ElijahLee commited on
Commit
5a066c1
1 Parent(s): 5a368ad

Removed all files from the repository

Browse files
Files changed (47) hide show
  1. LICENSE.txt +0 -437
  2. README.md +0 -68
  3. config.json +0 -30
  4. model-00001-of-00039.safetensors +0 -3
  5. model-00002-of-00039.safetensors +0 -3
  6. model-00003-of-00039.safetensors +0 -3
  7. model-00004-of-00039.safetensors +0 -3
  8. model-00005-of-00039.safetensors +0 -3
  9. model-00006-of-00039.safetensors +0 -3
  10. model-00007-of-00039.safetensors +0 -3
  11. model-00008-of-00039.safetensors +0 -3
  12. model-00009-of-00039.safetensors +0 -3
  13. model-00010-of-00039.safetensors +0 -3
  14. model-00011-of-00039.safetensors +0 -3
  15. model-00012-of-00039.safetensors +0 -3
  16. model-00013-of-00039.safetensors +0 -3
  17. model-00014-of-00039.safetensors +0 -3
  18. model-00015-of-00039.safetensors +0 -3
  19. model-00016-of-00039.safetensors +0 -3
  20. model-00017-of-00039.safetensors +0 -3
  21. model-00018-of-00039.safetensors +0 -3
  22. model-00019-of-00039.safetensors +0 -3
  23. model-00020-of-00039.safetensors +0 -3
  24. model-00021-of-00039.safetensors +0 -3
  25. model-00022-of-00039.safetensors +0 -3
  26. model-00023-of-00039.safetensors +0 -3
  27. model-00024-of-00039.safetensors +0 -3
  28. model-00025-of-00039.safetensors +0 -3
  29. model-00026-of-00039.safetensors +0 -3
  30. model-00027-of-00039.safetensors +0 -3
  31. model-00028-of-00039.safetensors +0 -3
  32. model-00029-of-00039.safetensors +0 -3
  33. model-00030-of-00039.safetensors +0 -3
  34. model-00031-of-00039.safetensors +0 -3
  35. model-00032-of-00039.safetensors +0 -3
  36. model-00033-of-00039.safetensors +0 -3
  37. model-00034-of-00039.safetensors +0 -3
  38. model-00035-of-00039.safetensors +0 -3
  39. model-00036-of-00039.safetensors +0 -3
  40. model-00037-of-00039.safetensors +0 -3
  41. model-00038-of-00039.safetensors +0 -3
  42. model-00039-of-00039.safetensors +0 -3
  43. model.safetensors.index.json +0 -1001
  44. special_tokens_map.json +0 -30
  45. tokenizer.json +0 -0
  46. tokenizer.model +0 -3
  47. tokenizer_config.json +0 -45
LICENSE.txt DELETED
@@ -1,437 +0,0 @@
1
- Attribution-NonCommercial-ShareAlike 4.0 International
2
-
3
- =======================================================================
4
-
5
- Creative Commons Corporation ("Creative Commons") is not a law firm and
6
- does not provide legal services or legal advice. Distribution of
7
- Creative Commons public licenses does not create a lawyer-client or
8
- other relationship. Creative Commons makes its licenses and related
9
- information available on an "as-is" basis. Creative Commons gives no
10
- warranties regarding its licenses, any material licensed under their
11
- terms and conditions, or any related information. Creative Commons
12
- disclaims all liability for damages resulting from their use to the
13
- fullest extent possible.
14
-
15
- Using Creative Commons Public Licenses
16
-
17
- Creative Commons public licenses provide a standard set of terms and
18
- conditions that creators and other rights holders may use to share
19
- original works of authorship and other material subject to copyright
20
- and certain other rights specified in the public license below. The
21
- following considerations are for informational purposes only, are not
22
- exhaustive, and do not form part of our licenses.
23
-
24
- Considerations for licensors: Our public licenses are
25
- intended for use by those authorized to give the public
26
- permission to use material in ways otherwise restricted by
27
- copyright and certain other rights. Our licenses are
28
- irrevocable. Licensors should read and understand the terms
29
- and conditions of the license they choose before applying it.
30
- Licensors should also secure all rights necessary before
31
- applying our licenses so that the public can reuse the
32
- material as expected. Licensors should clearly mark any
33
- material not subject to the license. This includes other CC-
34
- licensed material, or material used under an exception or
35
- limitation to copyright. More considerations for licensors:
36
- wiki.creativecommons.org/Considerations_for_licensors
37
-
38
- Considerations for the public: By using one of our public
39
- licenses, a licensor grants the public permission to use the
40
- licensed material under specified terms and conditions. If
41
- the licensor's permission is not necessary for any reason--for
42
- example, because of any applicable exception or limitation to
43
- copyright--then that use is not regulated by the license. Our
44
- licenses grant only permissions under copyright and certain
45
- other rights that a licensor has authority to grant. Use of
46
- the licensed material may still be restricted for other
47
- reasons, including because others have copyright or other
48
- rights in the material. A licensor may make special requests,
49
- such as asking that all changes be marked or described.
50
- Although not required by our licenses, you are encouraged to
51
- respect those requests where reasonable. More considerations
52
- for the public:
53
- wiki.creativecommons.org/Considerations_for_licensees
54
-
55
- =======================================================================
56
-
57
- Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
58
- Public License
59
-
60
- By exercising the Licensed Rights (defined below), You accept and agree
61
- to be bound by the terms and conditions of this Creative Commons
62
- Attribution-NonCommercial-ShareAlike 4.0 International Public License
63
- ("Public License"). To the extent this Public License may be
64
- interpreted as a contract, You are granted the Licensed Rights in
65
- consideration of Your acceptance of these terms and conditions, and the
66
- Licensor grants You such rights in consideration of benefits the
67
- Licensor receives from making the Licensed Material available under
68
- these terms and conditions.
69
-
70
-
71
- Section 1 -- Definitions.
72
-
73
- a. Adapted Material means material subject to Copyright and Similar
74
- Rights that is derived from or based upon the Licensed Material
75
- and in which the Licensed Material is translated, altered,
76
- arranged, transformed, or otherwise modified in a manner requiring
77
- permission under the Copyright and Similar Rights held by the
78
- Licensor. For purposes of this Public License, where the Licensed
79
- Material is a musical work, performance, or sound recording,
80
- Adapted Material is always produced where the Licensed Material is
81
- synched in timed relation with a moving image.
82
-
83
- b. Adapter's License means the license You apply to Your Copyright
84
- and Similar Rights in Your contributions to Adapted Material in
85
- accordance with the terms and conditions of this Public License.
86
-
87
- c. BY-NC-SA Compatible License means a license listed at
88
- creativecommons.org/compatiblelicenses, approved by Creative
89
- Commons as essentially the equivalent of this Public License.
90
-
91
- d. Copyright and Similar Rights means copyright and/or similar rights
92
- closely related to copyright including, without limitation,
93
- performance, broadcast, sound recording, and Sui Generis Database
94
- Rights, without regard to how the rights are labeled or
95
- categorized. For purposes of this Public License, the rights
96
- specified in Section 2(b)(1)-(2) are not Copyright and Similar
97
- Rights.
98
-
99
- e. Effective Technological Measures means those measures that, in the
100
- absence of proper authority, may not be circumvented under laws
101
- fulfilling obligations under Article 11 of the WIPO Copyright
102
- Treaty adopted on December 20, 1996, and/or similar international
103
- agreements.
104
-
105
- f. Exceptions and Limitations means fair use, fair dealing, and/or
106
- any other exception or limitation to Copyright and Similar Rights
107
- that applies to Your use of the Licensed Material.
108
-
109
- g. License Elements means the license attributes listed in the name
110
- of a Creative Commons Public License. The License Elements of this
111
- Public License are Attribution, NonCommercial, and ShareAlike.
112
-
113
- h. Licensed Material means the artistic or literary work, database,
114
- or other material to which the Licensor applied this Public
115
- License.
116
-
117
- i. Licensed Rights means the rights granted to You subject to the
118
- terms and conditions of this Public License, which are limited to
119
- all Copyright and Similar Rights that apply to Your use of the
120
- Licensed Material and that the Licensor has authority to license.
121
-
122
- j. Licensor means the individual(s) or entity(ies) granting rights
123
- under this Public License.
124
-
125
- k. NonCommercial means not primarily intended for or directed towards
126
- commercial advantage or monetary compensation. For purposes of
127
- this Public License, the exchange of the Licensed Material for
128
- other material subject to Copyright and Similar Rights by digital
129
- file-sharing or similar means is NonCommercial provided there is
130
- no payment of monetary compensation in connection with the
131
- exchange.
132
-
133
- l. Share means to provide material to the public by any means or
134
- process that requires permission under the Licensed Rights, such
135
- as reproduction, public display, public performance, distribution,
136
- dissemination, communication, or importation, and to make material
137
- available to the public including in ways that members of the
138
- public may access the material from a place and at a time
139
- individually chosen by them.
140
-
141
- m. Sui Generis Database Rights means rights other than copyright
142
- resulting from Directive 96/9/EC of the European Parliament and of
143
- the Council of 11 March 1996 on the legal protection of databases,
144
- as amended and/or succeeded, as well as other essentially
145
- equivalent rights anywhere in the world.
146
-
147
- n. You means the individual or entity exercising the Licensed Rights
148
- under this Public License. Your has a corresponding meaning.
149
-
150
-
151
- Section 2 -- Scope.
152
-
153
- a. License grant.
154
-
155
- 1. Subject to the terms and conditions of this Public License,
156
- the Licensor hereby grants You a worldwide, royalty-free,
157
- non-sublicensable, non-exclusive, irrevocable license to
158
- exercise the Licensed Rights in the Licensed Material to:
159
-
160
- a. reproduce and Share the Licensed Material, in whole or
161
- in part, for NonCommercial purposes only; and
162
-
163
- b. produce, reproduce, and Share Adapted Material for
164
- NonCommercial purposes only.
165
-
166
- 2. Exceptions and Limitations. For the avoidance of doubt, where
167
- Exceptions and Limitations apply to Your use, this Public
168
- License does not apply, and You do not need to comply with
169
- its terms and conditions.
170
-
171
- 3. Term. The term of this Public License is specified in Section
172
- 6(a).
173
-
174
- 4. Media and formats; technical modifications allowed. The
175
- Licensor authorizes You to exercise the Licensed Rights in
176
- all media and formats whether now known or hereafter created,
177
- and to make technical modifications necessary to do so. The
178
- Licensor waives and/or agrees not to assert any right or
179
- authority to forbid You from making technical modifications
180
- necessary to exercise the Licensed Rights, including
181
- technical modifications necessary to circumvent Effective
182
- Technological Measures. For purposes of this Public License,
183
- simply making modifications authorized by this Section 2(a)
184
- (4) never produces Adapted Material.
185
-
186
- 5. Downstream recipients.
187
-
188
- a. Offer from the Licensor -- Licensed Material. Every
189
- recipient of the Licensed Material automatically
190
- receives an offer from the Licensor to exercise the
191
- Licensed Rights under the terms and conditions of this
192
- Public License.
193
-
194
- b. Additional offer from the Licensor -- Adapted Material.
195
- Every recipient of Adapted Material from You
196
- automatically receives an offer from the Licensor to
197
- exercise the Licensed Rights in the Adapted Material
198
- under the conditions of the Adapter's License You apply.
199
-
200
- c. No downstream restrictions. You may not offer or impose
201
- any additional or different terms or conditions on, or
202
- apply any Effective Technological Measures to, the
203
- Licensed Material if doing so restricts exercise of the
204
- Licensed Rights by any recipient of the Licensed
205
- Material.
206
-
207
- 6. No endorsement. Nothing in this Public License constitutes or
208
- may be construed as permission to assert or imply that You
209
- are, or that Your use of the Licensed Material is, connected
210
- with, or sponsored, endorsed, or granted official status by,
211
- the Licensor or others designated to receive attribution as
212
- provided in Section 3(a)(1)(A)(i).
213
-
214
- b. Other rights.
215
-
216
- 1. Moral rights, such as the right of integrity, are not
217
- licensed under this Public License, nor are publicity,
218
- privacy, and/or other similar personality rights; however, to
219
- the extent possible, the Licensor waives and/or agrees not to
220
- assert any such rights held by the Licensor to the limited
221
- extent necessary to allow You to exercise the Licensed
222
- Rights, but not otherwise.
223
-
224
- 2. Patent and trademark rights are not licensed under this
225
- Public License.
226
-
227
- 3. To the extent possible, the Licensor waives any right to
