amyeroberts HF staff jbochi commited on
Commit
201888b
0 Parent(s):

Duplicate from jbochi/madlad400-10b-mt

Browse files

Co-authored-by: J Bochi <[email protected]>

.gitattributes ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
37
+ *.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,621 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - multilingual
5
+ - en
6
+ - ru
7
+ - es
8
+ - fr
9
+ - de
10
+ - it
11
+ - pt
12
+ - pl
13
+ - nl
14
+ - vi
15
+ - tr
16
+ - sv
17
+ - id
18
+ - ro
19
+ - cs
20
+ - zh
21
+ - hu
22
+ - ja
23
+ - th
24
+ - fi
25
+ - fa
26
+ - uk
27
+ - da
28
+ - el
29
+ - "no"
30
+ - bg
31
+ - sk
32
+ - ko
33
+ - ar
34
+ - lt
35
+ - ca
36
+ - sl
37
+ - he
38
+ - et
39
+ - lv
40
+ - hi
41
+ - sq
42
+ - ms
43
+ - az
44
+ - sr
45
+ - ta
46
+ - hr
47
+ - kk
48
+ - is
49
+ - ml
50
+ - mr
51
+ - te
52
+ - af
53
+ - gl
54
+ - fil
55
+ - be
56
+ - mk
57
+ - eu
58
+ - bn
59
+ - ka
60
+ - mn
61
+ - bs
62
+ - uz
63
+ - ur
64
+ - sw
65
+ - yue
66
+ - ne
67
+ - kn
68
+ - kaa
69
+ - gu
70
+ - si
71
+ - cy
72
+ - eo
73
+ - la
74
+ - hy
75
+ - ky
76
+ - tg
77
+ - ga
78
+ - mt
79
+ - my
80
+ - km
81
+ - tt
82
+ - so
83
+ - ku
84
+ - ps
85
+ - pa
86
+ - rw
87
+ - lo
88
+ - ha
89
+ - dv
90
+ - fy
91
+ - lb
92
+ - ckb
93
+ - mg
94
+ - gd
95
+ - am
96
+ - ug
97
+ - ht
98
+ - grc
99
+ - hmn
100
+ - sd
101
+ - jv
102
+ - mi
103
+ - tk
104
+ - ceb
105
+ - yi
106
+ - ba
107
+ - fo
108
+ - or
109
+ - xh
110
+ - su
111
+ - kl
112
+ - ny
113
+ - sm
114
+ - sn
115
+ - co
116
+ - zu
117
+ - ig
118
+ - yo
119
+ - pap
120
+ - st
121
+ - haw
122
+ - as
123
+ - oc
124
+ - cv
125
+ - lus
126
+ - tet
127
+ - gsw
128
+ - sah
129
+ - br
130
+ - rm
131
+ - sa
132
+ - bo
133
+ - om
134
+ - se
135
+ - ce
136
+ - cnh
137
+ - ilo
138
+ - hil
139
+ - udm
140
+ - os
141
+ - lg
142
+ - ti
143
+ - vec
144
+ - ts
145
+ - tyv
146
+ - kbd
147
+ - ee
148
+ - iba
149
+ - av
150
+ - kha
151
+ - to
152
+ - tn
153
+ - nso
154
+ - fj
155
+ - zza
156
+ - ak
157
+ - ada
158
+ - otq
159
+ - dz
160
+ - bua
161
+ - cfm
162
+ - ln
163
+ - chm
164
+ - gn
165
+ - krc
166
+ - wa
167
+ - hif
168
+ - yua
169
+ - srn
170
+ - war
171
+ - rom
172
+ - bik
173
+ - pam
174
+ - sg
175
+ - lu
176
+ - ady
177
+ - kbp
178
+ - syr
179
+ - ltg
180
+ - myv
181
+ - iso
182
+ - kac
183
+ - bho
184
+ - ay
185
+ - kum
186
+ - qu
187
+ - za
188
+ - pag
189
+ - ngu
190
+ - ve
191
+ - pck
192
+ - zap
193
+ - tyz
194
+ - hui
195
+ - bbc
196
+ - tzo
197
+ - tiv
198
+ - ksd
199
+ - gom
200
+ - min
201
+ - ang
202
+ - nhe
203
+ - bgp
204
+ - nzi
205
+ - nnb
206
+ - nv
207
+ - zxx
208
+ - bci
209
+ - kv
210
+ - new
211
+ - mps
212
+ - alt
213
+ - meu
214
+ - bew
215
+ - fon
216
+ - iu
217
+ - abt
