022.safetensors",
459
+ "model.layers.45.input_layernorm.weight": "model-00010-of-00022.safetensors",
460
+ "model.layers.45.mlp.down_proj.weight": "model-00010-of-00022.safetensors",
461
+ "model.layers.45.mlp.gate_up_proj.weight": "model-00010-of-00022.safetensors",
462
+ "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00022.safetensors",
463
+ "model.layers.45.post_mlp_layernorm.weight": "model-00010-of-00022.safetensors",
464
+ "model.layers.45.post_self_attn_layernorm.weight": "model-00010-of-00022.safetensors",
465
+ "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00022.safetensors",
466
+ "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00022.safetensors",
467
+ "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00022.safetensors",
468
+ "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00022.safetensors",
469
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00022.safetensors",
470
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00022.safetensors",
471
+ "model.layers.46.mlp.gate_up_proj.weight": "model-00011-of-00022.safetensors",
472
+ "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00022.safetensors",
473
+ "model.layers.46.post_mlp_layernorm.weight": "model-00011-of-00022.safetensors",
474
+ "model.layers.46.post_self_attn_layernorm.weight": "model-00011-of-00022.safetensors",
475
+ "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00022.safetensors",
476
+ "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00022.safetensors",
477
+ "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00022.safetensors",
478
+ "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00022.safetensors",
479
+ "model.layers.47.input_layernorm.weight": "model-00011-of-00022.safetensors",
480
+ "model.layers.47.mlp.down_proj.weight": "model-00011-of-00022.safetensors",
481
+ "model.layers.47.mlp.gate_up_proj.weight": "model-00011-of-00022.safetensors",
482
+ "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00022.safetensors",
483
+ "model.layers.47.post_mlp_layernorm.weight": "model-00011-of-00022.safetensors",
484
+ "model.layers.47.post_self_attn_layernorm.weight": "model-00011-of-00022.safetensors",
485
+ "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00022.safetensors",
486
+ "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00022.safetensors",
487
+ "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00022.safetensors",
488
+ "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00022.safetensors",
489
+ "model.layers.48.input_layernorm.weight": "model-00011-of-00022.safetensors",
490
+ "model.layers.48.mlp.down_proj.weight": "model-00011-of-00022.safetensors",
491
+ "model.layers.48.mlp.gate_up_proj.weight": "model-00011-of-00022.safetensors",
492
+ "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00022.safetensors",
493
+ "model.layers.48.post_mlp_layernorm.weight": "model-00011-of-00022.safetensors",
494
+ "model.layers.48.post_self_attn_layernorm.weight": "model-00011-of-00022.safetensors",
495
+ "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00022.safetensors",
496
+ "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00022.safetensors",
497
+ "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00022.safetensors",
498
+ "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00022.safetensors",
499
+ "model.layers.49.input_layernorm.weight": "model-00011-of-00022.safetensors",
500
+ "model.layers.49.mlp.down_proj.weight": "model-00011-of-00022.safetensors",
501
+ "model.layers.49.mlp.gate_up_proj.weight": "model-00011-of-00022.safetensors",
502
+ "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00022.safetensors",
503
+ "model.layers.49.post_mlp_layernorm.weight": "model-00011-of-00022.safetensors",
504
+ "model.layers.49.post_self_attn_layernorm.weight": "model-00011-of-00022.safetensors",
505
+ "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00022.safetensors",
506
+ "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00022.safetensors",
507
+ "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00022.safetensors",
508
+ "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00022.safetensors",
509
+ "model.layers.50.input_layernorm.weight": "model-00011-of-00022.safetensors",
510
+ "model.layers.50.mlp.down_proj.weight": "model-00011-of-00022.safetensors",
511
+ "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00022.safetensors",
512
+ "model.layers.50.post_mlp_layernorm.weight": "model-00011-of-00022.safetensors",
513
+ "model.layers.50.post_self_attn_layernorm.weight": "model-00011-of-00022.safetensors",
514
+ "model.layers.50.mlp.gate_up_proj.weight": "model-00011-of-00022.safetensors",
515
+ "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00022.safetensors",
516
+ "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00022.safetensors",
517
+ "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00022.safetensors",
518
+ "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00022.safetensors",
519
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00022.safetensors",
520
+ "model.layers.51.mlp.down_proj.weight": "model-00011-of-00022.safetensors",
521
+ "model.layers.51.mlp.gate_up_proj.weight": "model-00012-of-00022.safetensors",
522
+ "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00022.safetensors",
523
+ "model.layers.51.post_mlp_layernorm.weight": "model-00012-of-00022.safetensors",
524
+ "model.layers.51.post_self_attn_layernorm.weight": "model-00012-of-00022.safetensors",
525
+ "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00022.safetensors",
526
+ "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00022.safetensors",
527
+ "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00022.safetensors",
528
+ "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00022.safetensors",
529
+ "model.layers.52.input_layernorm.weight": "model-00012-of-00022.safetensors",
530
+ "model.layers.52.mlp.down_proj.weight": "model-00012-of-00022.safetensors",
531
+ "model.layers.52.mlp.gate_up_proj.weight": "model-00012-of-00022.safetensors",
532
+ "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00022.safetensors",
533
+ "model.layers.52.post_mlp_layernorm.weight": "model-00012-of-00022.safetensors",
534
+ "model.layers.52.post_self_attn_layernorm.weight": "model-00012-of-00022.safetensors",
535
+ "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00022.safetensors",
536
+ "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00022.safetensors",
537
+ "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00022.safetensors",
538