228
- collect royalties from You for the exercise of the Licensed
229
- Rights, whether directly or through a collecting society
230
- under any voluntary or waivable statutory or compulsory
231
- licensing scheme. In all other cases the Licensor expressly
232
- reserves any right to collect such royalties, including when
233
- the Licensed Material is used other than for NonCommercial
234
- purposes.
235
-
236
-
237
- Section 3 -- License Conditions.
238
-
239
- Your exercise of the Licensed Rights is expressly made subject to the
240
- following conditions.
241
-
242
- a. Attribution.
243
-
244
- 1. If You Share the Licensed Material (including in modified
245
- form), You must:
246
-
247
- a. retain the following if it is supplied by the Licensor
248
- with the Licensed Material:
249
-
250
- i. identification of the creator(s) of the Licensed
251
- Material and any others designated to receive
252
- attribution, in any reasonable manner requested by
253
- the Licensor (including by pseudonym if
254
- designated);
255
-
256
- ii. a copyright notice;
257
-
258
- iii. a notice that refers to this Public License;
259
-
260
- iv. a notice that refers to the disclaimer of
261
- warranties;
262
-
263
- v. a URI or hyperlink to the Licensed Material to the
264
- extent reasonably practicable;
265
-
266
- b. indicate if You modified the Licensed Material and
267
- retain an indication of any previous modifications; and
268
-
269
- c. indicate the Licensed Material is licensed under this
270
- Public License, and include the text of, or the URI or
271
- hyperlink to, this Public License.
272
-
273
- 2. You may satisfy the conditions in Section 3(a)(1) in any
274
- reasonable manner based on the medium, means, and context in
275
- which You Share the Licensed Material. For example, it may be
276
- reasonable to satisfy the conditions by providing a URI or
277
- hyperlink to a resource that includes the required
278
- information.
279
- 3. If requested by the Licensor, You must remove any of the
280
- information required by Section 3(a)(1)(A) to the extent
281
- reasonably practicable.
282
-
283
- b. ShareAlike.
284
-
285
- In addition to the conditions in Section 3(a), if You Share
286
- Adapted Material You produce, the following conditions also apply.
287
-
288
- 1. The Adapter's License You apply must be a Creative Commons
289
- license with the same License Elements, this version or
290
- later, or a BY-NC-SA Compatible License.
291
-
292
- 2. You must include the text of, or the URI or hyperlink to, the
293
- Adapter's License You apply. You may satisfy this condition
294
- in any reasonable manner based on the medium, means, and
295
- context in which You Share Adapted Material.
296
-
297
- 3. You may not offer or impose any additional or different terms
298
- or conditions on, or apply any Effective Technological
299
- Measures to, Adapted Material that restrict exercise of the
300
- rights granted under the Adapter's License You apply.
301
-
302
-
303
- Section 4 -- Sui Generis Database Rights.
304
-
305
- Where the Licensed Rights include Sui Generis Database Rights that
306
- apply to Your use of the Licensed Material:
307
-
308
- a. for the avoidance of doubt, Section 2(a)(1) grants You the right
309
- to extract, reuse, reproduce, and Share all or a substantial
310
- portion of the contents of the database for NonCommercial purposes
311
- only;
312
-
313
- b. if You include all or a substantial portion of the database
314
- contents in a database in which You have Sui Generis Database
315
- Rights, then the database in which You have Sui Generis Database
316
- Rights (but not its individual contents) is Adapted Material,
317
- including for purposes of Section 3(b); and
318
-
319
- c. You must comply with the conditions in Section 3(a) if You Share
320
- all or a substantial portion of the contents of the database.
321
-
322
- For the avoidance of doubt, this Section 4 supplements and does not
323
- replace Your obligations under this Public License where the Licensed
324
- Rights include other Copyright and Similar Rights.
325
-
326
-
327
- Section 5 -- Disclaimer of Warranties and Limitation of Liability.
328
-
329
- a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
330
- EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
331
- AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
332
- ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
333
- IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
334
- WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
335
- PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
336
- ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
337
- KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
338
- ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
339
-
340
- b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
341
- TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
342
- NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
343
- INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
344
- COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
345
- USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
346
- ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
347
- DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
348
- IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
349
-
350
- c. The disclaimer of warranties and limitation of liability provided
351
- above shall be interpreted in a manner that, to the extent
352
- possible, most closely approximates an absolute disclaimer and
353
- waiver of all liability.
354
-
355
-
356
- Section 6 -- Term and Termination.
357
-
358
- a. This Public License applies for the term of the Copyright and
359
- Similar Rights licensed here. However, if You fail to comply with
360
- this Public License, then Your rights under this Public License
361
- terminate automatically.
362
-
363
- b. Where Your right to use the Licensed Material has terminated under
364
- Section 6(a), it reinstates:
365
-
366
- 1. automatically as of the date the violation is cured, provided
367
- it is cured within 30 days of Your discovery of the
368
- violation; or
369
-
370
- 2. upon express reinstatement by the Licensor.
371
-
372
- For the avoidance of doubt, this Section 6(b) does not affect any
373
- right the Licensor may have to seek remedies for Your violations
374
- of this Public License.
375
-
376
- c. For the avoidance of doubt, the Licensor may also offer the
377
- Licensed Material under separate terms or conditions or stop
378
- distributing the Licensed Material at any time; however, doing so
379
- will not terminate this Public License.
380
-
381
- d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
382
- License.
383
-
384
-
385
- Section 7 -- Other Terms and Conditions.
386
-
387
- a. The Licensor shall not be bound by any additional or different
388
- terms or conditions communicated by You unless expressly agreed.
389
-
390
- b. Any arrangements, understandings, or agreements regarding the
391
- Licensed Material not stated herein are separate from and
392
- independent of the terms and conditions of this Public License.
393
-
394
-
395
- Section 8 -- Interpretation.
396
-
397
- a. For the avoidance of doubt, this Public License does not, and
398
- shall not be interpreted to, reduce, limit, restrict, or impose
399
- conditions on any use of the Licensed Material that could lawfully
400
- be made without permission under this Public License.
401
-
402
- b. To the extent possible, if any provision of this Public License is
403
- deemed unenforceable, it shall be automatically reformed to the
404
- minimum extent necessary to make it enforceable. If the provision
405
- cannot be reformed, it shall be severed from this Public License
406
- without affecting the enforceability of the remaining terms and
407
- conditions.
408
-
409
- c. No term or condition of this Public License will be waived and no
410
- failure to comply consented to unless expressly agreed to by the
411
- Licensor.
412
-
413
- d. Nothing in this Public License constitutes or may be interpreted
414
- as a limitation upon, or waiver of, any privileges and immunities
415
- that apply to the Licensor or You, including from the legal
416
- processes of any jurisdiction or authority.
417
-
418
- =======================================================================
419
-
420
- Creative Commons is not a party to its public
421
- licenses. Notwithstanding, Creative Commons may elect to apply one of
422
- its public licenses to material it publishes and in those instances
423
- will be considered the “Licensor.” The text of the Creative Commons
424
- public licenses is dedicated to the public domain under the CC0 Public
425
- Domain Dedication. Except for the limited purpose of indicating that
426
- material is shared under a Creative Commons public license or as
427
- otherwise permitted by the Creative Commons policies published at
428
- creativecommons.org/policies, Creative Commons does not authorize the
429
- use of the trademark "Creative Commons" or any other trademark or logo
430
- of Creative Commons without its prior written consent including,
431
- without limitation, in connection with any unauthorized modifications
432
- to any of its public licenses or any other arrangements,
433
- understandings, or agreements concerning use of licensed material. For
434
- the avoidance of doubt, this paragraph does not form part of the
435
- public licenses.
436
-
437
- Creative Commons may be contacted at creativecommons.org.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
README.md DELETED
@@ -1,68 +0,0 @@
1
- ---
2
- language:
3
- - en
4
- - ar
5
- metrics:
6
- - accuracy
7
- pipeline_tag: text-generation
8
- tags:
9
- - medical
10
- license: cc-by-nc-sa-4.0
11
- ---
12
-
13
- ## Model Card for BiMediX-Bilingual
14
-
15
- ### Model Details
16
- - **Name:** BiMediX
17
- - **Version:** 1.0
18
- - **Type:** Bilingual Medical Mixture of Experts Large Language Model (LLM)
19
- - **Languages:** English, Arabic
20
- - **Model Architecture:** [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
21
- - **Training Data:** BiMed1.3M, a bilingual dataset with diverse medical interactions.
22
-
23
- ### Intended Use
24
- - **Primary Use:** Medical interactions in both English and Arabic.
25
- - **Capabilities:** MCQA, closed QA and chats.
26
-
27
- ## Getting Started
28
-
29
- ```python
30
- from transformers import AutoModelForCausalLM, AutoTokenizer
31
-
32
- model_id = "BiMediX/BiMediX-Bi"
33
-
34
- tokenizer = AutoTokenizer.from_pretrained(model_id)
35
- model = AutoModelForCausalLM.from_pretrained(model_id)
36
-
37
- text = "Hello BiMediX! I've been experiencing increased tiredness in the past week."
38
- inputs = tokenizer(text, return_tensors="pt")
39
-
40
- outputs = model.generate(**inputs, max_new_tokens=500)
41
- print(tokenizer.decode(outputs[0], skip_special_tokens=True))
42
- ```
43
-
44
- ### Training Procedure
45
- - **Dataset:** BiMed1.3M, 632 million healthcare specialized tokens.
46
- - **QLoRA Adaptation:** Implements a low-rank adaptation technique, incorporating learnable low-rank adapter weights into the experts and the routing network. This results in training about 4% of the original parameters.
47
- - **Training Resources:** The model underwent training on approximately 632 million tokens from the Arabic-English corpus, including 288 million tokens exclusively for English.
48
-
49
- ### Model Performance
50
- - **Benchmarks:** Outperforms the baseline model and Jais-30B in medical evaluations.
51
-
52
- | **Model** | **CKG** | **CBio** | **CMed** | **MedGen** | **ProMed** | **Ana** | **MedMCQA** | **MedQA** | **PubmedQA** | **AVG** |
53
- |-----------------------------------|------------|-----------|-----------|-------------|-------------|---------|-------------|-----------|--------------|---------|
54
- | Jais-30B | 57.4 | 55.2 | 46.2 | 55.0 | 46.0 | 48.9 | 40.2 | 31.0 | 75.5 | 50.6 |
55
- | Mixtral-8x7B| 59.1 | 57.6 | 52.6 | 59.5 | 53.3 | 54.4 | 43.2 | 40.6 | 74.7 | 55.0 |
56
- | **BiMediX (Bilingual)** | **70.6** | **72.2** | **59.3** | **74.0** | **64.2** | **59.6**| **55.8** | **54.0** | **78.6** | **65.4**|
57
-
58
- ### Safety and Ethical Considerations
59
- - **Potential issues**: hallucinations, toxicity, stereotypes.
60
- - **Usage:** Research purposes only.
61
-
62
- ### Accessibility
63
- - **Availability:** [BiMediX GitHub Repository](https://github.com/mbzuai-oryx/BiMediX).
64
- - arxiv.org/abs/2402.13253
65
-
66
- ### Authors
67
- Sara Pieri, Sahal Shaji Mullappilly, Fahad Shahbaz Khan, Rao Muhammad Anwer Salman Khan, Timothy Baldwin, Hisham Cholakkal
68
- **Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)**
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "_name_or_path": "BiMediX_ar_en",
3
- "architectures": [
4
- "MixtralModel"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mixtral",
15
- "num_attention_heads": 32,
16
- "num_experts_per_tok": 2,
17
- "num_hidden_layers": 32,
18
- "num_key_value_heads": 8,
19
- "num_local_experts": 8,
20
- "output_router_logits": true,
21
- "rms_norm_eps": 1e-05,
22
- "rope_theta": 1000000.0,
23
- "router_aux_loss_coef": 0.02,
24
- "sliding_window": null,
25
- "tie_word_embeddings": false,
26
- "torch_dtype": "float32",
27
- "transformers_version": "4.36.2",
28
- "use_cache": false,
29
- "vocab_size": 32000
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model-00001-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1baf6fc0c23c3a7fc7536b242ed6991f91d42c21af13565e2fa20903756f2dc5
3
- size 4920052576
 