218
+ - mgh
219
+ - mnw
220
+ - tvl
221
+ - dov
222
+ - tlh
223
+ - ho
224
+ - kw
225
+ - mrj
226
+ - meo
227
+ - crh
228
+ - mbt
229
+ - emp
230
+ - ace
231
+ - ium
232
+ - mam
233
+ - gym
234
+ - mai
235
+ - crs
236
+ - pon
237
+ - ubu
238
+ - fip
239
+ - quc
240
+ - gv
241
+ - kj
242
+ - btx
243
+ - ape
244
+ - chk
245
+ - rcf
246
+ - shn
247
+ - tzh
248
+ - mdf
249
+ - ppk
250
+ - ss
251
+ - gag
252
+ - cab
253
+ - kri
254
+ - seh
255
+ - ibb
256
+ - tbz
257
+ - bru
258
+ - enq
259
+ - ach
260
+ - cuk
261
+ - kmb
262
+ - wo
263
+ - kek
264
+ - qub
265
+ - tab
266
+ - bts
267
+ - kos
268
+ - rwo
269
+ - cak
270
+ - tuc
271
+ - bum
272
+ - cjk
273
+ - gil
274
+ - stq
275
+ - tsg
276
+ - quh
277
+ - mak
278
+ - arn
279
+ - ban
280
+ - jiv
281
+ - sja
282
+ - yap
283
+ - tcy
284
+ - toj
285
+ - twu
286
+ - xal
287
+ - amu
288
+ - rmc
289
+ - hus
290
+ - nia
291
+ - kjh
292
+ - bm
293
+ - guh
294
+ - mas
295
+ - acf
296
+ - dtp
297
+ - ksw
298
+ - bzj
299
+ - din
300
+ - zne
301
+ - mad
302
+ - msi
303
+ - mag
304
+ - mkn
305
+ - kg
306
+ - lhu
307
+ - ch
308
+ - qvi
309
+ - mh
310
+ - djk
311
+ - sus
312
+ - mfe
313
+ - srm
314
+ - dyu
315
+ - ctu
316
+ - gui
317
+ - pau
318
+ - inb
319
+ - bi
320
+ - mni
321
+ - guc
322
+ - jam
323
+ - wal
324
+ - jac
325
+ - bas
326
+ - gor
327
+ - skr
328
+ - nyu
329
+ - noa
330
+ - sda
331
+ - gub
332
+ - nog
333
+ - cni
334
+ - teo
335
+ - tdx
336
+ - sxn
337
+ - rki
338
+ - nr
339
+ - frp
340
+ - alz
341
+ - taj
342
+ - lrc
343
+ - cce
344
+ - rn
345
+ - jvn
346
+ - hvn
347
+ - nij
348
+ - dwr
349
+ - izz
350
+ - msm
351
+ - bus
352
+ - ktu
353
+ - chr
354
+ - maz
355
+ - tzj
356
+ - suz
357
+ - knj
358
+ - bim
359
+ - gvl
360
+ - bqc
361
+ - tca
362
+ - pis
363
+ - prk
364
+ - laj
365
+ - mel
366
+ - qxr
367
+ - niq
368
+ - ahk
369
+ - shp
370
+ - hne
371
+ - spp
372
+ - koi
373
+ - krj
374
+ - quf
375
+ - luz
376
+ - agr
377
+ - tsc
378
+ - mqy
379
+ - gof
380
+ - gbm
381
+ - miq
382
+ - dje
383
+ - awa
384
+ - bjj
385
+ - qvz
386
+ - sjp
387
+ - tll
388
+ - raj
389
+ - kjg
390
+ - bgz
391
+ - quy
392
+ - cbk
393
+ - akb
394
+ - oj
395
+ - ify
396
+ - mey
397
+ - ks
398
+ - cac
399
+ - brx
400
+ - qup
401
+ - syl
402
+ - jax
403
+ - ff
404
+ - ber
405
+ - tks
406
+ - trp
407
+ - mrw
408
+ - adh
409
+ - smt
410
+ - srr
411
+ - ffm
412
+ - qvc
413
+ - mtr
414
+ - ann
415
+ - kaa
416
+ - aa
417
+ - noe
418
+ - nut
419
+ - gyn
420
+ - kwi
421
+ - xmm
422
+ - msb
423
+ library_name: transformers
424
+ tags:
425
+ - text2text-generation
426
+ - text-generation-inference
427
+ datasets:
428
+ - allenai/MADLAD-400
429
+ pipeline_tag: translation
430
+
431
+ widget:
432
+ - text: "<2en> Como vai, amigo?"