+ "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00022.safetensors",
539
+ "model.layers.53.input_layernorm.weight": "model-00012-of-00022.safetensors",
540
+ "model.layers.53.mlp.down_proj.weight": "model-00012-of-00022.safetensors",
541
+ "model.layers.53.mlp.gate_up_proj.weight": "model-00012-of-00022.safetensors",
542
+ "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00022.safetensors",
543
+ "model.layers.53.post_mlp_layernorm.weight": "model-00012-of-00022.safetensors",
544
+ "model.layers.53.post_self_attn_layernorm.weight": "model-00012-of-00022.safetensors",
545
+ "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00022.safetensors",
546
+ "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00022.safetensors",
547
+ "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00022.safetensors",
548
+ "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00022.safetensors",
549
+ "model.layers.54.input_layernorm.weight": "model-00012-of-00022.safetensors",
550
+ "model.layers.54.mlp.down_proj.weight": "model-00012-of-00022.safetensors",
551
+ "model.layers.54.mlp.gate_up_proj.weight": "model-00012-of-00022.safetensors",
552
+ "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00022.safetensors",
553
+ "model.layers.54.post_mlp_layernorm.weight": "model-00012-of-00022.safetensors",
554
+ "model.layers.54.post_self_attn_layernorm.weight": "model-00012-of-00022.safetensors",
555
+ "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00022.safetensors",
556
+ "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00022.safetensors",
557
+ "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00022.safetensors",
558
+ "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00022.safetensors",
559
+ "model.layers.55.mlp.gate_up_proj.weight": "model-00012-of-00022.safetensors",
560
+ "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00022.safetensors",
561
+ "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00022.safetensors",
562
+ "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00022.safetensors",
563
+ "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00022.safetensors",
564
+ "model.layers.55.input_layernorm.weight": "model-00012-of-00022.safetensors",
565
+ "model.layers.55.mlp.down_proj.weight": "model-00012-of-00022.safetensors",
566
+ "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00022.safetensors",
567
+ "model.layers.55.post_mlp_layernorm.weight": "model-00012-of-00022.safetensors",
568
+ "model.layers.55.post_self_attn_layernorm.weight": "model-00012-of-00022.safetensors",
569
+ "model.layers.56.input_layernorm.weight": "model-00012-of-00022.safetensors",
570
+ "model.layers.56.mlp.down_proj.weight": "model-00012-of-00022.safetensors",
571
+ "model.layers.56.mlp.gate_up_proj.weight": "model-00013-of-00022.safetensors",
572
+ "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00022.safetensors",
573
+ "model.layers.56.post_mlp_layernorm.weight": "model-00013-of-00022.safetensors",
574
+ "model.layers.56.post_self_attn_layernorm.weight": "model-00013-of-00022.safetensors",
575
+ "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00022.safetensors",
576
+ "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00022.safetensors",
577
+ "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00022.safetensors",
578
+ "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00022.safetensors",
579
+ "model.layers.57.input_layernorm.weight": "model-00013-of-00022.safetensors",
580
+ "model.layers.57.mlp.down_proj.weight": "model-00013-of-00022.safetensors",
581
+ "model.layers.57.mlp.gate_up_proj.weight": "model-00013-of-00022.safetensors",
582
+ "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00022.safetensors",
583
+ "model.layers.57.post_mlp_layernorm.weight": "model-00013-of-00022.safetensors",
584
+ "model.layers.57.post_self_attn_layernorm.weight": "model-00013-of-00022.safetensors",
585
+ "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00022.safetensors",
586
+ "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00022.safetensors",
587
+ "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00022.safetensors",
588
+ "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00022.safetensors",
589
+ "model.layers.58.input_layernorm.weight": "model-00013-of-00022.safetensors",
590
+ "model.layers.58.mlp.down_proj.weight": "model-00013-of-00022.safetensors",
591
+ "model.layers.58.mlp.gate_up_proj.weight": "model-00013-of-00022.safetensors",
592
+ "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00022.safetensors",
593
+ "model.layers.58.post_mlp_layernorm.weight": "model-00013-of-00022.safetensors",
594
+ "model.layers.58.post_self_attn_layernorm.weight": "model-00013-of-00022.safetensors",
595
+ "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00022.safetensors",
596
+ "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00022.safetensors",
597
+ "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00022.safetensors",
598
+ "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00022.safetensors",
599
+ "model.layers.59.input_layernorm.weight": "model-00013-of-00022.safetensors",
600
+ "model.layers.59.mlp.down_proj.weight": "model-00013-of-00022.safetensors",
601
+ "model.layers.59.mlp.gate_up_proj.weight": "model-00013-of-00022.safetensors",
602
+ "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00022.safetensors",
603
+ "model.layers.59.post_mlp_layernorm.weight": "model-00013-of-00022.safetensors",
604
+ "model.layers.59.post_self_attn_layernorm.weight": "model-00013-of-00022.safetensors",
605
+ "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00022.safetensors",
606
+ "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00022.safetensors",
607
+ "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00022.safetensors",
608
+ "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00022.safetensors",
609
+ "model.layers.60.input_layernorm.weight": "model-00013-of-00022.safetensors",
610
+ "model.layers.60.mlp.down_proj.weight": "model-00013-of-00022.safetensors",
611
+ "model.layers.60.mlp.gate_up_proj.weight": "model-00013-of-00022.safetensors",
612
+ "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00022.safetensors",
613
+ "model.layers.60.post_mlp_layernorm.weight": "model-00013-of-00022.safetensors",
614
+ "model.layers.60.post_self_attn_layernorm.weight": "model-00013-of-00022.safetensors",
615
+ "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00022.safetensors",
616
+ "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00022.safetensors",
617