 
 
 
model-00002-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:810862c8a4917d2796787a62b837bebfade62c42f7683a56017267fd47878677
3
- size 4865559752
 
 
 
 
model-00003-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:79fd765378879f4a840c31198fd14c99c7a8cb62cb1c931eb8d95aee5b979495
3
- size 4865559752
 
 
 
 
model-00004-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fcf66b0d6278f7aba3b84795728096705ca27394fa85b8bda0909283c806083
3
- size 4865559752
 
 
 
 
model-00005-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:71418f4cfe7ff1ff318f952ec9c22d96f6366160a25fa96f4449670beb6cde2f
3
- size 4865559752
 
 
 
 
model-00006-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4cea7fe3b6dd5cbbaa2a56b78b2f7f9b8fd0b645240bec94b7162ef564ab01f
3
- size 4932504136
 
 
 
 
model-00007-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d00d477df028778f60e272601c2ba43f94561751e2a717219c47ec4fed7e0a01
3
- size 4865559752
 
 
 
 
model-00008-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:309de74e6574a94901c55a95122e767afd3563542fc896c4edd691dcd208e514
3
- size 4865559752
 
 
 
 
model-00009-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ac577bb5e6eaf934a4a01287ec38178134fb73f1a999599f615f99d1bea9317
3
- size 4865559752
 
 
 
 
model-00010-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:51c4495807859a642892301ada42b1587113271b9f508deaf6458a9d5a01d647
3
- size 4865559752
 
 
 
 
model-00011-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:47cd7fcd7f3d69a7734e6f26f0b44310c942edeea9d085e1b75cb55276f96c95
3
- size 4865559752
 
 
 
 
model-00012-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:31157c892a1aa6d10abd7ad2b1c93b9eb20ba0668c55fb0f36b599bb58e4ade7
3
- size 4999646096
 
 
 
 
model-00013-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e2cb4e851b4d2df44b983c2763ce7b28d3cb2ef768018fb0b2ad99a2713b84b
3
- size 4798417824
 
 
 
 
model-00014-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:30a731ee2585039601ee2759cd6c80999533a7d377d5586110452c35c56c8a5f
3
- size 4865559776
 
 
 
 
model-00015-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:780505df2dfa8e17130e485744ebacf22ce1a2a02aa3d9164b69f66983b9af5b
3
- size 4865559784
 
 
 
 
model-00016-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4ab5ad113b2554f96269626eca3c44b1d0ee8ae7253544c0959f61a586300f5
3
- size 4865559784
 
 
 
 
model-00017-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:db2a84fc5bfcdb482ffc6d8e4e27de2b087eecbb8ef996cdb38c9fd3375ccf16
3
- size 4865559784
 
 
 
 
model-00018-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e179e90f8650fb8ab5007f350c03c72a7004df7f981ccadb63b4622a1aa6e8a
3
- size 4865559784
 
 
 
 
model-00019-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f3439ff47e2a0090f382331d1047f95d07069e6c5ffd73c2f2fb16e659a99f7
3
- size 4932504152
 
 
 
 
model-00020-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1138eb26d7fd872cde0c3000f8d91d15ee315e39cf3398c0de8fd1b75f4abf50
3
- size 4865559776
 
 
 
 
model-00021-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ceeff72624282350a2df47390e61d36ae983b89ac5eadb5b3faf5791060627b0
3
- size 4865559784
 
 
 
 
model-00022-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a78e7ee661fb1201c88c4523824e344d8e0f43b551b08ae13d82e3750d1ed0a2
3
- size 4865559784
 
 
 
 
model-00023-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:57be616a1c580c580075daa2da23b347387675437dafe352ac9a13cb53a6834e
3
- size 4865559784
 
 
 
 
model-00024-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1f7904f55f37b96c604018ed4ea6ee540753ad7de1c825105d419373087d55b
3
- size 4865559784
 
 
 
 
model-00025-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d63299a83cad8c1775d977653f001fafa4be8aa11abae8817ae44fc9f048957c
3
- size 4932504152
 
 
 
 
model-00026-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6268c4c42bde8dfabbe8f5080459741c1885ab41b147a0c176aa59c1b6b16a9c
3
- size 4865559776
 
 
 
 
model-00027-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:22a7707d48b52c016a9984eca0cabeec487218415f68bfede26ad4fa81567832
3
- size 4865559784
 
 
 
 
model-00028-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:34480602749cfef8703153d159e4f36f7265be3e17f112682ed5172c10baa670
3
- size 4865559784
 
 
 
 
model-00029-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dff36462f51ef5a2c535cf6f2e5a05ff99b144bdd51c1e88b52ea86720c91802
3
- size 4865559784
 
 
 
 
model-00030-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f38fb4c2c9d6ec9fd45a92ef8d5d187f8cb138c13a9af35e049cbefa241cc129
3
- size 4865559784
 
 
 
 
model-00031-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdf152377e648ccc76f2e77683f0f2e7f989d3f5a7a32912965313021a5eccf2
3
- size 4932504152
 
 
 
 
model-00032-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e840d3f632f1822ad825e3346f6b008cc61df2ccad52d965004be70991ff03f
3
- size 4865559776
 
 
 
 
model-00033-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6a549ae04c02ca76480b7484e0edc69f2bd9f0bc2170ffb4b6b3a0ff53cfe36
3
- size 4865559784
 
 
 
 
model-00034-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dec50307f73828911ab1c410d5024aec45fbaeeadcf1533a6e339b1689ed2f3
3
- size 4865559784
 
 
 
 
model-00035-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea57002c4bb181021881f374cbdaae5b96a28b1a88fb9db59dc62e6fb32c7a9d
3
- size 4865559784
 
 
 
 
model-00036-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ac0f9a6e881e4495948a77041cbe6cde961f67d4bb144d9d80d2d564e412fe2
3
- size 4865559784
 
 
 
 
model-00037-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:35af04df3f45ec69786da79d60dfcd71aebc1e5f3b2587e50bbb83d431e11c02
3
- size 4999646120
 
 
 
 
model-00038-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a02195d61f5a74711097b962e1b31c750319774a7a33bda2afbd11d92d6b8b6e
3
- size 4798417824
 
 
 