433
+ example_title: "Translation to English"
434
+ - text: "<2de> Do you speak German?"
435
+ example_title: "Translation to German"
436
+
437
+ ---
438
+
439
+ # Model Card for MADLAD-400-7B-MT
440
+
441
+ # Table of Contents
442
+
443
+ 0. [TL;DR](#TL;DR)
444
+ 1. [Model Details](#model-details)
445
+ 2. [Usage](#usage)
446
+ 3. [Uses](#uses)
447
+ 4. [Bias, Risks, and Limitations](#bias-risks-and-limitations)
448
+ 5. [Training Details](#training-details)
449
+ 6. [Evaluation](#evaluation)
450
+ 7. [Environmental Impact](#environmental-impact)
451
+ 8. [Citation](#citation)
452
+
453
+ # TL;DR
454
+
455
+ MADLAD-400-10B-MT is a multilingual machine translation model based on the T5 architecture that was
456
+ trained on 250 billion tokens covering over 450 languages using publicly available data.
457
+ It is competitive with models that are significantly larger.
458
+
459
+ **Disclaimer**: [Juarez Bochi](https://huggingface.co/jbochi), who was not involved in this research, converted
460
+ the original weights and wrote the contents of this model card based on the original paper and Flan-T5.
461
+
462
+ # Model Details
463
+
464
+ ## Model Description
465
+
466
+ - **Model type:** Language model
467
+ - **Language(s) (NLP):** Multilingual (400+ languages)
468
+ - **License:** Apache 2.0
469
+ - **Related Models:** [All MADLAD-400 Checkpoints](https://huggingface.co/models?search=madlad)
470
+ - **Original Checkpoints:** [All Original MADLAD-400 Checkpoints](https://github.com/google-research/google-research/tree/master/madlad_400)
471
+ - **Resources for more information:**
472
+ - [Research paper](https://arxiv.org/abs/2309.04662)
473
+ - [GitHub Repo](https://github.com/google-research/t5x)
474
+ - [Hugging Face MADLAD-400 Docs (Similar to T5) ](https://huggingface.co/docs/transformers/model_doc/MADLAD-400) - [Pending PR](https://github.com/huggingface/transformers/pull/27471)
475
+
476
+ # Usage
477
+
478
+ Find below some example scripts on how to use the model:
479
+
480
+ ## Using the Pytorch model with `transformers`
481
+
482
+ ### Running the model on a CPU or GPU
483
+
484
+ <details>
485
+ <summary> Click to expand </summary>
486
+
487
+ First, install the Python packages that are required:
488
+
489
+ `pip install transformers accelerate sentencepiece`
490
+
491
+ ```python
492
+ from transformers import T5ForConditionalGeneration, T5Tokenizer
493
+
494
+ model_name = 'jbochi/madlad400-10b-mt'
495
+ model = T5ForConditionalGeneration.from_pretrained(model_name, device_map="auto")
496
+ tokenizer = T5Tokenizer.from_pretrained(model_name)
497
+
498
+ text = "<2pt> I love pizza!"
499
+ input_ids = tokenizer(text, return_tensors="pt").input_ids.to(model.device)
500
+ outputs = model.generate(input_ids=input_ids)
501
+
502
+ tokenizer.decode(outputs[0], skip_special_tokens=True)
503
+ # Eu adoro pizza!
504
+ ```
505
+
506
+ </details>
507
+
508
+ ## Running the model with Candle
509
+
510
+ <details>
511
+ <summary> Click to expand </summary>
512
+
513
+ Usage with [candle](https://github.com/huggingface/candle):
514
+
515
+ ```bash
516
+ $ cargo run --example t5 --release -- \
517
+ --model-id "jbochi/madlad400-10b-mt" \
518
+ --prompt "<2de> How are you, my friend?" \
519
+ --decode --temperature 0
520
+ ```
521
+
522
+ </details>
523
+
524
+
525
+ # Uses
526
+
527
+ ## Direct Use and Downstream Use
528
+
529
+ > Primary intended uses: Machine Translation and multilingual NLP tasks on over 400 languages.
530
+ > Primary intended users: Research community.
531
+
532
+ ## Out-of-Scope Use
533
+
534
+ > These models are trained on general domain data and are therefore not meant to
535
+ > work on domain-specific models out-of-the box. Moreover, these research models have not been assessed
536
+ > for production usecases.