+ "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00022.safetensors",
618
+ "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00022.safetensors",
619
+ "model.layers.61.input_layernorm.weight": "model-00013-of-00022.safetensors",
620
+ "model.layers.61.mlp.down_proj.weight": "model-00013-of-00022.safetensors",
621
+ "model.layers.61.mlp.gate_up_proj.weight": "model-00014-of-00022.safetensors",
622
+ "model.layers.61.post_attention_layernorm.weight": "model-00014-of-00022.safetensors",
623
+ "model.layers.61.post_mlp_layernorm.weight": "model-00014-of-00022.safetensors",
624
+ "model.layers.61.post_self_attn_layernorm.weight": "model-00014-of-00022.safetensors",
625
+ "model.layers.61.self_attn.k_proj.weight": "model-00014-of-00022.safetensors",
626
+ "model.layers.61.self_attn.o_proj.weight": "model-00014-of-00022.safetensors",
627
+ "model.layers.61.self_attn.q_proj.weight": "model-00014-of-00022.safetensors",
628
+ "model.layers.61.self_attn.v_proj.weight": "model-00014-of-00022.safetensors",
629
+ "model.layers.62.input_layernorm.weight": "model-00014-of-00022.safetensors",
630
+ "model.layers.62.mlp.down_proj.weight": "model-00014-of-00022.safetensors",
631
+ "model.layers.62.mlp.gate_up_proj.weight": "model-00014-of-00022.safetensors",
632
+ "model.layers.62.post_attention_layernorm.weight": "model-00014-of-00022.safetensors",
633
+ "model.layers.62.post_mlp_layernorm.weight": "model-00014-of-00022.safetensors",
634
+ "model.layers.62.post_self_attn_layernorm.weight": "model-00014-of-00022.safetensors",
635
+ "model.layers.62.self_attn.k_proj.weight": "model-00014-of-00022.safetensors",
636
+ "model.layers.62.self_attn.o_proj.weight": "model-00014-of-00022.safetensors",
637
+ "model.layers.62.self_attn.q_proj.weight": "model-00014-of-00022.safetensors",
638
+ "model.layers.62.self_attn.v_proj.weight": "model-00014-of-00022.safetensors",
639
+ "model.layers.63.input_layernorm.weight": "model-00014-of-00022.safetensors",
640
+ "model.layers.63.mlp.down_proj.weight": "model-00014-of-00022.safetensors",
641
+ "model.layers.63.mlp.gate_up_proj.weight": "model-00014-of-00022.safetensors",
642
+ "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00022.safetensors",
643
+ "model.layers.63.post_mlp_layernorm.weight": "model-00014-of-00022.safetensors",
644
+ "model.layers.63.post_self_attn_layernorm.weight": "model-00014-of-00022.safetensors",
645
+ "model.layers.63.self_attn.k_proj.weight": "model-00014-of-00022.safetensors",
646
+ "model.layers.63.self_attn.o_proj.weight": "model-00014-of-00022.safetensors",
647
+ "model.layers.63.self_attn.q_proj.weight": "model-00014-of-00022.safetensors",
648
+ "model.layers.63.self_attn.v_proj.weight": "model-00014-of-00022.safetensors",
649
+ "model.layers.64.input_layernorm.weight": "model-00014-of-00022.safetensors",
650
+ "model.layers.64.mlp.down_proj.weight": "model-00014-of-00022.safetensors",
651
+ "model.layers.64.mlp.gate_up_proj.weight": "model-00014-of-00022.safetensors",
652
+ "model.layers.64.post_attention_layernorm.weight": "model-00014-of-00022.safetensors",
653
+ "model.layers.64.post_mlp_layernorm.weight": "model-00014-of-00022.safetensors",
654
+ "model.layers.64.post_self_attn_layernorm.weight": "model-00014-of-00022.safetensors",
655
+ "model.layers.64.self_attn.k_proj.weight": "model-00014-of-00022.safetensors",
656
+ "model.layers.64.self_attn.o_proj.weight": "model-00014-of-00022.safetensors",
657
+ "model.layers.64.self_attn.q_proj.weight": "model-00014-of-00022.safetensors",
658
+ "model.layers.64.self_attn.v_proj.weight": "model-00014-of-00022.safetensors",
659
+ "model.layers.65.input_layernorm.weight": "model-00014-of-00022.safetensors",
660
+ "model.layers.65.mlp.down_proj.weight": "model-00014-of-00022.safetensors",
661
+ "model.layers.65.mlp.gate_up_proj.weight": "model-00014-of-00022.safetensors",
662
+ "model.layers.65.post_attention_layernorm.weight": "model-00014-of-00022.safetensors",
663
+ "model.layers.65.post_mlp_layernorm.weight": "model-00014-of-00022.safetensors",
664
+ "model.layers.65.post_self_attn_layernorm.weight": "model-00014-of-00022.safetensors",
665
+ "model.layers.65.self_attn.o_proj.weight": "model-00014-of-00022.safetensors",
666
+ "model.layers.65.self_attn.k_proj.weight": "model-00014-of-00022.safetensors",
667
+ "model.layers.65.self_attn.q_proj.weight": "model-00014-of-00022.safetensors",
668
+ "model.layers.65.self_attn.v_proj.weight": "model-00014-of-00022.safetensors",
669
+ "model.layers.66.input_layernorm.weight": "model-00014-of-00022.safetensors",
670
+ "model.layers.66.mlp.down_proj.weight": "model-00014-of-00022.safetensors",
671
+ "model.layers.66.mlp.gate_up_proj.weight": "model-00015-of-00022.safetensors",
672
+ "model.layers.66.post_attention_layernorm.weight": "model-00015-of-00022.safetensors",
673
+ "model.layers.66.post_mlp_layernorm.weight": "model-00015-of-00022.safetensors",
674
+ "model.layers.66.post_self_attn_layernorm.weight": "model-00015-of-00022.safetensors",
675
+ "model.layers.66.self_attn.k_proj.weight": "model-00015-of-00022.safetensors",
676
+ "model.layers.66.self_attn.o_proj.weight": "model-00015-of-00022.safetensors",
677
+ "model.layers.66.self_attn.q_proj.weight": "model-00015-of-00022.safetensors",
678
+ "model.layers.66.self_attn.v_proj.weight": "model-00015-of-00022.safetensors",
679
+ "model.layers.67.input_layernorm.weight": "model-00015-of-00022.safetensors",
680
+ "model.layers.67.mlp.down_proj.weight": "model-00015-of-00022.safetensors",
681
+ "model.layers.67.mlp.gate_up_proj.weight": "model-00015-of-00022.safetensors",
682
+ "model.layers.67.post_attention_layernorm.weight": "model-00015-of-00022.safetensors",
683
+ "model.layers.67.post_mlp_layernorm.weight": "model-00015-of-00022.safetensors",
684
+ "model.layers.67.post_self_attn_layernorm.weight": "model-00015-of-00022.safetensors",
685
+ "model.layers.67.self_attn.k_proj.weight": "model-00015-of-00022.safetensors",
686
+ "model.layers.67.self_attn.o_proj.weight": "model-00015-of-00022.safetensors",
687
+ "model.layers.67.self_attn.q_proj.weight": "model-00015-of-00022.safetensors",
688
+ "model.layers.67.self_attn.v_proj.weight": "model-00015-of-00022.safetensors",
689
+ "model.layers.68.input_layernorm.weight": "model-00015-of-00022.safetensors",
690
+ "model.layers.68.mlp.down_proj.weight": "model-00015-of-00022.safetensors",
691
+ "model.layers.68.mlp.gate_up_proj.weight": "model-00015-of-00022.safetensors",
692
+ "model.layers.68.post_attention_layernorm.weight": "model-00015-of-00022.safetensors",
693
+ "model.layers.68.post_mlp_layernorm.weight": "model-00015-of-00022.safetensors",