 
model-00039-of-00039.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b39804dc082c5ba7ae8d6e1dce7a574c5df482eb2929a21531e38489a7c1a549
3
- size 939574072
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,1001 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 186286882816
4
- },
5
- "weight_map": {
6
- "embed_tokens.weight": "model-00001-of-00039.safetensors",
7
- "layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00039.safetensors",
8
- "layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00039.safetensors",
9
- "layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00039.safetensors",
10
- "layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00039.safetensors",
11
- "layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00039.safetensors",
12
- "layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00039.safetensors",
13
- "layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00039.safetensors",
14
- "layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00039.safetensors",
15
- "layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00039.safetensors",
16
- "layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00039.safetensors",
17
- "layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00039.safetensors",
18
- "layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00039.safetensors",
19
- "layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00039.safetensors",
20
- "layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00039.safetensors",
21
- "layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00039.safetensors",
22
- "layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00039.safetensors",
23
- "layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00039.safetensors",
24
- "layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00039.safetensors",
25
- "layers.0.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00039.safetensors",
26
- "layers.0.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00039.safetensors",
27
- "layers.0.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00039.safetensors",
28
- "layers.0.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00039.safetensors",
29
- "layers.0.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00039.safetensors",
30
- "layers.0.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00039.safetensors",
31
- "layers.0.block_sparse_moe.gate.weight": "model-00001-of-00039.safetensors",
32
- "layers.0.input_layernorm.weight": "model-00002-of-00039.safetensors",
33
- "layers.0.post_attention_layernorm.weight": "model-00002-of-00039.safetensors",
34
- "layers.0.self_attn.k_proj.weight": "model-00001-of-00039.safetensors",
35
- "layers.0.self_attn.o_proj.weight": "model-00001-of-00039.safetensors",
36
- "layers.0.self_attn.q_proj.weight": "model-00001-of-00039.safetensors",
37
- "layers.0.self_attn.v_proj.weight": "model-00001-of-00039.safetensors",
38
- "layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00039.safetensors",
39
- "layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00039.safetensors",
40
- "layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00039.safetensors",
41
- "layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00039.safetensors",
42
- "layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00039.safetensors",
43
- "layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00039.safetensors",
44
- "layers.1.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00039.safetensors",
45
- "layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00039.safetensors",
46
- "layers.1.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00039.safetensors",
47
- "layers.1.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00039.safetensors",
48
- "layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00039.safetensors",
49
- "layers.1.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00039.safetensors",
50
- "layers.1.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00039.safetensors",
51
- "layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00039.safetensors",
52
- "layers.1.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00039.safetensors",
53
- "layers.1.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00039.safetensors",
54
- "layers.1.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00039.safetensors",
55
- "layers.1.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00039.safetensors",
56
- "layers.1.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00039.safetensors",
57
- "layers.1.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00039.safetensors",
58
- "layers.1.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00039.safetensors",
59
- "layers.1.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00039.safetensors",
60
- "layers.1.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00039.safetensors",
61
- "layers.1.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00039.safetensors",
62
- "layers.1.block_sparse_moe.gate.weight": "model-00002-of-00039.safetensors",
63
- "layers.1.input_layernorm.weight": "model-00003-of-00039.safetensors",
64
- "layers.1.post_attention_layernorm.weight": "model-00003-of-00039.safetensors",
65
- "layers.1.self_attn.k_proj.weight": "model-00002-of-00039.safetensors",
66
- "layers.1.self_attn.o_proj.weight": "model-00002-of-00039.safetensors",
67
- "layers.1.self_attn.q_proj.weight": "model-00002-of-00039.safetensors",
68
- "layers.1.self_attn.v_proj.weight": "model-00002-of-00039.safetensors",
69
- "layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00039.safetensors",
70
- "layers.10.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00039.safetensors",
71
- "layers.10.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00039.safetensors",
72
- "layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00039.safetensors",
73
- "layers.10.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00039.safetensors",
74
- "layers.10.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00039.safetensors",
75
- "layers.10.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00039.safetensors",
76
- "layers.10.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00039.safetensors",
77
- "layers.10.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00039.safetensors",
78
- "layers.10.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00039.safetensors",
79
- "layers.10.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00039.safetensors",
80
- "layers.10.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00039.safetensors",
81
- "layers.10.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00039.safetensors",
82
- "layers.10.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00039.safetensors",
83
- "layers.10.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00039.safetensors",
84
- "layers.10.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00039.safetensors",
85
- "layers.10.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00039.safetensors",
86
- "layers.10.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00039.safetensors",
87
- "layers.10.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00039.safetensors",
88
- "layers.10.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00039.safetensors",
89
- "layers.10.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00039.safetensors",
90
- "layers.10.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00039.safetensors",
91
- "layers.10.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00039.safetensors",
92
- "layers.10.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00039.safetensors",
93
- "layers.10.block_sparse_moe.gate.weight": "model-00013-of-00039.safetensors",
94
- "layers.10.input_layernorm.weight": "model-00014-of-00039.safetensors",
95
- "layers.10.post_attention_layernorm.weight": "model-00014-of-00039.safetensors",
96
- "layers.10.self_attn.k_proj.weight": "model-00013-of-00039.safetensors",
97
- "layers.10.self_attn.o_proj.weight": "model-00013-of-00039.safetensors",
98
- "layers.10.self_attn.q_proj.weight": "model-00012-of-00039.safetensors",
99
- "layers.10.self_attn.v_proj.weight": "model-00013-of-00039.safetensors",
100
- "layers.11.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00039.safetensors",
101
- "layers.11.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00039.safetensors",
102
- "layers.11.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00039.safetensors",
103
- "layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00039.safetensors",
104
- "layers.11.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00039.safetensors",
105
- "layers.11.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00039.safetensors",
106
- "layers.11.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00039.safetensors",
107
- "layers.11.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00039.safetensors",
108
- "layers.11.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00039.safetensors",
109
- "layers.11.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00039.safetensors",
110
- "layers.11.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00039.safetensors",
111
- "layers.11.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00039.safetensors",
112
- "layers.11.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00039.safetensors",
113
- "layers.11.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00039.safetensors",
114
- "layers.11.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00039.safetensors",
115
- "layers.11.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00039.safetensors",
116
- "layers.11.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00039.safetensors",
117
- "layers.11.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00039.safetensors",
118
- "layers.11.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00039.safetensors",
119
- "layers.11.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00039.safetensors",
120
- "layers.11.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00039.safetensors",
121
- "layers.11.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00039.safetensors",
122
- "layers.11.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00039.safetensors",
123
- "layers.11.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00039.safetensors",
124
- "layers.11.block_sparse_moe.gate.weight": "model-00014-of-00039.safetensors",
125
- "layers.11.input_layernorm.weight": "model-00015-of-00039.safetensors",
126
- "layers.11.post_attention_layernorm.weight": "model-00015-of-00039.safetensors",
127
- "layers.11.self_attn.k_proj.weight": "model-00014-of-00039.safetensors",
128
- "layers.11.self_attn.o_proj.weight": "model-00014-of-00039.safetensors",
129
- "layers.11.self_attn.q_proj.weight": "model-00014-of-00039.safetensors",
130
- "layers.11.self_attn.v_proj.weight": "model-00014-of-00039.safetensors",
131
- "layers.12.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00039.safetensors",
132
- "layers.12.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00039.safetensors",
133
- "layers.12.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00039.safetensors",
134
- "layers.12.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00039.safetensors",
135
- "layers.12.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00039.safetensors",
136
- "layers.12.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00039.safetensors",
137
- "layers.12.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00039.safetensors",
138
- "layers.12.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00039.safetensors",
139
- "layers.12.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00039.safetensors",
140
- "layers.12.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00039.safetensors",
141
- "layers.12.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00039.safetensors",
142
- "layers.12.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00039.safetensors",
143
- "layers.12.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00039.safetensors",
144
- "layers.12.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00039.safetensors",
145
- "layers.12.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00039.safetensors",
146
- "layers.12.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00039.safetensors",
147
- "layers.12.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00039.safetensors",
148
- "layers.12.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00039.safetensors",
149
- "layers.12.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00039.safetensors",
150
- "layers.12.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00039.safetensors",
151
- "layers.12.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00039.safetensors",
152
- "layers.12.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00039.safetensors",
153
- "layers.12.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00039.safetensors",
154
- "layers.12.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00039.safetensors",
155
- "layers.12.block_sparse_moe.gate.weight": "model-00015-of-00039.safetensors",
156
- "layers.12.input_layernorm.weight": "model-00016-of-00039.safetensors",
157
- "layers.12.post_attention_layernorm.weight": "model-00016-of-00039.safetensors",
158
- "layers.12.self_attn.k_proj.weight": "model-00015-of-00039.safetensors",
159
- "layers.12.self_attn.o_proj.weight": "model-00015-of-00039.safetensors",
160
- "layers.12.self_attn.q_proj.weight": "model-00015-of-00039.safetensors",
161
- "layers.12.self_attn.v_proj.weight": "model-00015-of-00039.safetensors",
162
- "layers.13.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00039.safetensors",
163
- "layers.13.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00039.safetensors",
164
- "layers.13.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00039.safetensors",
165
- "layers.13.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00039.safetensors",
166
- "layers.13.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00039.safetensors",
167
- "layers.13.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00039.safetensors",
168
- "layers.13.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00039.safetensors",
169
- "layers.13.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00039.safetensors",
170
- "layers.13.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00039.safetensors",
171
- "layers.13.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00039.safetensors",
172
- "layers.13.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00039.safetensors",
173
- "layers.13.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00039.safetensors",
174
- "layers.13.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00039.safetensors",
175
- "layers.13.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00039.safetensors",