537
+
538
+ # Bias, Risks, and Limitations
539
+
540
+ > We note that we evaluate on only 204 of the languages supported by these models and on machine translation
541
+ > and few-shot machine translation tasks. Users must consider use of this model carefully for their own
542
+ > usecase.
543
+
544
+ ## Ethical considerations and risks
545
+
546
+ > We trained these models with MADLAD-400 and publicly available data to create baseline models that
547
+ > support NLP for over 400 languages, with a focus on languages underrepresented in large-scale corpora.
548
+ > Given that these models were trained with web-crawled datasets that may contain sensitive, offensive or
549
+ > otherwise low-quality content despite extensive preprocessing, it is still possible that these issues to the
550
+ > underlying training data may cause differences in model performance and toxic (or otherwise problematic)
551
+ > output for certain domains. Moreover, large models are dual use technologies that have specific risks
552
+ > associated with their use and development. We point the reader to surveys such as those written by
553
+ > Weidinger et al. or Bommasani et al. for a more detailed discussion of these risks, and to Liebling
554
+ > et al. for a thorough discussion of the risks of machine translation systems.
555
+
556
+ ## Known Limitations
557
+
558
+ More information needed
559
+
560
+ ## Sensitive Use:
561
+
562
+ More information needed
563
+
564
+ # Training Details
565
+
566
+ > We train models of various sizes: a 3B, 32-layer parameter model,
567
+ > a 7.2B 48-layer parameter model and a 10.7B 32-layer parameter model.
568
+ > We share all parameters of the model across language pairs,
569
+ > and use a Sentence Piece Model with 256k tokens shared on both the encoder and decoder
570
+ > side. Each input sentence has a <2xx> token prepended to the source sentence to indicate the target
571
+ > language.
572
+
573
+ See the [research paper](https://arxiv.org/pdf/2309.04662.pdf) for further details.
574
+
575
+ ## Training Data
576
+
577
+ > For both the machine translation and language model, MADLAD-400 is used. For the machine translation
578
+ > model, a combination of parallel datasources covering 157 languages is also used. Further details are
579
+ > described in the [paper](https://arxiv.org/pdf/2309.04662.pdf).
580
+
581
+ ## Training Procedure
582
+
583
+ See the [research paper](https://arxiv.org/pdf/2309.04662.pdf) for further details.
584
+
585
+ # Evaluation
586
+
587
+ ## Testing Data, Factors & Metrics
588
+
589
+ > For evaluation, we used WMT, NTREX, Flores-200 and Gatones datasets as described in Section 4.3 in the [paper](https://arxiv.org/pdf/2309.04662.pdf).
590
+
591
+ > The translation quality of this model varies based on language, as seen in the paper, and likely varies on
592
+ > domain, though we have not assessed this.
593
+
594
+ ## Results
595
+
596
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b7f632037d6452a321fa15/EzsMD1AwCuFH0S0DeD-n8.png)
597
+
598
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b7f632037d6452a321fa15/CJ5zCUVy7vTU76Lc8NZcK.png)
599
+
600
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b7f632037d6452a321fa15/NK0S-yVeWuhKoidpLYh3m.png)
601
+
602
+ See the [research paper](https://arxiv.org/pdf/2309.04662.pdf) for further details.
603
+
604
+ # Environmental Impact
605
+
606
+ More information needed
607
+
608
+ # Citation
609
+
610
+ **BibTeX:**
611
+
612
+ ```bibtex
613
+ @misc{kudugunta2023madlad400,
614
+ title={MADLAD-400: A Multilingual And Document-Level Large Audited Dataset},
615
+ author={Sneha Kudugunta and Isaac Caswell and Biao Zhang and Xavier Garcia and Christopher A. Choquette-Choo and Katherine Lee and Derrick Xin and Aditya Kusupati and Romi Stella and Ankur Bapna and Orhan Firat},
616
+ year={2023},
617
+ eprint={2309.04662},
618
+ archivePrefix={arXiv},
619
+ primaryClass={cs.CL}
620
+ }
621
+ ```
added_tokens.json ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ {
2
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 16384,
7
+ "d_kv": 128,
8
+ "d_model": 2048,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 2,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 32,
21
+ "num_heads": 32,
22
+ "num_layers": 32,
23
+ "output_past": true,
24
+ "pad_token_id": 1,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {},
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.35.0",
31
+ "use_cache": true,
32
+ "vocab_size": 256000
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.35.0"
7
+ }
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9e86fef943ce2ed0d9af7bb9b95fd4c23f08adecbf3ed3c69701c083a70084c
3
+ size 4915824880
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0113037361356eb550caf34fd9a6c82562d9c49a337c3d7c8115f9fc6afbe10f
3
+ size 4966213544
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b8d92c9a72aedd06fb1efd2b11dcfb83d12374732cd45d6e86bb95f95a0cad
3
+ size 4966213584
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229207583daae9ed3282f0cfb467d366cb803417baad32865b9a735bafafceab
3
+ size 4966234776
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd6ed8d7d72d4e0f471aafad94acbd5140d403c218e84173e58a696ab3d361b8
3
+ size 4999811840
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e7d39bdb30107d9d4f2f0ae4785d47861c05060678d11203f33b4ee2fa883ef
3
+ size 4932694504
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8607844d74a28c18f46465b355465f5ec9395832bd4aa661ccb48c81bf0a9ed9
3
+ size 4999803272
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23295d4fb84d4a657c0af7f362d12d6ad4395e2a3c8b26e8256f832c2bc3eb5f
3
+ size 4932703208
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d115240ace78581b178664a89a2d0be15beebcf536a7deddee8d4108d7ef7d5b
3
+ size 3170937232
model-q4k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b93486cbacec996339de76bddec0f1fc348f0a8b3ea9e5fc105555940f85cdd8
3
+ size 6027040384
model-q6k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c50c5711697466b75018885a76e0d5ebf424325aac4e475cec717f6e5c3cb3c
3
+ size 8788792960
model.safetensors.index.json ADDED
@@ -0,0 +1,749 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 42850344960
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00009.safetensors",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00004-of-00009.safetensors",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00004-of-00009.safetensors",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00004-of-00009.safetensors",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00004-of-00009.safetensors",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
32
+ "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
33
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
34
+ "decoder.block.1.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
35
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
36
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
37
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
38
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
39
+ "decoder.block.10.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
40
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
41
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
42
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
43
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
44
+ "decoder.block.10.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
45
+ "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
46
+ "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
47
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
48
+ "decoder.block.10.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
49
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
50
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
51
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
52
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
53
+ "decoder.block.11.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
54
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
55
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
56
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
57
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
58
+ "decoder.block.11.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
59
+ "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
60
+ "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
61
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
62
+ "decoder.block.11.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
63
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
64
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
65
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
66
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
67
+ "decoder.block.12.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
68
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
69
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
70
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
71
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
72
+ "decoder.block.12.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
73
+ "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
74
+ "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
75
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
76
+ "decoder.block.12.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
77
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
78
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
79
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
80
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
81
+ "decoder.block.13.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
82
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
83
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
84
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
85
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
86
+ "decoder.block.13.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
87
+ "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
88
+ "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
89
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
90
+ "decoder.block.13.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
91
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
92
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
93
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
94
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
95
+ "decoder.block.14.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
96
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
97
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
98
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