694
+ "model.layers.68.post_self_attn_layernorm.weight": "model-00015-of-00022.safetensors",
695
+ "model.layers.68.self_attn.k_proj.weight": "model-00015-of-00022.safetensors",
696
+ "model.layers.68.self_attn.o_proj.weight": "model-00015-of-00022.safetensors",
697
+ "model.layers.68.self_attn.q_proj.weight": "model-00015-of-00022.safetensors",
698
+ "model.layers.68.self_attn.v_proj.weight": "model-00015-of-00022.safetensors",
699
+ "model.layers.69.input_layernorm.weight": "model-00015-of-00022.safetensors",
700
+ "model.layers.69.mlp.down_proj.weight": "model-00015-of-00022.safetensors",
701
+ "model.layers.69.mlp.gate_up_proj.weight": "model-00015-of-00022.safetensors",
702
+ "model.layers.69.post_attention_layernorm.weight": "model-00015-of-00022.safetensors",
703
+ "model.layers.69.post_mlp_layernorm.weight": "model-00015-of-00022.safetensors",
704
+ "model.layers.69.post_self_attn_layernorm.weight": "model-00015-of-00022.safetensors",
705
+ "model.layers.69.self_attn.k_proj.weight": "model-00015-of-00022.safetensors",
706
+ "model.layers.69.self_attn.o_proj.weight": "model-00015-of-00022.safetensors",
707
+ "model.layers.69.self_attn.q_proj.weight": "model-00015-of-00022.safetensors",
708
+ "model.layers.69.self_attn.v_proj.weight": "model-00015-of-00022.safetensors",
709
+ "model.layers.70.input_layernorm.weight": "model-00015-of-00022.safetensors",
710
+ "model.layers.70.mlp.down_proj.weight": "model-00015-of-00022.safetensors",
711
+ "model.layers.70.mlp.gate_up_proj.weight": "model-00015-of-00022.safetensors",
712
+ "model.layers.70.post_attention_layernorm.weight": "model-00015-of-00022.safetensors",
713
+ "model.layers.70.post_mlp_layernorm.weight": "model-00015-of-00022.safetensors",
714
+ "model.layers.70.post_self_attn_layernorm.weight": "model-00015-of-00022.safetensors",
715
+ "model.layers.70.self_attn.k_proj.weight": "model-00015-of-00022.safetensors",
716
+ "model.layers.70.self_attn.o_proj.weight": "model-00015-of-00022.safetensors",
717
+ "model.layers.70.self_attn.q_proj.weight": "model-00015-of-00022.safetensors",
718
+ "model.layers.70.self_attn.v_proj.weight": "model-00015-of-00022.safetensors",
719
+ "model.layers.71.input_layernorm.weight": "model-00015-of-00022.safetensors",
720
+ "model.layers.71.mlp.down_proj.weight": "model-00015-of-00022.safetensors",
721
+ "model.layers.71.mlp.gate_up_proj.weight": "model-00016-of-00022.safetensors",
722
+ "model.layers.71.post_attention_layernorm.weight": "model-00016-of-00022.safetensors",
723
+ "model.layers.71.post_mlp_layernorm.weight": "model-00016-of-00022.safetensors",
724
+ "model.layers.71.post_self_attn_layernorm.weight": "model-00016-of-00022.safetensors",
725
+ "model.layers.71.self_attn.k_proj.weight": "model-00016-of-00022.safetensors",
726
+ "model.layers.71.self_attn.o_proj.weight": "model-00016-of-00022.safetensors",
727
+ "model.layers.71.self_attn.q_proj.weight": "model-00016-of-00022.safetensors",
728
+ "model.layers.71.self_attn.v_proj.weight": "model-00016-of-00022.safetensors",
729
+ "model.layers.72.input_layernorm.weight": "model-00016-of-00022.safetensors",
730
+ "model.layers.72.mlp.down_proj.weight": "model-00016-of-00022.safetensors",
731
+ "model.layers.72.mlp.gate_up_proj.weight": "model-00016-of-00022.safetensors",
732
+ "model.layers.72.post_attention_layernorm.weight": "model-00016-of-00022.safetensors",
733
+ "model.layers.72.post_mlp_layernorm.weight": "model-00016-of-00022.safetensors",
734
+ "model.layers.72.post_self_attn_layernorm.weight": "model-00016-of-00022.safetensors",
735
+ "model.layers.72.self_attn.k_proj.weight": "model-00016-of-00022.safetensors",
736
+ "model.layers.72.self_attn.o_proj.weight": "model-00016-of-00022.safetensors",
737
+ "model.layers.72.self_attn.q_proj.weight": "model-00016-of-00022.safetensors",
738
+ "model.layers.72.self_attn.v_proj.weight": "model-00016-of-00022.safetensors",
739
+ "model.layers.73.input_layernorm.weight": "model-00016-of-00022.safetensors",
740
+ "model.layers.73.mlp.down_proj.weight": "model-00016-of-00022.safetensors",
741
+ "model.layers.73.mlp.gate_up_proj.weight": "model-00016-of-00022.safetensors",
742
+ "model.layers.73.post_attention_layernorm.weight": "model-00016-of-00022.safetensors",
743
+ "model.layers.73.post_mlp_layernorm.weight": "model-00016-of-00022.safetensors",
744
+ "model.layers.73.post_self_attn_layernorm.weight": "model-00016-of-00022.safetensors",
745
+ "model.layers.73.self_attn.k_proj.weight": "model-00016-of-00022.safetensors",
746
+ "model.layers.73.self_attn.o_proj.weight": "model-00016-of-00022.safetensors",
747
+ "model.layers.73.self_attn.q_proj.weight": "model-00016-of-00022.safetensors",
748
+ "model.layers.73.self_attn.v_proj.weight": "model-00016-of-00022.safetensors",
749
+ "model.layers.74.input_layernorm.weight": "model-00016-of-00022.safetensors",
750
+ "model.layers.74.mlp.down_proj.weight": "model-00016-of-00022.safetensors",
751
+ "model.layers.74.post_attention_layernorm.weight": "model-00016-of-00022.safetensors",
752
+ "model.layers.74.post_mlp_layernorm.weight": "model-00016-of-00022.safetensors",
753
+ "model.layers.74.post_self_attn_layernorm.weight": "model-00016-of-00022.safetensors",
754
+ "model.layers.74.mlp.gate_up_proj.weight": "model-00016-of-00022.safetensors",
755
+ "model.layers.74.self_attn.k_proj.weight": "model-00016-of-00022.safetensors",
756
+ "model.layers.74.self_attn.o_proj.weight": "model-00016-of-00022.safetensors",
757
+ "model.layers.74.self_attn.q_proj.weight": "model-00016-of-00022.safetensors",
758
+ "model.layers.74.self_attn.v_proj.weight": "model-00016-of-00022.safetensors",
759
+ "model.layers.75.input_layernorm.weight": "model-00016-of-00022.safetensors",
760
+ "model.layers.75.mlp.down_proj.weight": "model-00016-of-00022.safetensors",
761
+ "model.layers.75.mlp.gate_up_proj.weight": "model-00016-of-00022.safetensors",
762
+ "model.layers.75.post_attention_layernorm.weight": "model-00016-of-00022.safetensors",
763
+ "model.layers.75.post_mlp_layernorm.weight": "model-00016-of-00022.safetensors",
764
+ "model.layers.75.post_self_attn_layernorm.weight": "model-00016-of-00022.safetensors",
765
+ "model.layers.75.self_attn.k_proj.weight": "model-00016-of-00022.safetensors",
766
+ "model.layers.75.self_attn.o_proj.weight": "model-00016-of-00022.safetensors",
767
+ "model.layers.75.self_attn.q_proj.weight": "model-00016-of-00022.safetensors",
768
+ "model.layers.75.self_attn.v_proj.weight": "model-00016-of-00022.safetensors",
769
+ "model.layers.76.input_layernorm.weight": "model-00016-of-00022.safetensors",
770