176
- "layers.13.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00039.safetensors",
177
- "layers.13.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00039.safetensors",
178
- "layers.13.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00039.safetensors",
179
- "layers.13.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00039.safetensors",
180
- "layers.13.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00039.safetensors",
181
- "layers.13.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00039.safetensors",
182
- "layers.13.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00039.safetensors",
183
- "layers.13.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00039.safetensors",
184
- "layers.13.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00039.safetensors",
185
- "layers.13.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00039.safetensors",
186
- "layers.13.block_sparse_moe.gate.weight": "model-00016-of-00039.safetensors",
187
- "layers.13.input_layernorm.weight": "model-00017-of-00039.safetensors",
188
- "layers.13.post_attention_layernorm.weight": "model-00017-of-00039.safetensors",
189
- "layers.13.self_attn.k_proj.weight": "model-00016-of-00039.safetensors",
190
- "layers.13.self_attn.o_proj.weight": "model-00016-of-00039.safetensors",
191
- "layers.13.self_attn.q_proj.weight": "model-00016-of-00039.safetensors",
192
- "layers.13.self_attn.v_proj.weight": "model-00016-of-00039.safetensors",
193
- "layers.14.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00039.safetensors",
194
- "layers.14.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00039.safetensors",
195
- "layers.14.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00039.safetensors",
196
- "layers.14.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00039.safetensors",
197
- "layers.14.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00039.safetensors",
198
- "layers.14.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00039.safetensors",
199
- "layers.14.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00039.safetensors",
200
- "layers.14.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00039.safetensors",
201
- "layers.14.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00039.safetensors",
202
- "layers.14.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00039.safetensors",
203
- "layers.14.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00039.safetensors",
204
- "layers.14.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00039.safetensors",
205
- "layers.14.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00039.safetensors",
206
- "layers.14.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00039.safetensors",
207
- "layers.14.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00039.safetensors",
208
- "layers.14.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00039.safetensors",
209
- "layers.14.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00039.safetensors",
210
- "layers.14.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00039.safetensors",
211
- "layers.14.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00039.safetensors",
212
- "layers.14.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00039.safetensors",
213
- "layers.14.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00039.safetensors",
214
- "layers.14.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00039.safetensors",
215
- "layers.14.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00039.safetensors",
216
- "layers.14.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00039.safetensors",
217
- "layers.14.block_sparse_moe.gate.weight": "model-00017-of-00039.safetensors",
218
- "layers.14.input_layernorm.weight": "model-00018-of-00039.safetensors",
219
- "layers.14.post_attention_layernorm.weight": "model-00018-of-00039.safetensors",
220
- "layers.14.self_attn.k_proj.weight": "model-00017-of-00039.safetensors",
221
- "layers.14.self_attn.o_proj.weight": "model-00017-of-00039.safetensors",
222
- "layers.14.self_attn.q_proj.weight": "model-00017-of-00039.safetensors",
223
- "layers.14.self_attn.v_proj.weight": "model-00017-of-00039.safetensors",
224
- "layers.15.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00039.safetensors",
225
- "layers.15.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00039.safetensors",
226
- "layers.15.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00039.safetensors",
227
- "layers.15.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00039.safetensors",
228
- "layers.15.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00039.safetensors",
229
- "layers.15.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00039.safetensors",
230
- "layers.15.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00039.safetensors",
231
- "layers.15.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00039.safetensors",
232
- "layers.15.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00039.safetensors",
233
- "layers.15.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00039.safetensors",
234
- "layers.15.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00039.safetensors",
235
- "layers.15.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00039.safetensors",
236
- "layers.15.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00039.safetensors",
237
- "layers.15.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00039.safetensors",
238
- "layers.15.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00039.safetensors",
239
- "layers.15.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00039.safetensors",
240
- "layers.15.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00039.safetensors",
241
- "layers.15.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00039.safetensors",
242
- "layers.15.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00039.safetensors",
243
- "layers.15.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00039.safetensors",
244
- "layers.15.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00039.safetensors",
245
- "layers.15.block_sparse_moe.experts.7.w1.weight": "model-00020-of-00039.safetensors",
246
- "layers.15.block_sparse_moe.experts.7.w2.weight": "model-00020-of-00039.safetensors",
247
- "layers.15.block_sparse_moe.experts.7.w3.weight": "model-00020-of-00039.safetensors",
248
- "layers.15.block_sparse_moe.gate.weight": "model-00018-of-00039.safetensors",
249
- "layers.15.input_layernorm.weight": "model-00020-of-00039.safetensors",
250
- "layers.15.post_attention_layernorm.weight": "model-00020-of-00039.safetensors",
251
- "layers.15.self_attn.k_proj.weight": "model-00018-of-00039.safetensors",
252
- "layers.15.self_attn.o_proj.weight": "model-00018-of-00039.safetensors",
253
- "layers.15.self_attn.q_proj.weight": "model-00018-of-00039.safetensors",
254
- "layers.15.self_attn.v_proj.weight": "model-00018-of-00039.safetensors",
255
- "layers.16.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00039.safetensors",
256
- "layers.16.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00039.safetensors",
257
- "layers.16.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00039.safetensors",
258
- "layers.16.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00039.safetensors",
259
- "layers.16.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00039.safetensors",
260
- "layers.16.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00039.safetensors",
261
- "layers.16.block_sparse_moe.experts.2.w1.weight": "model-00020-of-00039.safetensors",
262
- "layers.16.block_sparse_moe.experts.2.w2.weight": "model-00020-of-00039.safetensors",
263
- "layers.16.block_sparse_moe.experts.2.w3.weight": "model-00020-of-00039.safetensors",
264
- "layers.16.block_sparse_moe.experts.3.w1.weight": "model-00020-of-00039.safetensors",
265
- "layers.16.block_sparse_moe.experts.3.w2.weight": "model-00020-of-00039.safetensors",
266
- "layers.16.block_sparse_moe.experts.3.w3.weight": "model-00020-of-00039.safetensors",
267
- "layers.16.block_sparse_moe.experts.4.w1.weight": "model-00020-of-00039.safetensors",
268
- "layers.16.block_sparse_moe.experts.4.w2.weight": "model-00020-of-00039.safetensors",
269
- "layers.16.block_sparse_moe.experts.4.w3.weight": "model-00020-of-00039.safetensors",
270
- "layers.16.block_sparse_moe.experts.5.w1.weight": "model-00020-of-00039.safetensors",
271
- "layers.16.block_sparse_moe.experts.5.w2.weight": "model-00020-of-00039.safetensors",
272
- "layers.16.block_sparse_moe.experts.5.w3.weight": "model-00021-of-00039.safetensors",
273
- "layers.16.block_sparse_moe.experts.6.w1.weight": "model-00021-of-00039.safetensors",
274
- "layers.16.block_sparse_moe.experts.6.w2.weight": "model-00021-of-00039.safetensors",
275
- "layers.16.block_sparse_moe.experts.6.w3.weight": "model-00021-of-00039.safetensors",
276
- "layers.16.block_sparse_moe.experts.7.w1.weight": "model-00021-of-00039.safetensors",
277
- "layers.16.block_sparse_moe.experts.7.w2.weight": "model-00021-of-00039.safetensors",
278
- "layers.16.block_sparse_moe.experts.7.w3.weight": "model-00021-of-00039.safetensors",
279
- "layers.16.block_sparse_moe.gate.weight": "model-00020-of-00039.safetensors",
280
- "layers.16.input_layernorm.weight": "model-00021-of-00039.safetensors",
281
- "layers.16.post_attention_layernorm.weight": "model-00021-of-00039.safetensors",
282
- "layers.16.self_attn.k_proj.weight": "model-00020-of-00039.safetensors",
283
- "layers.16.self_attn.o_proj.weight": "model-00020-of-00039.safetensors",
284
- "layers.16.self_attn.q_proj.weight": "model-00020-of-00039.safetensors",
285
- "layers.16.self_attn.v_proj.weight": "model-00020-of-00039.safetensors",
286
- "layers.17.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00039.safetensors",
287
- "layers.17.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00039.safetensors",
288
- "layers.17.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00039.safetensors",
289
- "layers.17.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00039.safetensors",
290
- "layers.17.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00039.safetensors",
291
- "layers.17.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00039.safetensors",
292
- "layers.17.block_sparse_moe.experts.2.w1.weight": "model-00021-of-00039.safetensors",
293
- "layers.17.block_sparse_moe.experts.2.w2.weight": "model-00021-of-00039.safetensors",
294
- "layers.17.block_sparse_moe.experts.2.w3.weight": "model-00021-of-00039.safetensors",
295
- "layers.17.block_sparse_moe.experts.3.w1.weight": "model-00021-of-00039.safetensors",
296
- "layers.17.block_sparse_moe.experts.3.w2.weight": "model-00021-of-00039.safetensors",
297
- "layers.17.block_sparse_moe.experts.3.w3.weight": "model-00021-of-00039.safetensors",
298
- "layers.17.block_sparse_moe.experts.4.w1.weight": "model-00021-of-00039.safetensors",
299
- "layers.17.block_sparse_moe.experts.4.w2.weight": "model-00022-of-00039.safetensors",
300
- "layers.17.block_sparse_moe.experts.4.w3.weight": "model-00022-of-00039.safetensors",
301
- "layers.17.block_sparse_moe.experts.5.w1.weight": "model-00022-of-00039.safetensors",
302
- "layers.17.block_sparse_moe.experts.5.w2.weight": "model-00022-of-00039.safetensors",
303
- "layers.17.block_sparse_moe.experts.5.w3.weight": "model-00022-of-00039.safetensors",
304
- "layers.17.block_sparse_moe.experts.6.w1.weight": "model-00022-of-00039.safetensors",
305
- "layers.17.block_sparse_moe.experts.6.w2.weight": "model-00022-of-00039.safetensors",
306
- "layers.17.block_sparse_moe.experts.6.w3.weight": "model-00022-of-00039.safetensors",
307
- "layers.17.block_sparse_moe.experts.7.w1.weight": "model-00022-of-00039.safetensors",
308
- "layers.17.block_sparse_moe.experts.7.w2.weight": "model-00022-of-00039.safetensors",
309
- "layers.17.block_sparse_moe.experts.7.w3.weight": "model-00022-of-00039.safetensors",
310
- "layers.17.block_sparse_moe.gate.weight": "model-00021-of-00039.safetensors",
311
- "layers.17.input_layernorm.weight": "model-00022-of-00039.safetensors",
312
- "layers.17.post_attention_layernorm.weight": "model-00022-of-00039.safetensors",
313
- "layers.17.self_attn.k_proj.weight": "model-00021-of-00039.safetensors",
314
- "layers.17.self_attn.o_proj.weight": "model-00021-of-00039.safetensors",
315
- "layers.17.self_attn.q_proj.weight": "model-00021-of-00039.safetensors",
316
- "layers.17.self_attn.v_proj.weight": "model-00021-of-00039.safetensors",
317
- "layers.18.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00039.safetensors",
318
- "layers.18.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00039.safetensors",
319
- "layers.18.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00039.safetensors",
320
- "layers.18.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00039.safetensors",
321
- "layers.18.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00039.safetensors",
322
- "layers.18.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00039.safetensors",
323
- "layers.18.block_sparse_moe.experts.2.w1.weight": "model-00022-of-00039.safetensors",
324
- "layers.18.block_sparse_moe.experts.2.w2.weight": "model-00022-of-00039.safetensors",
325
- "layers.18.block_sparse_moe.experts.2.w3.weight": "model-00022-of-00039.safetensors",
326
- "layers.18.block_sparse_moe.experts.3.w1.weight": "model-00023-of-00039.safetensors",
327
- "layers.18.block_sparse_moe.experts.3.w2.weight": "model-00023-of-00039.safetensors",
328
- "layers.18.block_sparse_moe.experts.3.w3.weight": "model-00023-of-00039.safetensors",
329
- "layers.18.block_sparse_moe.experts.4.w1.weight": "model-00023-of-00039.safetensors",
330
- "layers.18.block_sparse_moe.experts.4.w2.weight": "model-00023-of-00039.safetensors",
331
- "layers.18.block_sparse_moe.experts.4.w3.weight": "model-00023-of-00039.safetensors",
332
- "layers.18.block_sparse_moe.experts.5.w1.weight": "model-00023-of-00039.safetensors",
333
- "layers.18.block_sparse_moe.experts.5.w2.weight": "model-00023-of-00039.safetensors",
334
- "layers.18.block_sparse_moe.experts.5.w3.weight": "model-00023-of-00039.safetensors",
335
- "layers.18.block_sparse_moe.experts.6.w1.weight": "model-00023-of-00039.safetensors",
336
- "layers.18.block_sparse_moe.experts.6.w2.weight": "model-00023-of-00039.safetensors",
337
- "layers.18.block_sparse_moe.experts.6.w3.weight": "model-00023-of-00039.safetensors",
338
- "layers.18.block_sparse_moe.experts.7.w1.weight": "model-00023-of-00039.safetensors",
339
- "layers.18.block_sparse_moe.experts.7.w2.weight": "model-00023-of-00039.safetensors",
340
- "layers.18.block_sparse_moe.experts.7.w3.weight": "model-00023-of-00039.safetensors",
341
- "layers.18.block_sparse_moe.gate.weight": "model-00022-of-00039.safetensors",
342
- "layers.18.input_layernorm.weight": "model-00023-of-00039.safetensors",
343
- "layers.18.post_attention_layernorm.weight": "model-00023-of-00039.safetensors",
344