99
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
100
+ "decoder.block.14.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
101
+ "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
102
+ "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
103
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
104
+ "decoder.block.14.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
105
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
106
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
107
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
108
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
109
+ "decoder.block.15.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
110
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
111
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
112
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
113
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
114
+ "decoder.block.15.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
115
+ "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
116
+ "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
117
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
118
+ "decoder.block.15.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
119
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
120
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
121
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
122
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
123
+ "decoder.block.16.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
124
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
125
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
126
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
127
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
128
+ "decoder.block.16.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
129
+ "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
130
+ "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
131
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
132
+ "decoder.block.16.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
133
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
134
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
135
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
136
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
137
+ "decoder.block.17.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
138
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
139
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
140
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
141
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
142
+ "decoder.block.17.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
143
+ "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
144
+ "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
145
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
146
+ "decoder.block.17.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
147
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
148
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
149
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
150
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
151
+ "decoder.block.18.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
152
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
153
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
154
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
155
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
156
+ "decoder.block.18.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
157
+ "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
158
+ "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
159
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
160
+ "decoder.block.18.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
161
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
162
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
163
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
164
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
165
+ "decoder.block.19.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
166
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
167
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
168
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
169
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
170
+ "decoder.block.19.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
171
+ "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
172
+ "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
173
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
174
+ "decoder.block.19.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
175
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
176
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
177
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
178
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
179
+ "decoder.block.2.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
180
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
181
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
182
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
183
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
184
+ "decoder.block.2.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
185
+ "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
186
+ "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
187
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
188
+ "decoder.block.2.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
189
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
190
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
191
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
192
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
193
+ "decoder.block.20.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
194
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
195
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
196
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
197
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
198
+ "decoder.block.20.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
199
+ "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
200
+ "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
201
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
202
+ "decoder.block.20.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
203
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
204
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
205
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
206
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
207
+ "decoder.block.21.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
208
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
209
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
210
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
211
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
212
+ "decoder.block.21.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
213
+ "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
214
+ "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
215
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
216
+ "decoder.block.21.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
217
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
218
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
219
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
220
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
221
+ "decoder.block.22.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
222
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
223
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
224
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
225
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
226
+ "decoder.block.22.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
227
+ "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
228
+ "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
229
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
230
+ "decoder.block.22.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
231
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
232
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
233
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
234
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
235
+ "decoder.block.23.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
236
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
237
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
238
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
239
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
240
+ "decoder.block.23.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
241
+ "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
242
+ "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
243
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
244
+ "decoder.block.23.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
245
+ "decoder.block.24.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
246
+ "decoder.block.24.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
247
+ "decoder.block.24.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
248
+ "decoder.block.24.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
249
+ "decoder.block.24.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
250
+ "decoder.block.24.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
251
+ "decoder.block.24.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
252
+ "decoder.block.24.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
253
+ "decoder.block.24.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
254
+ "decoder.block.24.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
255
+ "decoder.block.24.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
256
+ "decoder.block.24.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
257
+ "decoder.block.24.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
258
+ "decoder.block.24.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
259
+ "decoder.block.25.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
260
+ "decoder.block.25.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
261
+ "decoder.block.25.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
262
+ "decoder.block.25.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
263
+ "decoder.block.25.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
264
+ "decoder.block.25.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
265
+ "decoder.block.25.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