+ "model.layers.76.mlp.down_proj.weight": "model-00016-of-00022.safetensors",
771
+ "model.layers.76.mlp.gate_up_proj.weight": "model-00017-of-00022.safetensors",
772
+ "model.layers.76.post_attention_layernorm.weight": "model-00017-of-00022.safetensors",
773
+ "model.layers.76.post_mlp_layernorm.weight": "model-00017-of-00022.safetensors",
774
+ "model.layers.76.post_self_attn_layernorm.weight": "model-00017-of-00022.safetensors",
775
+ "model.layers.76.self_attn.k_proj.weight": "model-00017-of-00022.safetensors",
776
+ "model.layers.76.self_attn.o_proj.weight": "model-00017-of-00022.safetensors",
777
+ "model.layers.76.self_attn.q_proj.weight": "model-00017-of-00022.safetensors",
778
+ "model.layers.76.self_attn.v_proj.weight": "model-00017-of-00022.safetensors",
779
+ "model.layers.77.input_layernorm.weight": "model-00017-of-00022.safetensors",
780
+ "model.layers.77.mlp.down_proj.weight": "model-00017-of-00022.safetensors",
781
+ "model.layers.77.mlp.gate_up_proj.weight": "model-00017-of-00022.safetensors",
782
+ "model.layers.77.post_attention_layernorm.weight": "model-00017-of-00022.safetensors",
783
+ "model.layers.77.post_mlp_layernorm.weight": "model-00017-of-00022.safetensors",
784
+ "model.layers.77.post_self_attn_layernorm.weight": "model-00017-of-00022.safetensors",
785
+ "model.layers.77.self_attn.k_proj.weight": "model-00017-of-00022.safetensors",
786
+ "model.layers.77.self_attn.o_proj.weight": "model-00017-of-00022.safetensors",
787
+ "model.layers.77.self_attn.q_proj.weight": "model-00017-of-00022.safetensors",
788
+ "model.layers.77.self_attn.v_proj.weight": "model-00017-of-00022.safetensors",
789
+ "model.layers.78.input_layernorm.weight": "model-00017-of-00022.safetensors",
790
+ "model.layers.78.mlp.down_proj.weight": "model-00017-of-00022.safetensors",
791
+ "model.layers.78.mlp.gate_up_proj.weight": "model-00017-of-00022.safetensors",
792
+ "model.layers.78.post_attention_layernorm.weight": "model-00017-of-00022.safetensors",
793
+ "model.layers.78.post_mlp_layernorm.weight": "model-00017-of-00022.safetensors",
794
+ "model.layers.78.post_self_attn_layernorm.weight": "model-00017-of-00022.safetensors",
795
+ "model.layers.78.self_attn.k_proj.weight": "model-00017-of-00022.safetensors",
796
+ "model.layers.78.self_attn.o_proj.weight": "model-00017-of-00022.safetensors",
797
+ "model.layers.78.self_attn.q_proj.weight": "model-00017-of-00022.safetensors",
798
+ "model.layers.78.self_attn.v_proj.weight": "model-00017-of-00022.safetensors",
799
+ "model.layers.79.self_attn.k_proj.weight": "model-00017-of-00022.safetensors",
800
+ "model.layers.79.self_attn.o_proj.weight": "model-00017-of-00022.safetensors",
801
+ "model.layers.79.self_attn.q_proj.weight": "model-00017-of-00022.safetensors",
802
+ "model.layers.79.self_attn.v_proj.weight": "model-00017-of-00022.safetensors",
803
+ "model.layers.79.input_layernorm.weight": "model-00017-of-00022.safetensors",
804
+ "model.layers.79.mlp.down_proj.weight": "model-00017-of-00022.safetensors",
805
+ "model.layers.79.mlp.gate_up_proj.weight": "model-00017-of-00022.safetensors",
806
+ "model.layers.79.post_attention_layernorm.weight": "model-00017-of-00022.safetensors",
807
+ "model.layers.79.post_mlp_layernorm.weight": "model-00017-of-00022.safetensors",
808
+ "model.layers.79.post_self_attn_layernorm.weight": "model-00017-of-00022.safetensors",
809
+ "model.layers.80.input_layernorm.weight": "model-00017-of-00022.safetensors",
810
+ "model.layers.80.mlp.down_proj.weight": "model-00017-of-00022.safetensors",
811
+ "model.layers.80.mlp.gate_up_proj.weight": "model-00017-of-00022.safetensors",
812
+ "model.layers.80.post_attention_layernorm.weight": "model-00017-of-00022.safetensors",
813
+ "model.layers.80.post_mlp_layernorm.weight": "model-00017-of-00022.safetensors",
814
+ "model.layers.80.post_self_attn_layernorm.weight": "model-00017-of-00022.safetensors",
815
+ "model.layers.80.self_attn.k_proj.weight": "model-00017-of-00022.safetensors",
816
+ "model.layers.80.self_attn.o_proj.weight": "model-00017-of-00022.safetensors",
817
+ "model.layers.80.self_attn.q_proj.weight": "model-00017-of-00022.safetensors",
818
+ "model.layers.80.self_attn.v_proj.weight": "model-00017-of-00022.safetensors",
819
+ "model.layers.81.input_layernorm.weight": "model-00017-of-00022.safetensors",
820
+ "model.layers.81.mlp.down_proj.weight": "model-00017-of-00022.safetensors",
821
+ "model.layers.81.mlp.gate_up_proj.weight": "model-00018-of-00022.safetensors",
822
+ "model.layers.81.post_attention_layernorm.weight": "model-00018-of-00022.safetensors",
823
+ "model.layers.81.post_mlp_layernorm.weight": "model-00018-of-00022.safetensors",
824
+ "model.layers.81.post_self_attn_layernorm.weight": "model-00018-of-00022.safetensors",
825
+ "model.layers.81.self_attn.k_proj.weight": "model-00018-of-00022.safetensors",
826
+ "model.layers.81.self_attn.o_proj.weight": "model-00018-of-00022.safetensors",
827
+ "model.layers.81.self_attn.q_proj.weight": "model-00018-of-00022.safetensors",
828
+ "model.layers.81.self_attn.v_proj.weight": "model-00018-of-00022.safetensors",
829
+ "model.layers.82.input_layernorm.weight": "model-00018-of-00022.safetensors",
830
+ "model.layers.82.mlp.down_proj.weight": "model-00018-of-00022.safetensors",
831
+ "model.layers.82.mlp.gate_up_proj.weight": "model-00018-of-00022.safetensors",
832
+ "model.layers.82.post_attention_layernorm.weight": "model-00018-of-00022.safetensors",
833
+ "model.layers.82.post_mlp_layernorm.weight": "model-00018-of-00022.safetensors",
834
+ "model.layers.82.post_self_attn_layernorm.weight": "model-00018-of-00022.safetensors",
835
+ "model.layers.82.self_attn.k_proj.weight": "model-00018-of-00022.safetensors",
836
+ "model.layers.82.self_attn.o_proj.weight": "model-00018-of-00022.safetensors",
837
+ "model.layers.82.self_attn.q_proj.weight": "model-00018-of-00022.safetensors",
838
+ "model.layers.82.self_attn.v_proj.weight": "model-00018-of-00022.safetensors",
839
+ "model.layers.83.input_layernorm.weight": "model-00018-of-00022.safetensors",
840
+ "model.layers.83.mlp.down_proj.weight": "model-00018-of-00022.safetensors",
841
+ "model.layers.83.mlp.gate_up_proj.weight": "model-00018-of-00022.safetensors",
842
+ "model.layers.83.post_attention_layernorm.weight": "model-00018-of-00022.safetensors",
843
+ "model.layers.83.post_mlp_layernorm.weight": "model-00018-of-00022.safetensors",
844
+ "model.layers.83.post_self_attn_layernorm.weight": "model-00018-of-00022.safetensors",
845
+ "model.layers.83.self_attn.k_proj.weight": "model-00018-of-00022.safetensors",
846