- "layers.18.self_attn.k_proj.weight": "model-00022-of-00039.safetensors",
345
- "layers.18.self_attn.o_proj.weight": "model-00022-of-00039.safetensors",
346
- "layers.18.self_attn.q_proj.weight": "model-00022-of-00039.safetensors",
347
- "layers.18.self_attn.v_proj.weight": "model-00022-of-00039.safetensors",
348
- "layers.19.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00039.safetensors",
349
- "layers.19.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00039.safetensors",
350
- "layers.19.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00039.safetensors",
351
- "layers.19.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00039.safetensors",
352
- "layers.19.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00039.safetensors",
353
- "layers.19.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00039.safetensors",
354
- "layers.19.block_sparse_moe.experts.2.w1.weight": "model-00024-of-00039.safetensors",
355
- "layers.19.block_sparse_moe.experts.2.w2.weight": "model-00024-of-00039.safetensors",
356
- "layers.19.block_sparse_moe.experts.2.w3.weight": "model-00024-of-00039.safetensors",
357
- "layers.19.block_sparse_moe.experts.3.w1.weight": "model-00024-of-00039.safetensors",
358
- "layers.19.block_sparse_moe.experts.3.w2.weight": "model-00024-of-00039.safetensors",
359
- "layers.19.block_sparse_moe.experts.3.w3.weight": "model-00024-of-00039.safetensors",
360
- "layers.19.block_sparse_moe.experts.4.w1.weight": "model-00024-of-00039.safetensors",
361
- "layers.19.block_sparse_moe.experts.4.w2.weight": "model-00024-of-00039.safetensors",
362
- "layers.19.block_sparse_moe.experts.4.w3.weight": "model-00024-of-00039.safetensors",
363
- "layers.19.block_sparse_moe.experts.5.w1.weight": "model-00024-of-00039.safetensors",
364
- "layers.19.block_sparse_moe.experts.5.w2.weight": "model-00024-of-00039.safetensors",
365
- "layers.19.block_sparse_moe.experts.5.w3.weight": "model-00024-of-00039.safetensors",
366
- "layers.19.block_sparse_moe.experts.6.w1.weight": "model-00024-of-00039.safetensors",
367
- "layers.19.block_sparse_moe.experts.6.w2.weight": "model-00024-of-00039.safetensors",
368
- "layers.19.block_sparse_moe.experts.6.w3.weight": "model-00024-of-00039.safetensors",
369
- "layers.19.block_sparse_moe.experts.7.w1.weight": "model-00024-of-00039.safetensors",
370
- "layers.19.block_sparse_moe.experts.7.w2.weight": "model-00024-of-00039.safetensors",
371
- "layers.19.block_sparse_moe.experts.7.w3.weight": "model-00024-of-00039.safetensors",
372
- "layers.19.block_sparse_moe.gate.weight": "model-00023-of-00039.safetensors",
373
- "layers.19.input_layernorm.weight": "model-00024-of-00039.safetensors",
374
- "layers.19.post_attention_layernorm.weight": "model-00024-of-00039.safetensors",
375
- "layers.19.self_attn.k_proj.weight": "model-00023-of-00039.safetensors",
376
- "layers.19.self_attn.o_proj.weight": "model-00023-of-00039.safetensors",
377
- "layers.19.self_attn.q_proj.weight": "model-00023-of-00039.safetensors",
378
- "layers.19.self_attn.v_proj.weight": "model-00023-of-00039.safetensors",
379
- "layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00039.safetensors",
380
- "layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00039.safetensors",
381
- "layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00039.safetensors",
382
- "layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00039.safetensors",
383
- "layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00039.safetensors",
384
- "layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00039.safetensors",
385
- "layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00039.safetensors",
386
- "layers.2.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00039.safetensors",
387
- "layers.2.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00039.safetensors",
388
- "layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00039.safetensors",
389
- "layers.2.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00039.safetensors",
390
- "layers.2.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00039.safetensors",
391
- "layers.2.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00039.safetensors",
392
- "layers.2.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00039.safetensors",
393
- "layers.2.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00039.safetensors",
394
- "layers.2.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00039.safetensors",
395
- "layers.2.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00039.safetensors",
396
- "layers.2.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00039.safetensors",
397
- "layers.2.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00039.safetensors",
398
- "layers.2.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00039.safetensors",
399
- "layers.2.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00039.safetensors",
400
- "layers.2.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00039.safetensors",
401
- "layers.2.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00039.safetensors",
402
- "layers.2.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00039.safetensors",
403
- "layers.2.block_sparse_moe.gate.weight": "model-00003-of-00039.safetensors",
404
- "layers.2.input_layernorm.weight": "model-00004-of-00039.safetensors",
405
- "layers.2.post_attention_layernorm.weight": "model-00004-of-00039.safetensors",
406
- "layers.2.self_attn.k_proj.weight": "model-00003-of-00039.safetensors",
407
- "layers.2.self_attn.o_proj.weight": "model-00003-of-00039.safetensors",
408
- "layers.2.self_attn.q_proj.weight": "model-00003-of-00039.safetensors",
409
- "layers.2.self_attn.v_proj.weight": "model-00003-of-00039.safetensors",
410
- "layers.20.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00039.safetensors",
411
- "layers.20.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00039.safetensors",
412
- "layers.20.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00039.safetensors",
413
- "layers.20.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00039.safetensors",
414
- "layers.20.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00039.safetensors",
415
- "layers.20.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00039.safetensors",
416
- "layers.20.block_sparse_moe.experts.2.w1.weight": "model-00025-of-00039.safetensors",
417
- "layers.20.block_sparse_moe.experts.2.w2.weight": "model-00025-of-00039.safetensors",
418
- "layers.20.block_sparse_moe.experts.2.w3.weight": "model-00025-of-00039.safetensors",
419
- "layers.20.block_sparse_moe.experts.3.w1.weight": "model-00025-of-00039.safetensors",
420
- "layers.20.block_sparse_moe.experts.3.w2.weight": "model-00025-of-00039.safetensors",
421
- "layers.20.block_sparse_moe.experts.3.w3.weight": "model-00025-of-00039.safetensors",
422
- "layers.20.block_sparse_moe.experts.4.w1.weight": "model-00025-of-00039.safetensors",
423
- "layers.20.block_sparse_moe.experts.4.w2.weight": "model-00025-of-00039.safetensors",
424
- "layers.20.block_sparse_moe.experts.4.w3.weight": "model-00025-of-00039.safetensors",
425
- "layers.20.block_sparse_moe.experts.5.w1.weight": "model-00025-of-00039.safetensors",
426
- "layers.20.block_sparse_moe.experts.5.w2.weight": "model-00025-of-00039.safetensors",
427
- "layers.20.block_sparse_moe.experts.5.w3.weight": "model-00025-of-00039.safetensors",
428
- "layers.20.block_sparse_moe.experts.6.w1.weight": "model-00025-of-00039.safetensors",
429
- "layers.20.block_sparse_moe.experts.6.w2.weight": "model-00025-of-00039.safetensors",
430
- "layers.20.block_sparse_moe.experts.6.w3.weight": "model-00025-of-00039.safetensors",
431
- "layers.20.block_sparse_moe.experts.7.w1.weight": "model-00025-of-00039.safetensors",
432
- "layers.20.block_sparse_moe.experts.7.w2.weight": "model-00026-of-00039.safetensors",
433
- "layers.20.block_sparse_moe.experts.7.w3.weight": "model-00026-of-00039.safetensors",
434
- "layers.20.block_sparse_moe.gate.weight": "model-00024-of-00039.safetensors",
435
- "layers.20.input_layernorm.weight": "model-00026-of-00039.safetensors",
436
- "layers.20.post_attention_layernorm.weight": "model-00026-of-00039.safetensors",
437
- "layers.20.self_attn.k_proj.weight": "model-00024-of-00039.safetensors",
438
- "layers.20.self_attn.o_proj.weight": "model-00024-of-00039.safetensors",
439
- "layers.20.self_attn.q_proj.weight": "model-00024-of-00039.safetensors",
440
- "layers.20.self_attn.v_proj.weight": "model-00024-of-00039.safetensors",
441
- "layers.21.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00039.safetensors",
442
- "layers.21.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00039.safetensors",
443
- "layers.21.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00039.safetensors",
444
- "layers.21.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00039.safetensors",
445
- "layers.21.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00039.safetensors",
446
- "layers.21.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00039.safetensors",
447
- "layers.21.block_sparse_moe.experts.2.w1.weight": "model-00026-of-00039.safetensors",
448
- "layers.21.block_sparse_moe.experts.2.w2.weight": "model-00026-of-00039.safetensors",
449
- "layers.21.block_sparse_moe.experts.2.w3.weight": "model-00026-of-00039.safetensors",
450
- "layers.21.block_sparse_moe.experts.3.w1.weight": "model-00026-of-00039.safetensors",
451
- "layers.21.block_sparse_moe.experts.3.w2.weight": "model-00026-of-00039.safetensors",
452
- "layers.21.block_sparse_moe.experts.3.w3.weight": "model-00026-of-00039.safetensors",
453
- "layers.21.block_sparse_moe.experts.4.w1.weight": "model-00026-of-00039.safetensors",
454
- "layers.21.block_sparse_moe.experts.4.w2.weight": "model-00026-of-00039.safetensors",
455
- "layers.21.block_sparse_moe.experts.4.w3.weight": "model-00026-of-00039.safetensors",
456
- "layers.21.block_sparse_moe.experts.5.w1.weight": "model-00026-of-00039.safetensors",
457
- "layers.21.block_sparse_moe.experts.5.w2.weight": "model-00026-of-00039.safetensors",
458
- "layers.21.block_sparse_moe.experts.5.w3.weight": "model-00026-of-00039.safetensors",
459
- "layers.21.block_sparse_moe.experts.6.w1.weight": "model-00027-of-00039.safetensors",
460
- "layers.21.block_sparse_moe.experts.6.w2.weight": "model-00027-of-00039.safetensors",
461
- "layers.21.block_sparse_moe.experts.6.w3.weight": "model-00027-of-00039.safetensors",
462
- "layers.21.block_sparse_moe.experts.7.w1.weight": "model-00027-of-00039.safetensors",
463
- "layers.21.block_sparse_moe.experts.7.w2.weight": "model-00027-of-00039.safetensors",
464
- "layers.21.block_sparse_moe.experts.7.w3.weight": "model-00027-of-00039.safetensors",
465
- "layers.21.block_sparse_moe.gate.weight": "model-00026-of-00039.safetensors",
466
- "layers.21.input_layernorm.weight": "model-00027-of-00039.safetensors",
467
- "layers.21.post_attention_layernorm.weight": "model-00027-of-00039.safetensors",
468
- "layers.21.self_attn.k_proj.weight": "model-00026-of-00039.safetensors",
469
- "layers.21.self_attn.o_proj.weight": "model-00026-of-00039.safetensors",
470
- "layers.21.self_attn.q_proj.weight": "model-00026-of-00039.safetensors",
471
- "layers.21.self_attn.v_proj.weight": "model-00026-of-00039.safetensors",
472
- "layers.22.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00039.safetensors",
473
- "layers.22.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00039.safetensors",
474
- "layers.22.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00039.safetensors",
475
- "layers.22.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00039.safetensors",
476
- "layers.22.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00039.safetensors",
477
- "layers.22.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00039.safetensors",
478
- "layers.22.block_sparse_moe.experts.2.w1.weight": "model-00027-of-00039.safetensors",
479
- "layers.22.block_sparse_moe.experts.2.w2.weight": "model-00027-of-00039.safetensors",
480
- "layers.22.block_sparse_moe.experts.2.w3.weight": "model-00027-of-00039.safetensors",
481
- "layers.22.block_sparse_moe.experts.3.w1.weight": "model-00027-of-00039.safetensors",
482
- "layers.22.block_sparse_moe.experts.3.w2.weight": "model-00027-of-00039.safetensors",
483
- "layers.22.block_sparse_moe.experts.3.w3.weight": "model-00027-of-00039.safetensors",
484
- "layers.22.block_sparse_moe.experts.4.w1.weight": "model-00027-of-00039.safetensors",
485
- "layers.22.block_sparse_moe.experts.4.w2.weight": "model-00027-of-00039.safetensors",
486
- "layers.22.block_sparse_moe.experts.4.w3.weight": "model-00028-of-00039.safetensors",
487
- "layers.22.block_sparse_moe.experts.5.w1.weight": "model-00028-of-00039.safetensors",
488
- "layers.22.block_sparse_moe.experts.5.w2.weight": "model-00028-of-00039.safetensors",
489
- "layers.22.block_sparse_moe.experts.5.w3.weight": "model-00028-of-00039.safetensors",
490
- "layers.22.block_sparse_moe.experts.6.w1.weight": "model-00028-of-00039.safetensors",
491
- "layers.22.block_sparse_moe.experts.6.w2.weight": "model-00028-of-00039.safetensors",
492
- "layers.22.block_sparse_moe.experts.6.w3.weight": "model-00028-of-00039.safetensors",
493
- "layers.22.block_sparse_moe.experts.7.w1.weight": "model-00028-of-00039.safetensors",
494
- "layers.22.block_sparse_moe.experts.7.w2.weight": "model-00028-of-00039.safetensors",
495
- "layers.22.block_sparse_moe.experts.7.w3.weight": "model-00028-of-00039.safetensors",
496
- "layers.22.block_sparse_moe.gate.weight": "model-00027-of-00039.safetensors",
497
- "layers.22.input_layernorm.weight": "model-00028-of-00039.safetensors",
498
- "layers.22.post_attention_layernorm.weight": "model-00028-of-00039.safetensors",
499
- "layers.22.self_attn.k_proj.weight": "model-00027-of-00039.safetensors",
500
- "layers.22.self_attn.o_proj.weight": "model-00027-of-00039.safetensors",
501
- "layers.22.self_attn.q_proj.weight": "model-00027-of-00039.safetensors",
502
- "layers.22.self_attn.v_proj.weight": "model-00027-of-00039.safetensors",
503
- "layers.23.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00039.safetensors",
504
- "layers.23.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00039.safetensors",
505
- "layers.23.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00039.safetensors",
506
- "layers.23.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00039.safetensors",
507
- "layers.23.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00039.safetensors",
508
- "layers.23.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00039.safetensors",
509
- "layers.23.block_sparse_moe.experts.2.w1.weight": "model-00028-of-00039.safetensors",
510
- "layers.23.block_sparse_moe.experts.2.w2.weight": "model-00028-of-00039.safetensors",
511
- "layers.23.block_sparse_moe.experts.2.w3.weight": "model-00028-of-00039.safetensors",
512
- "layers.23.block_sparse_moe.experts.3.w1.weight": "model-00028-of-00039.safetensors",
513