266
+ "decoder.block.25.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
267
+ "decoder.block.25.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
268
+ "decoder.block.25.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
269
+ "decoder.block.25.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
270
+ "decoder.block.25.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
271
+ "decoder.block.25.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
272
+ "decoder.block.25.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
273
+ "decoder.block.26.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
274
+ "decoder.block.26.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
275
+ "decoder.block.26.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
276
+ "decoder.block.26.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
277
+ "decoder.block.26.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
278
+ "decoder.block.26.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
279
+ "decoder.block.26.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
280
+ "decoder.block.26.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
281
+ "decoder.block.26.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
282
+ "decoder.block.26.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
283
+ "decoder.block.26.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
284
+ "decoder.block.26.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
285
+ "decoder.block.26.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
286
+ "decoder.block.26.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
287
+ "decoder.block.27.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
288
+ "decoder.block.27.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
289
+ "decoder.block.27.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
290
+ "decoder.block.27.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
291
+ "decoder.block.27.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
292
+ "decoder.block.27.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
293
+ "decoder.block.27.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
294
+ "decoder.block.27.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
295
+ "decoder.block.27.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
296
+ "decoder.block.27.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
297
+ "decoder.block.27.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
298
+ "decoder.block.27.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
299
+ "decoder.block.27.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
300
+ "decoder.block.27.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
301
+ "decoder.block.28.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
302
+ "decoder.block.28.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
303
+ "decoder.block.28.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
304
+ "decoder.block.28.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
305
+ "decoder.block.28.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
306
+ "decoder.block.28.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
307
+ "decoder.block.28.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
308
+ "decoder.block.28.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
309
+ "decoder.block.28.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
310
+ "decoder.block.28.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
311
+ "decoder.block.28.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
312
+ "decoder.block.28.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
313
+ "decoder.block.28.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
314
+ "decoder.block.28.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
315
+ "decoder.block.29.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
316
+ "decoder.block.29.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
317
+ "decoder.block.29.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
318
+ "decoder.block.29.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
319
+ "decoder.block.29.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
320
+ "decoder.block.29.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
321
+ "decoder.block.29.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
322
+ "decoder.block.29.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
323
+ "decoder.block.29.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
324
+ "decoder.block.29.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
325
+ "decoder.block.29.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
326
+ "decoder.block.29.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
327
+ "decoder.block.29.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
328
+ "decoder.block.29.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
329
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
330
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
331
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
332
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
333
+ "decoder.block.3.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
334
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
335
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
336
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
337
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
338
+ "decoder.block.3.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
339
+ "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
340
+ "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
341
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
342
+ "decoder.block.3.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
343
+ "decoder.block.30.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
344
+ "decoder.block.30.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
345
+ "decoder.block.30.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
346
+ "decoder.block.30.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
347
+ "decoder.block.30.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
348
+ "decoder.block.30.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
349
+ "decoder.block.30.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
350
+ "decoder.block.30.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
351
+ "decoder.block.30.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
352
+ "decoder.block.30.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
353
+ "decoder.block.30.layer.2.DenseReluDense.wi_0.weight": "model-00009-of-00009.safetensors",
354
+ "decoder.block.30.layer.2.DenseReluDense.wi_1.weight": "model-00009-of-00009.safetensors",
355
+ "decoder.block.30.layer.2.DenseReluDense.wo.weight": "model-00009-of-00009.safetensors",
356
+ "decoder.block.30.layer.2.layer_norm.weight": "model-00009-of-00009.safetensors",
357
+ "decoder.block.31.layer.0.SelfAttention.k.weight": "model-00009-of-00009.safetensors",
358
+ "decoder.block.31.layer.0.SelfAttention.o.weight": "model-00009-of-00009.safetensors",
359
+ "decoder.block.31.layer.0.SelfAttention.q.weight": "model-00009-of-00009.safetensors",
360
+ "decoder.block.31.layer.0.SelfAttention.v.weight": "model-00009-of-00009.safetensors",
361
+ "decoder.block.31.layer.0.layer_norm.weight": "model-00009-of-00009.safetensors",
362
+ "decoder.block.31.layer.1.EncDecAttention.k.weight": "model-00009-of-00009.safetensors",
363
+ "decoder.block.31.layer.1.EncDecAttention.o.weight": "model-00009-of-00009.safetensors",
364
+ "decoder.block.31.layer.1.EncDecAttention.q.weight": "model-00009-of-00009.safetensors",
365
+ "decoder.block.31.layer.1.EncDecAttention.v.weight": "model-00009-of-00009.safetensors",
366
+ "decoder.block.31.layer.1.layer_norm.weight": "model-00009-of-00009.safetensors",
367
+ "decoder.block.31.layer.2.DenseReluDense.wi_0.weight": "model-00009-of-00009.safetensors",
368
+ "decoder.block.31.layer.2.DenseReluDense.wi_1.weight": "model-00009-of-00009.safetensors",
369
+ "decoder.block.31.layer.2.DenseReluDense.wo.weight": "model-00009-of-00009.safetensors",
370
+ "decoder.block.31.layer.2.layer_norm.weight": "model-00009-of-00009.safetensors",
371
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
372
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
373
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
374
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
375
+ "decoder.block.4.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
376
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
377
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
378
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
379
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
380
+ "decoder.block.4.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
381
+ "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
382
+ "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
383
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
384
+ "decoder.block.4.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
385
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
386
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
387
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
388
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
389
+ "decoder.block.5.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
390
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
391
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
392
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
393
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
394
+ "decoder.block.5.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
395
+ "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
396
+ "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
397
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
398
+ "decoder.block.5.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
399
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
400
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
401
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
402
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
403
+ "decoder.block.6.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
404
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
405
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
406
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
407
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
408
+ "decoder.block.6.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
409
+ "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
410
+ "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
411