+ "model.layers.83.self_attn.o_proj.weight": "model-00018-of-00022.safetensors",
847
+ "model.layers.83.self_attn.q_proj.weight": "model-00018-of-00022.safetensors",
848
+ "model.layers.83.self_attn.v_proj.weight": "model-00018-of-00022.safetensors",
849
+ "model.layers.84.self_attn.k_proj.weight": "model-00018-of-00022.safetensors",
850
+ "model.layers.84.self_attn.q_proj.weight": "model-00018-of-00022.safetensors",
851
+ "model.layers.84.self_attn.v_proj.weight": "model-00018-of-00022.safetensors",
852
+ "model.layers.84.input_layernorm.weight": "model-00018-of-00022.safetensors",
853
+ "model.layers.84.mlp.down_proj.weight": "model-00018-of-00022.safetensors",
854
+ "model.layers.84.mlp.gate_up_proj.weight": "model-00018-of-00022.safetensors",
855
+ "model.layers.84.post_attention_layernorm.weight": "model-00018-of-00022.safetensors",
856
+ "model.layers.84.post_mlp_layernorm.weight": "model-00018-of-00022.safetensors",
857
+ "model.layers.84.post_self_attn_layernorm.weight": "model-00018-of-00022.safetensors",
858
+ "model.layers.84.self_attn.o_proj.weight": "model-00018-of-00022.safetensors",
859
+ "model.layers.85.input_layernorm.weight": "model-00018-of-00022.safetensors",
860
+ "model.layers.85.mlp.down_proj.weight": "model-00018-of-00022.safetensors",
861
+ "model.layers.85.mlp.gate_up_proj.weight": "model-00018-of-00022.safetensors",
862
+ "model.layers.85.post_attention_layernorm.weight": "model-00018-of-00022.safetensors",
863
+ "model.layers.85.post_mlp_layernorm.weight": "model-00018-of-00022.safetensors",
864
+ "model.layers.85.post_self_attn_layernorm.weight": "model-00018-of-00022.safetensors",
865
+ "model.layers.85.self_attn.k_proj.weight": "model-00018-of-00022.safetensors",
866
+ "model.layers.85.self_attn.o_proj.weight": "model-00018-of-00022.safetensors",
867
+ "model.layers.85.self_attn.q_proj.weight": "model-00018-of-00022.safetensors",
868
+ "model.layers.85.self_attn.v_proj.weight": "model-00018-of-00022.safetensors",
869
+ "model.layers.86.input_layernorm.weight": "model-00018-of-00022.safetensors",
870
+ "model.layers.86.mlp.down_proj.weight": "model-00018-of-00022.safetensors",
871
+ "model.layers.86.mlp.gate_up_proj.weight": "model-00019-of-00022.safetensors",
872
+ "model.layers.86.post_attention_layernorm.weight": "model-00019-of-00022.safetensors",
873
+ "model.layers.86.post_mlp_layernorm.weight": "model-00019-of-00022.safetensors",
874
+ "model.layers.86.post_self_attn_layernorm.weight": "model-00019-of-00022.safetensors",
875
+ "model.layers.86.self_attn.k_proj.weight": "model-00019-of-00022.safetensors",
876
+ "model.layers.86.self_attn.o_proj.weight": "model-00019-of-00022.safetensors",
877
+ "model.layers.86.self_attn.q_proj.weight": "model-00019-of-00022.safetensors",
878
+ "model.layers.86.self_attn.v_proj.weight": "model-00019-of-00022.safetensors",
879
+ "model.layers.87.input_layernorm.weight": "model-00019-of-00022.safetensors",
880
+ "model.layers.87.mlp.down_proj.weight": "model-00019-of-00022.safetensors",
881
+ "model.layers.87.mlp.gate_up_proj.weight": "model-00019-of-00022.safetensors",
882
+ "model.layers.87.post_attention_layernorm.weight": "model-00019-of-00022.safetensors",
883
+ "model.layers.87.post_mlp_layernorm.weight": "model-00019-of-00022.safetensors",
884
+ "model.layers.87.post_self_attn_layernorm.weight": "model-00019-of-00022.safetensors",
885
+ "model.layers.87.self_attn.k_proj.weight": "model-00019-of-00022.safetensors",
886
+ "model.layers.87.self_attn.o_proj.weight": "model-00019-of-00022.safetensors",
887
+ "model.layers.87.self_attn.q_proj.weight": "model-00019-of-00022.safetensors",
888
+ "model.layers.87.self_attn.v_proj.weight": "model-00019-of-00022.safetensors",
889
+ "model.layers.88.input_layernorm.weight": "model-00019-of-00022.safetensors",
890
+ "model.layers.88.mlp.down_proj.weight": "model-00019-of-00022.safetensors",
891
+ "model.layers.88.mlp.gate_up_proj.weight": "model-00019-of-00022.safetensors",
892
+ "model.layers.88.post_attention_layernorm.weight": "model-00019-of-00022.safetensors",
893
+ "model.layers.88.post_mlp_layernorm.weight": "model-00019-of-00022.safetensors",
894
+ "model.layers.88.post_self_attn_layernorm.weight": "model-00019-of-00022.safetensors",
895
+ "model.layers.88.self_attn.k_proj.weight": "model-00019-of-00022.safetensors",
896
+ "model.layers.88.self_attn.o_proj.weight": "model-00019-of-00022.safetensors",
897
+ "model.layers.88.self_attn.q_proj.weight": "model-00019-of-00022.safetensors",
898
+ "model.layers.88.self_attn.v_proj.weight": "model-00019-of-00022.safetensors",
899
+ "model.layers.89.input_layernorm.weight": "model-00019-of-00022.safetensors",
900
+ "model.layers.89.mlp.down_proj.weight": "model-00019-of-00022.safetensors",
901
+ "model.layers.89.mlp.gate_up_proj.weight": "model-00019-of-00022.safetensors",
902
+ "model.layers.89.post_attention_layernorm.weight": "model-00019-of-00022.safetensors",
903
+ "model.layers.89.post_mlp_layernorm.weight": "model-00019-of-00022.safetensors",
904
+ "model.layers.89.post_self_attn_layernorm.weight": "model-00019-of-00022.safetensors",
905
+ "model.layers.89.self_attn.k_proj.weight": "model-00019-of-00022.safetensors",
906
+ "model.layers.89.self_attn.o_proj.weight": "model-00019-of-00022.safetensors",
907
+ "model.layers.89.self_attn.q_proj.weight": "model-00019-of-00022.safetensors",
908
+ "model.layers.89.self_attn.v_proj.weight": "model-00019-of-00022.safetensors",
909
+ "model.layers.90.input_layernorm.weight": "model-00019-of-00022.safetensors",
910
+ "model.layers.90.mlp.down_proj.weight": "model-00019-of-00022.safetensors",
911
+ "model.layers.90.mlp.gate_up_proj.weight": "model-00019-of-00022.safetensors",
912
+ "model.layers.90.post_attention_layernorm.weight": "model-00019-of-00022.safetensors",
913
+ "model.layers.90.post_mlp_layernorm.weight": "model-00019-of-00022.safetensors",
914
+ "model.layers.90.post_self_attn_layernorm.weight": "model-00019-of-00022.safetensors",
915
+ "model.layers.90.self_attn.k_proj.weight": "model-00019-of-00022.safetensors",
916
+ "model.layers.90.self_attn.o_proj.weight": "model-00019-of-00022.safetensors",
917
+ "model.layers.90.self_attn.q_proj.weight": "model-00019-of-00022.safetensors",
918
+ "model.layers.90.self_attn.v_proj.weight": "model-00019-of-00022.safetensors",
919
+ "model.layers.91.input_layernorm.weight": "model-00019-of-00022.safetensors",
920
+ "model.layers.91.mlp.down_proj.weight": "model-00019-of-00022.safetensors",
921
+ "model.layers.91.mlp.gate_up_proj.weight": "model-00020-of-00022.safetensors",
922