- "layers.23.block_sparse_moe.experts.3.w2.weight": "model-00029-of-00039.safetensors",
514
- "layers.23.block_sparse_moe.experts.3.w3.weight": "model-00029-of-00039.safetensors",
515
- "layers.23.block_sparse_moe.experts.4.w1.weight": "model-00029-of-00039.safetensors",
516
- "layers.23.block_sparse_moe.experts.4.w2.weight": "model-00029-of-00039.safetensors",
517
- "layers.23.block_sparse_moe.experts.4.w3.weight": "model-00029-of-00039.safetensors",
518
- "layers.23.block_sparse_moe.experts.5.w1.weight": "model-00029-of-00039.safetensors",
519
- "layers.23.block_sparse_moe.experts.5.w2.weight": "model-00029-of-00039.safetensors",
520
- "layers.23.block_sparse_moe.experts.5.w3.weight": "model-00029-of-00039.safetensors",
521
- "layers.23.block_sparse_moe.experts.6.w1.weight": "model-00029-of-00039.safetensors",
522
- "layers.23.block_sparse_moe.experts.6.w2.weight": "model-00029-of-00039.safetensors",
523
- "layers.23.block_sparse_moe.experts.6.w3.weight": "model-00029-of-00039.safetensors",
524
- "layers.23.block_sparse_moe.experts.7.w1.weight": "model-00029-of-00039.safetensors",
525
- "layers.23.block_sparse_moe.experts.7.w2.weight": "model-00029-of-00039.safetensors",
526
- "layers.23.block_sparse_moe.experts.7.w3.weight": "model-00029-of-00039.safetensors",
527
- "layers.23.block_sparse_moe.gate.weight": "model-00028-of-00039.safetensors",
528
- "layers.23.input_layernorm.weight": "model-00029-of-00039.safetensors",
529
- "layers.23.post_attention_layernorm.weight": "model-00029-of-00039.safetensors",
530
- "layers.23.self_attn.k_proj.weight": "model-00028-of-00039.safetensors",
531
- "layers.23.self_attn.o_proj.weight": "model-00028-of-00039.safetensors",
532
- "layers.23.self_attn.q_proj.weight": "model-00028-of-00039.safetensors",
533
- "layers.23.self_attn.v_proj.weight": "model-00028-of-00039.safetensors",
534
- "layers.24.block_sparse_moe.experts.0.w1.weight": "model-00029-of-00039.safetensors",
535
- "layers.24.block_sparse_moe.experts.0.w2.weight": "model-00029-of-00039.safetensors",
536
- "layers.24.block_sparse_moe.experts.0.w3.weight": "model-00029-of-00039.safetensors",
537
- "layers.24.block_sparse_moe.experts.1.w1.weight": "model-00029-of-00039.safetensors",
538
- "layers.24.block_sparse_moe.experts.1.w2.weight": "model-00029-of-00039.safetensors",
539
- "layers.24.block_sparse_moe.experts.1.w3.weight": "model-00029-of-00039.safetensors",
540
- "layers.24.block_sparse_moe.experts.2.w1.weight": "model-00030-of-00039.safetensors",
541
- "layers.24.block_sparse_moe.experts.2.w2.weight": "model-00030-of-00039.safetensors",
542
- "layers.24.block_sparse_moe.experts.2.w3.weight": "model-00030-of-00039.safetensors",
543
- "layers.24.block_sparse_moe.experts.3.w1.weight": "model-00030-of-00039.safetensors",
544
- "layers.24.block_sparse_moe.experts.3.w2.weight": "model-00030-of-00039.safetensors",
545
- "layers.24.block_sparse_moe.experts.3.w3.weight": "model-00030-of-00039.safetensors",
546
- "layers.24.block_sparse_moe.experts.4.w1.weight": "model-00030-of-00039.safetensors",
547
- "layers.24.block_sparse_moe.experts.4.w2.weight": "model-00030-of-00039.safetensors",
548
- "layers.24.block_sparse_moe.experts.4.w3.weight": "model-00030-of-00039.safetensors",
549
- "layers.24.block_sparse_moe.experts.5.w1.weight": "model-00030-of-00039.safetensors",
550
- "layers.24.block_sparse_moe.experts.5.w2.weight": "model-00030-of-00039.safetensors",
551
- "layers.24.block_sparse_moe.experts.5.w3.weight": "model-00030-of-00039.safetensors",
552
- "layers.24.block_sparse_moe.experts.6.w1.weight": "model-00030-of-00039.safetensors",
553
- "layers.24.block_sparse_moe.experts.6.w2.weight": "model-00030-of-00039.safetensors",
554
- "layers.24.block_sparse_moe.experts.6.w3.weight": "model-00030-of-00039.safetensors",
555
- "layers.24.block_sparse_moe.experts.7.w1.weight": "model-00030-of-00039.safetensors",
556
- "layers.24.block_sparse_moe.experts.7.w2.weight": "model-00030-of-00039.safetensors",
557
- "layers.24.block_sparse_moe.experts.7.w3.weight": "model-00030-of-00039.safetensors",
558
- "layers.24.block_sparse_moe.gate.weight": "model-00029-of-00039.safetensors",
559
- "layers.24.input_layernorm.weight": "model-00030-of-00039.safetensors",
560
- "layers.24.post_attention_layernorm.weight": "model-00030-of-00039.safetensors",
561
- "layers.24.self_attn.k_proj.weight": "model-00029-of-00039.safetensors",
562
- "layers.24.self_attn.o_proj.weight": "model-00029-of-00039.safetensors",
563
- "layers.24.self_attn.q_proj.weight": "model-00029-of-00039.safetensors",
564
- "layers.24.self_attn.v_proj.weight": "model-00029-of-00039.safetensors",
565
- "layers.25.block_sparse_moe.experts.0.w1.weight": "model-00030-of-00039.safetensors",
566
- "layers.25.block_sparse_moe.experts.0.w2.weight": "model-00030-of-00039.safetensors",
567
- "layers.25.block_sparse_moe.experts.0.w3.weight": "model-00031-of-00039.safetensors",
568
- "layers.25.block_sparse_moe.experts.1.w1.weight": "model-00031-of-00039.safetensors",
569
- "layers.25.block_sparse_moe.experts.1.w2.weight": "model-00031-of-00039.safetensors",
570
- "layers.25.block_sparse_moe.experts.1.w3.weight": "model-00031-of-00039.safetensors",
571
- "layers.25.block_sparse_moe.experts.2.w1.weight": "model-00031-of-00039.safetensors",
572
- "layers.25.block_sparse_moe.experts.2.w2.weight": "model-00031-of-00039.safetensors",
573
- "layers.25.block_sparse_moe.experts.2.w3.weight": "model-00031-of-00039.safetensors",
574
- "layers.25.block_sparse_moe.experts.3.w1.weight": "model-00031-of-00039.safetensors",
575
- "layers.25.block_sparse_moe.experts.3.w2.weight": "model-00031-of-00039.safetensors",
576
- "layers.25.block_sparse_moe.experts.3.w3.weight": "model-00031-of-00039.safetensors",
577
- "layers.25.block_sparse_moe.experts.4.w1.weight": "model-00031-of-00039.safetensors",
578
- "layers.25.block_sparse_moe.experts.4.w2.weight": "model-00031-of-00039.safetensors",
579
- "layers.25.block_sparse_moe.experts.4.w3.weight": "model-00031-of-00039.safetensors",
580
- "layers.25.block_sparse_moe.experts.5.w1.weight": "model-00031-of-00039.safetensors",
581
- "layers.25.block_sparse_moe.experts.5.w2.weight": "model-00031-of-00039.safetensors",
582
- "layers.25.block_sparse_moe.experts.5.w3.weight": "model-00031-of-00039.safetensors",
583
- "layers.25.block_sparse_moe.experts.6.w1.weight": "model-00031-of-00039.safetensors",
584
- "layers.25.block_sparse_moe.experts.6.w2.weight": "model-00031-of-00039.safetensors",
585
- "layers.25.block_sparse_moe.experts.6.w3.weight": "model-00031-of-00039.safetensors",
586
- "layers.25.block_sparse_moe.experts.7.w1.weight": "model-00031-of-00039.safetensors",
587
- "layers.25.block_sparse_moe.experts.7.w2.weight": "model-00031-of-00039.safetensors",
588
- "layers.25.block_sparse_moe.experts.7.w3.weight": "model-00032-of-00039.safetensors",
589
- "layers.25.block_sparse_moe.gate.weight": "model-00030-of-00039.safetensors",
590
- "layers.25.input_layernorm.weight": "model-00032-of-00039.safetensors",
591
- "layers.25.post_attention_layernorm.weight": "model-00032-of-00039.safetensors",
592
- "layers.25.self_attn.k_proj.weight": "model-00030-of-00039.safetensors",
593
- "layers.25.self_attn.o_proj.weight": "model-00030-of-00039.safetensors",
594
- "layers.25.self_attn.q_proj.weight": "model-00030-of-00039.safetensors",
595
- "layers.25.self_attn.v_proj.weight": "model-00030-of-00039.safetensors",
596
- "layers.26.block_sparse_moe.experts.0.w1.weight": "model-00032-of-00039.safetensors",
597
- "layers.26.block_sparse_moe.experts.0.w2.weight": "model-00032-of-00039.safetensors",
598
- "layers.26.block_sparse_moe.experts.0.w3.weight": "model-00032-of-00039.safetensors",
599
- "layers.26.block_sparse_moe.experts.1.w1.weight": "model-00032-of-00039.safetensors",
600
- "layers.26.block_sparse_moe.experts.1.w2.weight": "model-00032-of-00039.safetensors",
601
- "layers.26.block_sparse_moe.experts.1.w3.weight": "model-00032-of-00039.safetensors",
602
- "layers.26.block_sparse_moe.experts.2.w1.weight": "model-00032-of-00039.safetensors",
603
- "layers.26.block_sparse_moe.experts.2.w2.weight": "model-00032-of-00039.safetensors",
604
- "layers.26.block_sparse_moe.experts.2.w3.weight": "model-00032-of-00039.safetensors",
605
- "layers.26.block_sparse_moe.experts.3.w1.weight": "model-00032-of-00039.safetensors",
606
- "layers.26.block_sparse_moe.experts.3.w2.weight": "model-00032-of-00039.safetensors",
607
- "layers.26.block_sparse_moe.experts.3.w3.weight": "model-00032-of-00039.safetensors",
608
- "layers.26.block_sparse_moe.experts.4.w1.weight": "model-00032-of-00039.safetensors",
609
- "layers.26.block_sparse_moe.experts.4.w2.weight": "model-00032-of-00039.safetensors",
610
- "layers.26.block_sparse_moe.experts.4.w3.weight": "model-00032-of-00039.safetensors",
611
- "layers.26.block_sparse_moe.experts.5.w1.weight": "model-00032-of-00039.safetensors",
612
- "layers.26.block_sparse_moe.experts.5.w2.weight": "model-00032-of-00039.safetensors",
613
- "layers.26.block_sparse_moe.experts.5.w3.weight": "model-00032-of-00039.safetensors",
614
- "layers.26.block_sparse_moe.experts.6.w1.weight": "model-00032-of-00039.safetensors",
615
- "layers.26.block_sparse_moe.experts.6.w2.weight": "model-00033-of-00039.safetensors",
616
- "layers.26.block_sparse_moe.experts.6.w3.weight": "model-00033-of-00039.safetensors",
617
- "layers.26.block_sparse_moe.experts.7.w1.weight": "model-00033-of-00039.safetensors",
618
- "layers.26.block_sparse_moe.experts.7.w2.weight": "model-00033-of-00039.safetensors",
619
- "layers.26.block_sparse_moe.experts.7.w3.weight": "model-00033-of-00039.safetensors",
620
- "layers.26.block_sparse_moe.gate.weight": "model-00032-of-00039.safetensors",
621
- "layers.26.input_layernorm.weight": "model-00033-of-00039.safetensors",
622
- "layers.26.post_attention_layernorm.weight": "model-00033-of-00039.safetensors",
623
- "layers.26.self_attn.k_proj.weight": "model-00032-of-00039.safetensors",
624
- "layers.26.self_attn.o_proj.weight": "model-00032-of-00039.safetensors",
625
- "layers.26.self_attn.q_proj.weight": "model-00032-of-00039.safetensors",
626
- "layers.26.self_attn.v_proj.weight": "model-00032-of-00039.safetensors",
627
- "layers.27.block_sparse_moe.experts.0.w1.weight": "model-00033-of-00039.safetensors",
628
- "layers.27.block_sparse_moe.experts.0.w2.weight": "model-00033-of-00039.safetensors",
629
- "layers.27.block_sparse_moe.experts.0.w3.weight": "model-00033-of-00039.safetensors",
630
- "layers.27.block_sparse_moe.experts.1.w1.weight": "model-00033-of-00039.safetensors",
631
- "layers.27.block_sparse_moe.experts.1.w2.weight": "model-00033-of-00039.safetensors",
632
- "layers.27.block_sparse_moe.experts.1.w3.weight": "model-00033-of-00039.safetensors",
633
- "layers.27.block_sparse_moe.experts.2.w1.weight": "model-00033-of-00039.safetensors",
634
- "layers.27.block_sparse_moe.experts.2.w2.weight": "model-00033-of-00039.safetensors",
635
- "layers.27.block_sparse_moe.experts.2.w3.weight": "model-00033-of-00039.safetensors",
636
- "layers.27.block_sparse_moe.experts.3.w1.weight": "model-00033-of-00039.safetensors",
637
- "layers.27.block_sparse_moe.experts.3.w2.weight": "model-00033-of-00039.safetensors",
638
- "layers.27.block_sparse_moe.experts.3.w3.weight": "model-00033-of-00039.safetensors",
639
- "layers.27.block_sparse_moe.experts.4.w1.weight": "model-00033-of-00039.safetensors",
640
- "layers.27.block_sparse_moe.experts.4.w2.weight": "model-00033-of-00039.safetensors",
641
- "layers.27.block_sparse_moe.experts.4.w3.weight": "model-00033-of-00039.safetensors",
642
- "layers.27.block_sparse_moe.experts.5.w1.weight": "model-00034-of-00039.safetensors",
643
- "layers.27.block_sparse_moe.experts.5.w2.weight": "model-00034-of-00039.safetensors",
644
- "layers.27.block_sparse_moe.experts.5.w3.weight": "model-00034-of-00039.safetensors",
645
- "layers.27.block_sparse_moe.experts.6.w1.weight": "model-00034-of-00039.safetensors",
646
- "layers.27.block_sparse_moe.experts.6.w2.weight": "model-00034-of-00039.safetensors",
647
- "layers.27.block_sparse_moe.experts.6.w3.weight": "model-00034-of-00039.safetensors",
648
- "layers.27.block_sparse_moe.experts.7.w1.weight": "model-00034-of-00039.safetensors",
649
- "layers.27.block_sparse_moe.experts.7.w2.weight": "model-00034-of-00039.safetensors",
650
- "layers.27.block_sparse_moe.experts.7.w3.weight": "model-00034-of-00039.safetensors",
651
- "layers.27.block_sparse_moe.gate.weight": "model-00033-of-00039.safetensors",
652
- "layers.27.input_layernorm.weight": "model-00034-of-00039.safetensors",
653
- "layers.27.post_attention_layernorm.weight": "model-00034-of-00039.safetensors",
654
- "layers.27.self_attn.k_proj.weight": "model-00033-of-00039.safetensors",
655
- "layers.27.self_attn.o_proj.weight": "model-00033-of-00039.safetensors",
656
- "layers.27.self_attn.q_proj.weight": "model-00033-of-00039.safetensors",
657
- "layers.27.self_attn.v_proj.weight": "model-00033-of-00039.safetensors",
658
- "layers.28.block_sparse_moe.experts.0.w1.weight": "model-00034-of-00039.safetensors",
659
- "layers.28.block_sparse_moe.experts.0.w2.weight": "model-00034-of-00039.safetensors",
660
- "layers.28.block_sparse_moe.experts.0.w3.weight": "model-00034-of-00039.safetensors",
661
- "layers.28.block_sparse_moe.experts.1.w1.weight": "model-00034-of-00039.safetensors",
662
- "layers.28.block_sparse_moe.experts.1.w2.weight": "model-00034-of-00039.safetensors",
663
- "layers.28.block_sparse_moe.experts.1.w3.weight": "model-00034-of-00039.safetensors",
664
- "layers.28.block_sparse_moe.experts.2.w1.weight": "model-00034-of-00039.safetensors",
665
- "layers.28.block_sparse_moe.experts.2.w2.weight": "model-00034-of-00039.safetensors",
666
- "layers.28.block_sparse_moe.experts.2.w3.weight": "model-00034-of-00039.safetensors",
667
- "layers.28.block_sparse_moe.experts.3.w1.weight": "model-00034-of-00039.safetensors",
668
- "layers.28.block_sparse_moe.experts.3.w2.weight": "model-00034-of-00039.safetensors",
669
- "layers.28.block_sparse_moe.experts.3.w3.weight": "model-00035-of-00039.safetensors",
670
- "layers.28.block_sparse_moe.experts.4.w1.weight": "model-00035-of-00039.safetensors",
671
- "layers.28.block_sparse_moe.experts.4.w2.weight": "model-00035-of-00039.safetensors",
672
- "layers.28.block_sparse_moe.experts.4.w3.weight": "model-00035-of-00039.safetensors",
673
- "layers.28.block_sparse_moe.experts.5.w1.weight": "model-00035-of-00039.safetensors",
674
- "layers.28.block_sparse_moe.experts.5.w2.weight": "model-00035-of-00039.safetensors",
675
- "layers.28.block_sparse_moe.experts.5.w3.weight": "model-00035-of-00039.safetensors",
676
- "layers.28.block_sparse_moe.experts.6.w1.weight": "model-00035-of-00039.safetensors",
677
- "layers.28.block_sparse_moe.experts.6.w2.weight": "model-00035-of-00039.safetensors",
678
- "layers.28.block_sparse_moe.experts.6.w3.weight": "model-00035-of-00039.safetensors",
679
- "layers.28.block_sparse_moe.experts.7.w1.weight": "model-00035-of-00039.safetensors",