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
412
+ "decoder.block.6.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
413
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
414
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
415
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
416
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
417
+ "decoder.block.7.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
418
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
419
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
420
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
421
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
422
+ "decoder.block.7.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
423
+ "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
424
+ "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
425
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
426
+ "decoder.block.7.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
427
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
428
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
429
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
430
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
431
+ "decoder.block.8.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
432
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
433
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
434
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
435
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
436
+ "decoder.block.8.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
437
+ "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
438
+ "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
439
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
440
+ "decoder.block.8.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
441
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
442
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
443
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
444
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
445
+ "decoder.block.9.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
446
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
447
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
448
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
449
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
450
+ "decoder.block.9.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
451
+ "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
452
+ "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
453
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
454
+ "decoder.block.9.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
455
+ "decoder.final_layer_norm.weight": "model-00009-of-00009.safetensors",
456
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
457
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
458
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
459
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00009.safetensors",
460
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
461
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
462
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
463
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
464
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
465
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
466
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
467
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
468
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
469
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
470
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
471
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
472
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
473
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
474
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
475
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
476
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
477
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
478
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
479
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
480
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
481
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
482
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
483
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
484
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
485
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
486
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
487
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
488
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
489
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
490
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
491
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
492
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
493
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
494
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
495
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
496
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
497
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
498
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
499
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
500
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
501
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
502
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
503
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
504
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
505
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
506
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
507
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
508
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
509
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
510
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
511
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
512
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
513
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
514
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
515
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
516
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
517
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
518
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
519
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
520
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
521
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
522
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
523
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
524
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
525
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
526
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
527
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
528
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
529
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
530
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
531
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
532
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
533
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
534
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
535
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
536
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
537
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
538
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
539
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
540
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
541
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
542
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
543
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
544
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
545
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
546
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
547
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
548
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
549
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
550
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
551
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
552
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
553
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
554
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
555
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
556
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
557
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
558
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
559
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
560
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
561
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
562
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
563
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
564
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
565
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
566
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
567
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
568
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
569
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
570
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
571
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
572
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
573
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
574
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
575
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
576
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
577
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
578
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
579
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
580
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
581
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
582
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
583
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
584
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
585
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
586
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
587
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
588
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
589
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
590
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
591
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
592
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