+ "model.layers.91.post_attention_layernorm.weight": "model-00020-of-00022.safetensors",
923
+ "model.layers.91.post_mlp_layernorm.weight": "model-00020-of-00022.safetensors",
924
+ "model.layers.91.post_self_attn_layernorm.weight": "model-00020-of-00022.safetensors",
925
+ "model.layers.91.self_attn.k_proj.weight": "model-00020-of-00022.safetensors",
926
+ "model.layers.91.self_attn.o_proj.weight": "model-00020-of-00022.safetensors",
927
+ "model.layers.91.self_attn.q_proj.weight": "model-00020-of-00022.safetensors",
928
+ "model.layers.91.self_attn.v_proj.weight": "model-00020-of-00022.safetensors",
929
+ "model.layers.92.input_layernorm.weight": "model-00020-of-00022.safetensors",
930
+ "model.layers.92.mlp.down_proj.weight": "model-00020-of-00022.safetensors",
931
+ "model.layers.92.mlp.gate_up_proj.weight": "model-00020-of-00022.safetensors",
932
+ "model.layers.92.post_attention_layernorm.weight": "model-00020-of-00022.safetensors",
933
+ "model.layers.92.post_mlp_layernorm.weight": "model-00020-of-00022.safetensors",
934
+ "model.layers.92.post_self_attn_layernorm.weight": "model-00020-of-00022.safetensors",
935
+ "model.layers.92.self_attn.k_proj.weight": "model-00020-of-00022.safetensors",
936
+ "model.layers.92.self_attn.o_proj.weight": "model-00020-of-00022.safetensors",
937
+ "model.layers.92.self_attn.q_proj.weight": "model-00020-of-00022.safetensors",
938
+ "model.layers.92.self_attn.v_proj.weight": "model-00020-of-00022.safetensors",
939
+ "model.layers.93.input_layernorm.weight": "model-00020-of-00022.safetensors",
940
+ "model.layers.93.mlp.down_proj.weight": "model-00020-of-00022.safetensors",
941
+ "model.layers.93.post_attention_layernorm.weight": "model-00020-of-00022.safetensors",
942
+ "model.layers.93.post_mlp_layernorm.weight": "model-00020-of-00022.safetensors",
943
+ "model.layers.93.post_self_attn_layernorm.weight": "model-00020-of-00022.safetensors",
944
+ "model.layers.93.mlp.gate_up_proj.weight": "model-00020-of-00022.safetensors",
945
+ "model.layers.93.self_attn.k_proj.weight": "model-00020-of-00022.safetensors",
946
+ "model.layers.93.self_attn.o_proj.weight": "model-00020-of-00022.safetensors",
947
+ "model.layers.93.self_attn.q_proj.weight": "model-00020-of-00022.safetensors",
948
+ "model.layers.93.self_attn.v_proj.weight": "model-00020-of-00022.safetensors",
949
+ "model.layers.94.input_layernorm.weight": "model-00020-of-00022.safetensors",
950
+ "model.layers.94.mlp.down_proj.weight": "model-00020-of-00022.safetensors",
951
+ "model.layers.94.mlp.gate_up_proj.weight": "model-00020-of-00022.safetensors",
952
+ "model.layers.94.post_attention_layernorm.weight": "model-00020-of-00022.safetensors",
953
+ "model.layers.94.post_mlp_layernorm.weight": "model-00020-of-00022.safetensors",
954
+ "model.layers.94.post_self_attn_layernorm.weight": "model-00020-of-00022.safetensors",
955
+ "model.layers.94.self_attn.k_proj.weight": "model-00020-of-00022.safetensors",
956
+ "model.layers.94.self_attn.o_proj.weight": "model-00020-of-00022.safetensors",
957
+ "model.layers.94.self_attn.q_proj.weight": "model-00020-of-00022.safetensors",
958
+ "model.layers.94.self_attn.v_proj.weight": "model-00020-of-00022.safetensors",
959
+ "model.layers.95.input_layernorm.weight": "model-00020-of-00022.safetensors",
960
+ "model.layers.95.mlp.down_proj.weight": "model-00020-of-00022.safetensors",
961
+ "model.layers.95.mlp.gate_up_proj.weight": "model-00020-of-00022.safetensors",
962
+ "model.layers.95.post_attention_layernorm.weight": "model-00020-of-00022.safetensors",
963
+ "model.layers.95.post_mlp_layernorm.weight": "model-00020-of-00022.safetensors",
964
+ "model.layers.95.post_self_attn_layernorm.weight": "model-00020-of-00022.safetensors",
965
+ "model.layers.95.self_attn.k_proj.weight": "model-00020-of-00022.safetensors",
966
+ "model.layers.95.self_attn.o_proj.weight": "model-00020-of-00022.safetensors",
967
+ "model.layers.95.self_attn.q_proj.weight": "model-00020-of-00022.safetensors",
968
+ "model.layers.95.self_attn.v_proj.weight": "model-00020-of-00022.safetensors",
969
+ "model.layers.96.input_layernorm.weight": "model-00020-of-00022.safetensors",
970
+ "model.layers.96.mlp.down_proj.weight": "model-00020-of-00022.safetensors",
971
+ "model.layers.96.mlp.gate_up_proj.weight": "model-00021-of-00022.safetensors",
972
+ "model.layers.96.post_attention_layernorm.weight": "model-00021-of-00022.safetensors",
973
+ "model.layers.96.post_mlp_layernorm.weight": "model-00021-of-00022.safetensors",
974
+ "model.layers.96.post_self_attn_layernorm.weight": "model-00021-of-00022.safetensors",
975
+ "model.layers.96.self_attn.k_proj.weight": "model-00021-of-00022.safetensors",
976
+ "model.layers.96.self_attn.o_proj.weight": "model-00021-of-00022.safetensors",
977
+ "model.layers.96.self_attn.q_proj.weight": "model-00021-of-00022.safetensors",
978
+ "model.layers.96.self_attn.v_proj.weight": "model-00021-of-00022.safetensors",
979
+ "model.layers.97.input_layernorm.weight": "model-00021-of-00022.safetensors",
980
+ "model.layers.97.mlp.down_proj.weight": "model-00021-of-00022.safetensors",
981
+ "model.layers.97.mlp.gate_up_proj.weight": "model-00021-of-00022.safetensors",
982
+ "model.layers.97.post_attention_layernorm.weight": "model-00021-of-00022.safetensors",
983
+ "model.layers.97.post_mlp_layernorm.weight": "model-00021-of-00022.safetensors",
984
+ "model.layers.97.post_self_attn_layernorm.weight": "model-00021-of-00022.safetensors",
985
+ "model.layers.97.self_attn.k_proj.weight": "model-00021-of-00022.safetensors",
986
+ "model.layers.97.self_attn.o_proj.weight": "model-00021-of-00022.safetensors",
987
+ "model.layers.97.self_attn.q_proj.weight": "model-00021-of-00022.safetensors",
988
+ "model.layers.97.self_attn.v_proj.weight": "model-00021-of-00022.safetensors",
989
+ "model.layers.98.input_layernorm.weight": "model-00021-of-00022.safetensors",
990
+ "model.layers.98.mlp.down_proj.weight": "model-00021-of-00022.safetensors",
991
+ "model.layers.98.mlp.gate_up_proj.weight": "model-00021-of-00022.safetensors",
992
+ "model.layers.98.post_attention_layernorm.weight": "model-00021-of-00022.safetensors",
993
+ "model.layers.98.post_mlp_layernorm.weight": "model-00021-of-00022.safetensors",
994
+ "model.layers.98.post_self_attn_layernorm.weight": "model-00021-of-00022.safetensors",
995
+ "model.layers.98.self_attn.k_proj.weight": "model-00021-of-00022.safetensors",
996
+ "model.layers.98.self_attn.o_proj.weight": "model-00021-of-00022.safetensors",
997
+ "model.layers.98.self_attn.q_proj.weight": "model-00021-of-00022.safetensors",
998
+ "model.layers.98.self_attn.v_proj.weight": "model-00021-of-00022.safetensors",