593
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
594
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
595
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
596
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
597
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
598
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
599
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
600
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
601
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
602
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
603
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
604
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
605
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
606
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
607
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
608
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
609
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
610
+ "encoder.block.24.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
611
+ "encoder.block.24.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
612
+ "encoder.block.24.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
613
+ "encoder.block.24.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
614
+ "encoder.block.24.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
615
+ "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
616
+ "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
617
+ "encoder.block.24.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
618
+ "encoder.block.24.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
619
+ "encoder.block.25.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
620
+ "encoder.block.25.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
621
+ "encoder.block.25.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
622
+ "encoder.block.25.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
623
+ "encoder.block.25.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
624
+ "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
625
+ "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
626
+ "encoder.block.25.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
627
+ "encoder.block.25.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
628
+ "encoder.block.26.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
629
+ "encoder.block.26.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
630
+ "encoder.block.26.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
631
+ "encoder.block.26.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
632
+ "encoder.block.26.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
633
+ "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
634
+ "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
635
+ "encoder.block.26.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
636
+ "encoder.block.26.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
637
+ "encoder.block.27.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
638
+ "encoder.block.27.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
639
+ "encoder.block.27.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
640
+ "encoder.block.27.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
641
+ "encoder.block.27.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
642
+ "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
643
+ "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
644
+ "encoder.block.27.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
645
+ "encoder.block.27.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
646
+ "encoder.block.28.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
647
+ "encoder.block.28.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
648
+ "encoder.block.28.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
649
+ "encoder.block.28.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
650
+ "encoder.block.28.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
651
+ "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
652
+ "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
653
+ "encoder.block.28.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
654
+ "encoder.block.28.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
655
+ "encoder.block.29.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
656
+ "encoder.block.29.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
657
+ "encoder.block.29.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
658
+ "encoder.block.29.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
659
+ "encoder.block.29.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
660
+ "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
661
+ "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
662
+ "encoder.block.29.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
663
+ "encoder.block.29.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
664
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
665
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
666
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
667
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
668
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
669
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
670
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
671
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
672
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
673
+ "encoder.block.30.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
674
+ "encoder.block.30.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
675
+ "encoder.block.30.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
676
+ "encoder.block.30.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
677
+ "encoder.block.30.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
678
+ "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
679
+ "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
680
+ "encoder.block.30.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
681
+ "encoder.block.30.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
682
+ "encoder.block.31.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
683
+ "encoder.block.31.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
684
+ "encoder.block.31.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
685
+ "encoder.block.31.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
686
+ "encoder.block.31.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
687
+ "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
688
+ "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
689
+ "encoder.block.31.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
690
+ "encoder.block.31.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
691
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
692
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
693
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
694
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
695
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
696
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
697
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
698
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
699
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
700
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
701
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
702
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
703
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
704
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
705
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
706
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
707
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
708
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
709
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
710
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
711
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
712
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
713
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
714
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
715
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
716
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
717
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
718
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
719
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
720
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
721
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
722
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
723
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
724
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
725
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
726
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
727
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
728
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
729
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
730
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
731
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
732
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
733
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
734
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
735
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
736
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
737
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
738
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
739
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
740
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
741
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
742
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
743
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
744
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
745
+ "encoder.final_layer_norm.weight": "model-00004-of-00009.safetensors",
746
+ "lm_head.weight": "model-00009-of-00009.safetensors",
747
+ "shared.weight": "model-00001-of-00009.safetensors"
748
+ }
749
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef11ac9a22c7503492f56d48dce53be20e339b63605983e9f27d2cd0e0f3922c
3
+ size 4427844
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2799ccc696b752ba00c34f58726bfe253a04921ceb6cfc620400f560474790b
3
+ size 16629031
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "clean_up_tokenization_spaces": true,
30
+ "eos_token": "</s>",
31
+ "extra_ids": 0,
32
+ "legacy": false,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<s>",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "T5Tokenizer",
37
+ "unk_token": "<unk>"
38
+ }