999
+ "model.layers.99.input_layernorm.weight": "model-00021-of-00022.safetensors",
1000
+ "model.layers.99.mlp.down_proj.weight": "model-00021-of-00022.safetensors",
1001
+ "model.layers.99.mlp.gate_up_proj.weight": "model-00021-of-00022.safetensors",
1002
+ "model.layers.99.post_attention_layernorm.weight": "model-00021-of-00022.safetensors",
1003
+ "model.layers.99.post_mlp_layernorm.weight": "model-00021-of-00022.safetensors",
1004
+ "model.layers.99.post_self_attn_layernorm.weight": "model-00021-of-00022.safetensors",
1005
+ "model.layers.99.self_attn.k_proj.weight": "model-00021-of-00022.safetensors",
1006
+ "model.layers.99.self_attn.o_proj.weight": "model-00021-of-00022.safetensors",
1007
+ "model.layers.99.self_attn.q_proj.weight": "model-00021-of-00022.safetensors",
1008
+ "model.layers.99.self_attn.v_proj.weight": "model-00021-of-00022.safetensors",
1009
+ "model.layers.100.input_layernorm.weight": "model-00021-of-00022.safetensors",
1010
+ "model.layers.100.mlp.down_proj.weight": "model-00021-of-00022.safetensors",
1011
+ "model.layers.100.mlp.gate_up_proj.weight": "model-00021-of-00022.safetensors",
1012
+ "model.layers.100.post_attention_layernorm.weight": "model-00021-of-00022.safetensors",
1013
+ "model.layers.100.post_mlp_layernorm.weight": "model-00021-of-00022.safetensors",
1014
+ "model.layers.100.post_self_attn_layernorm.weight": "model-00021-of-00022.safetensors",
1015
+ "model.layers.100.self_attn.k_proj.weight": "model-00021-of-00022.safetensors",
1016
+ "model.layers.100.self_attn.o_proj.weight": "model-00021-of-00022.safetensors",
1017
+ "model.layers.100.self_attn.q_proj.weight": "model-00021-of-00022.safetensors",
1018
+ "model.layers.100.self_attn.v_proj.weight": "model-00021-of-00022.safetensors",
1019
+ "model.layers.101.input_layernorm.weight": "model-00021-of-00022.safetensors",
1020
+ "model.layers.101.mlp.down_proj.weight": "model-00021-of-00022.safetensors",
1021
+ "model.layers.101.mlp.gate_up_proj.weight": "model-00022-of-00022.safetensors",
1022
+ "model.layers.101.post_attention_layernorm.weight": "model-00022-of-00022.safetensors",
1023
+ "model.layers.101.post_mlp_layernorm.weight": "model-00022-of-00022.safetensors",
1024
+ "model.layers.101.post_self_attn_layernorm.weight": "model-00022-of-00022.safetensors",
1025
+ "model.layers.101.self_attn.k_proj.weight": "model-00022-of-00022.safetensors",
1026
+ "model.layers.101.self_attn.o_proj.weight": "model-00022-of-00022.safetensors",
1027
+ "model.layers.101.self_attn.q_proj.weight": "model-00022-of-00022.safetensors",
1028
+ "model.layers.101.self_attn.v_proj.weight": "model-00022-of-00022.safetensors",
1029
+ "model.layers.102.input_layernorm.weight": "model-00022-of-00022.safetensors",
1030
+ "model.layers.102.mlp.down_proj.weight": "model-00022-of-00022.safetensors",
1031
+ "model.layers.102.mlp.gate_up_proj.weight": "model-00022-of-00022.safetensors",
1032
+ "model.layers.102.post_attention_layernorm.weight": "model-00022-of-00022.safetensors",
1033
+ "model.layers.102.post_mlp_layernorm.weight": "model-00022-of-00022.safetensors",
1034
+ "model.layers.102.post_self_attn_layernorm.weight": "model-00022-of-00022.safetensors",
1035
+ "model.layers.102.self_attn.k_proj.weight": "model-00022-of-00022.safetensors",
1036
+ "model.layers.102.self_attn.o_proj.weight": "model-00022-of-00022.safetensors",
1037
+ "model.layers.102.self_attn.q_proj.weight": "model-00022-of-00022.safetensors",
1038
+ "model.layers.102.self_attn.v_proj.weight": "model-00022-of-00022.safetensors",
1039
+ "model.layers.103.self_attn.k_proj.weight": "model-00022-of-00022.safetensors",
1040
+ "model.layers.103.self_attn.q_proj.weight": "model-00022-of-00022.safetensors",
1041
+ "model.layers.103.self_attn.v_proj.weight": "model-00022-of-00022.safetensors",
1042
+ "model.layers.103.input_layernorm.weight": "model-00022-of-00022.safetensors",
1043
+ "model.layers.103.mlp.down_proj.weight": "model-00022-of-00022.safetensors",
1044
+ "model.layers.103.mlp.gate_up_proj.weight": "model-00022-of-00022.safetensors",
1045
+ "model.layers.103.post_attention_layernorm.weight": "model-00022-of-00022.safetensors",
1046
+ "model.layers.103.post_mlp_layernorm.weight": "model-00022-of-00022.safetensors",
1047
+ "model.layers.103.post_self_attn_layernorm.weight": "model-00022-of-00022.safetensors",
1048
+ "model.layers.103.self_attn.o_proj.weight": "model-00022-of-00022.safetensors"
1049
+ }
1050
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "[MASK]",
5
+ "[gMASK]",
6
+ "[sMASK]",
7
+ "<sop>",
8
+ "<eop>",
9
+ "<|system|>",
10
+ "<|user|>",
11
+ "<|assistant|>",
12
+ "<|observation|>",
13
+ "<|begin_of_image|>",
14
+ "<|end_of_image|>",
15
+ "<|begin_of_video|>",
16
+ "<|end_of_video|>"
17
+ ],
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
3
+ size 19966496
tokenizer_config.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151329": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151330": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151331": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151332": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151333": {
36
+ "content": "<sop>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151334": {
44
+ "content": "<eop>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151335": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151336": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151337": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151338": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151339": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151340": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151341": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151342": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ }
115
+ },
116
+ "additional_special_tokens": [
117
+ "<|endoftext|>",
118
+ "[MASK]",
119
+ "[gMASK]",
120
+ "[sMASK]",
121
+ "<sop>",
122
+ "<eop>",
123
+ "<|system|>",
124
+ "<|user|>",
125
+ "<|assistant|>",
126
+ "<|observation|>",
127
+ "<|begin_of_image|>",
128
+ "<|end_of_image|>",
129
+ "<|begin_of_video|>",
130
+ "<|end_of_video|>"
131
+ ],
132
+ "clean_up_tokenization_spaces": false,
133
+ "do_lower_case": false,
134
+ "eos_token": "<|endoftext|>",
135
+ "extra_special_tokens": {},
136
+ "model_input_names": [
137
+ "input_ids",
138
+ "attention_mask"
139
+ ],
140
+ "model_max_length": 128000,
141
+ "pad_token": "<|endoftext|>",
142
+ "padding_side": "left",
143
+ "remove_space": false,
144
+ "tokenizer_class": "PreTrainedTokenizerFast"
145
+ }