680
- "layers.28.block_sparse_moe.experts.7.w2.weight": "model-00035-of-00039.safetensors",
681
- "layers.28.block_sparse_moe.experts.7.w3.weight": "model-00035-of-00039.safetensors",
682
- "layers.28.block_sparse_moe.gate.weight": "model-00034-of-00039.safetensors",
683
- "layers.28.input_layernorm.weight": "model-00035-of-00039.safetensors",
684
- "layers.28.post_attention_layernorm.weight": "model-00035-of-00039.safetensors",
685
- "layers.28.self_attn.k_proj.weight": "model-00034-of-00039.safetensors",
686
- "layers.28.self_attn.o_proj.weight": "model-00034-of-00039.safetensors",
687
- "layers.28.self_attn.q_proj.weight": "model-00034-of-00039.safetensors",
688
- "layers.28.self_attn.v_proj.weight": "model-00034-of-00039.safetensors",
689
- "layers.29.block_sparse_moe.experts.0.w1.weight": "model-00035-of-00039.safetensors",
690
- "layers.29.block_sparse_moe.experts.0.w2.weight": "model-00035-of-00039.safetensors",
691
- "layers.29.block_sparse_moe.experts.0.w3.weight": "model-00035-of-00039.safetensors",
692
- "layers.29.block_sparse_moe.experts.1.w1.weight": "model-00035-of-00039.safetensors",
693
- "layers.29.block_sparse_moe.experts.1.w2.weight": "model-00035-of-00039.safetensors",
694
- "layers.29.block_sparse_moe.experts.1.w3.weight": "model-00035-of-00039.safetensors",
695
- "layers.29.block_sparse_moe.experts.2.w1.weight": "model-00035-of-00039.safetensors",
696
- "layers.29.block_sparse_moe.experts.2.w2.weight": "model-00036-of-00039.safetensors",
697
- "layers.29.block_sparse_moe.experts.2.w3.weight": "model-00036-of-00039.safetensors",
698
- "layers.29.block_sparse_moe.experts.3.w1.weight": "model-00036-of-00039.safetensors",
699
- "layers.29.block_sparse_moe.experts.3.w2.weight": "model-00036-of-00039.safetensors",
700
- "layers.29.block_sparse_moe.experts.3.w3.weight": "model-00036-of-00039.safetensors",
701
- "layers.29.block_sparse_moe.experts.4.w1.weight": "model-00036-of-00039.safetensors",
702
- "layers.29.block_sparse_moe.experts.4.w2.weight": "model-00036-of-00039.safetensors",
703
- "layers.29.block_sparse_moe.experts.4.w3.weight": "model-00036-of-00039.safetensors",
704
- "layers.29.block_sparse_moe.experts.5.w1.weight": "model-00036-of-00039.safetensors",
705
- "layers.29.block_sparse_moe.experts.5.w2.weight": "model-00036-of-00039.safetensors",
706
- "layers.29.block_sparse_moe.experts.5.w3.weight": "model-00036-of-00039.safetensors",
707
- "layers.29.block_sparse_moe.experts.6.w1.weight": "model-00036-of-00039.safetensors",
708
- "layers.29.block_sparse_moe.experts.6.w2.weight": "model-00036-of-00039.safetensors",
709
- "layers.29.block_sparse_moe.experts.6.w3.weight": "model-00036-of-00039.safetensors",
710
- "layers.29.block_sparse_moe.experts.7.w1.weight": "model-00036-of-00039.safetensors",
711
- "layers.29.block_sparse_moe.experts.7.w2.weight": "model-00036-of-00039.safetensors",
712
- "layers.29.block_sparse_moe.experts.7.w3.weight": "model-00036-of-00039.safetensors",
713
- "layers.29.block_sparse_moe.gate.weight": "model-00035-of-00039.safetensors",
714
- "layers.29.input_layernorm.weight": "model-00036-of-00039.safetensors",
715
- "layers.29.post_attention_layernorm.weight": "model-00036-of-00039.safetensors",
716
- "layers.29.self_attn.k_proj.weight": "model-00035-of-00039.safetensors",
717
- "layers.29.self_attn.o_proj.weight": "model-00035-of-00039.safetensors",
718
- "layers.29.self_attn.q_proj.weight": "model-00035-of-00039.safetensors",
719
- "layers.29.self_attn.v_proj.weight": "model-00035-of-00039.safetensors",
720
- "layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00039.safetensors",
721
- "layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00039.safetensors",
722
- "layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00039.safetensors",
723
- "layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00039.safetensors",
724
- "layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00039.safetensors",
725
- "layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00039.safetensors",
726
- "layers.3.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00039.safetensors",
727
- "layers.3.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00039.safetensors",
728
- "layers.3.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00039.safetensors",
729
- "layers.3.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00039.safetensors",
730
- "layers.3.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00039.safetensors",
731
- "layers.3.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00039.safetensors",
732
- "layers.3.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00039.safetensors",
733
- "layers.3.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00039.safetensors",
734
- "layers.3.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00039.safetensors",
735
- "layers.3.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00039.safetensors",
736
- "layers.3.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00039.safetensors",
737
- "layers.3.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00039.safetensors",
738
- "layers.3.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00039.safetensors",
739
- "layers.3.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00039.safetensors",
740
- "layers.3.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00039.safetensors",
741
- "layers.3.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00039.safetensors",
742
- "layers.3.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00039.safetensors",
743
- "layers.3.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00039.safetensors",
744
- "layers.3.block_sparse_moe.gate.weight": "model-00004-of-00039.safetensors",
745
- "layers.3.input_layernorm.weight": "model-00005-of-00039.safetensors",
746
- "layers.3.post_attention_layernorm.weight": "model-00005-of-00039.safetensors",
747
- "layers.3.self_attn.k_proj.weight": "model-00004-of-00039.safetensors",
748
- "layers.3.self_attn.o_proj.weight": "model-00004-of-00039.safetensors",
749
- "layers.3.self_attn.q_proj.weight": "model-00004-of-00039.safetensors",
750
- "layers.3.self_attn.v_proj.weight": "model-00004-of-00039.safetensors",
751
- "layers.30.block_sparse_moe.experts.0.w1.weight": "model-00036-of-00039.safetensors",
752
- "layers.30.block_sparse_moe.experts.0.w2.weight": "model-00036-of-00039.safetensors",
753
- "layers.30.block_sparse_moe.experts.0.w3.weight": "model-00036-of-00039.safetensors",
754
- "layers.30.block_sparse_moe.experts.1.w1.weight": "model-00037-of-00039.safetensors",
755
- "layers.30.block_sparse_moe.experts.1.w2.weight": "model-00037-of-00039.safetensors",
756
- "layers.30.block_sparse_moe.experts.1.w3.weight": "model-00037-of-00039.safetensors",
757
- "layers.30.block_sparse_moe.experts.2.w1.weight": "model-00037-of-00039.safetensors",
758
- "layers.30.block_sparse_moe.experts.2.w2.weight": "model-00037-of-00039.safetensors",
759
- "layers.30.block_sparse_moe.experts.2.w3.weight": "model-00037-of-00039.safetensors",
760
- "layers.30.block_sparse_moe.experts.3.w1.weight": "model-00037-of-00039.safetensors",
761
- "layers.30.block_sparse_moe.experts.3.w2.weight": "model-00037-of-00039.safetensors",
762
- "layers.30.block_sparse_moe.experts.3.w3.weight": "model-00037-of-00039.safetensors",
763
- "layers.30.block_sparse_moe.experts.4.w1.weight": "model-00037-of-00039.safetensors",
764
- "layers.30.block_sparse_moe.experts.4.w2.weight": "model-00037-of-00039.safetensors",
765
- "layers.30.block_sparse_moe.experts.4.w3.weight": "model-00037-of-00039.safetensors",
766
- "layers.30.block_sparse_moe.experts.5.w1.weight": "model-00037-of-00039.safetensors",
767
- "layers.30.block_sparse_moe.experts.5.w2.weight": "model-00037-of-00039.safetensors",
768
- "layers.30.block_sparse_moe.experts.5.w3.weight": "model-00037-of-00039.safetensors",
769
- "layers.30.block_sparse_moe.experts.6.w1.weight": "model-00037-of-00039.safetensors",
770
- "layers.30.block_sparse_moe.experts.6.w2.weight": "model-00037-of-00039.safetensors",
771
- "layers.30.block_sparse_moe.experts.6.w3.weight": "model-00037-of-00039.safetensors",
772
- "layers.30.block_sparse_moe.experts.7.w1.weight": "model-00037-of-00039.safetensors",
773
- "layers.30.block_sparse_moe.experts.7.w2.weight": "model-00037-of-00039.safetensors",
774
- "layers.30.block_sparse_moe.experts.7.w3.weight": "model-00037-of-00039.safetensors",
775
- "layers.30.block_sparse_moe.gate.weight": "model-00036-of-00039.safetensors",
776
- "layers.30.input_layernorm.weight": "model-00037-of-00039.safetensors",
777
- "layers.30.post_attention_layernorm.weight": "model-00037-of-00039.safetensors",
778
- "layers.30.self_attn.k_proj.weight": "model-00036-of-00039.safetensors",
779
- "layers.30.self_attn.o_proj.weight": "model-00036-of-00039.safetensors",
780
- "layers.30.self_attn.q_proj.weight": "model-00036-of-00039.safetensors",
781
- "layers.30.self_attn.v_proj.weight": "model-00036-of-00039.safetensors",
782
- "layers.31.block_sparse_moe.experts.0.w1.weight": "model-00038-of-00039.safetensors",
783
- "layers.31.block_sparse_moe.experts.0.w2.weight": "model-00038-of-00039.safetensors",
784
- "layers.31.block_sparse_moe.experts.0.w3.weight": "model-00038-of-00039.safetensors",
785
- "layers.31.block_sparse_moe.experts.1.w1.weight": "model-00038-of-00039.safetensors",
786
- "layers.31.block_sparse_moe.experts.1.w2.weight": "model-00038-of-00039.safetensors",
787
- "layers.31.block_sparse_moe.experts.1.w3.weight": "model-00038-of-00039.safetensors",
788
- "layers.31.block_sparse_moe.experts.2.w1.weight": "model-00038-of-00039.safetensors",
789
- "layers.31.block_sparse_moe.experts.2.w2.weight": "model-00038-of-00039.safetensors",
790
- "layers.31.block_sparse_moe.experts.2.w3.weight": "model-00038-of-00039.safetensors",
791
- "layers.31.block_sparse_moe.experts.3.w1.weight": "model-00038-of-00039.safetensors",
792
- "layers.31.block_sparse_moe.experts.3.w2.weight": "model-00038-of-00039.safetensors",
793
- "layers.31.block_sparse_moe.experts.3.w3.weight": "model-00038-of-00039.safetensors",
794
- "layers.31.block_sparse_moe.experts.4.w1.weight": "model-00038-of-00039.safetensors",
795
- "layers.31.block_sparse_moe.experts.4.w2.weight": "model-00038-of-00039.safetensors",
796
- "layers.31.block_sparse_moe.experts.4.w3.weight": "model-00038-of-00039.safetensors",
797
- "layers.31.block_sparse_moe.experts.5.w1.weight": "model-00038-of-00039.safetensors",
798
- "layers.31.block_sparse_moe.experts.5.w2.weight": "model-00038-of-00039.safetensors",
799
- "layers.31.block_sparse_moe.experts.5.w3.weight": "model-00038-of-00039.safetensors",
800
- "layers.31.block_sparse_moe.experts.6.w1.weight": "model-00038-of-00039.safetensors",
801
- "layers.31.block_sparse_moe.experts.6.w2.weight": "model-00038-of-00039.safetensors",
802
- "layers.31.block_sparse_moe.experts.6.w3.weight": "model-00039-of-00039.safetensors",
803
- "layers.31.block_sparse_moe.experts.7.w1.weight": "model-00039-of-00039.safetensors",
804
- "layers.31.block_sparse_moe.experts.7.w2.weight": "model-00039-of-00039.safetensors",
805
- "layers.31.block_sparse_moe.experts.7.w3.weight": "model-00039-of-00039.safetensors",
806
- "layers.31.block_sparse_moe.gate.weight": "model-00038-of-00039.safetensors",
807
- "layers.31.input_layernorm.weight": "model-00039-of-00039.safetensors",
808
- "layers.31.post_attention_layernorm.weight": "model-00039-of-00039.safetensors",
809
- "layers.31.self_attn.k_proj.weight": "model-00038-of-00039.safetensors",
810
- "layers.31.self_attn.o_proj.weight": "model-00038-of-00039.safetensors",
811
- "layers.31.self_attn.q_proj.weight": "model-00037-of-00039.safetensors",
812
- "layers.31.self_attn.v_proj.weight": "model-00038-of-00039.safetensors",
813
- "layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00039.safetensors",
814
- "layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00039.safetensors",
815
- "layers.4.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00039.safetensors",
816
- "layers.4.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00039.safetensors",
817
- "layers.4.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00039.safetensors",
818
- "layers.4.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00039.safetensors",
819
- "layers.4.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00039.safetensors",
820
- "layers.4.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00039.safetensors",
821
- "layers.4.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00039.safetensors",
822
- "layers.4.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00039.safetensors",
823
- "layers.4.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00039.safetensors",
824
- "layers.4.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00039.safetensors",
825
- "layers.4.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00039.safetensors",
826
- "layers.4.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00039.safetensors",
827
- "layers.4.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00039.safetensors",
828
- "layers.4.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00039.safetensors",
829
- "layers.4.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00039.safetensors",
830
- "layers.4.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00039.safetensors",
831
- "layers.4.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00039.safetensors",
832
- "layers.4.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00039.safetensors",
833
- "layers.4.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00039.safetensors",
834
- "layers.4.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00039.safetensors",
835
- "layers.4.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00039.safetensors",
836
- "layers.4.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00039.safetensors",
837
- "layers.4.block_sparse_moe.gate.weight": "model-00005-of-00039.safetensors",
838
- "layers.4.input_layernorm.weight": "model-00007-of-00039.safetensors",
839
- "layers.4.post_attention_layernorm.weight": "model-00007-of-00039.safetensors",
840
- "layers.4.self_attn.k_proj.weight": "model-00005-of-00039.safetensors",
841
- "layers.4.self_attn.o_proj.weight": "model-00005-of-00039.safetensors",
842
- "layers.4.self_attn.q_proj.weight": "model-00005-of-00039.safetensors",
843
- "layers.4.self_attn.v_proj.weight": "model-00005-of-00039.safetensors",
844
- "layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00039.safetensors",
845
- "layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00039.safetensors",
846
- "layers.5.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00039.safetensors",
847
- "layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00039.safetensors",
848
- "layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00039.safetensors",
849
- "layers.5.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00039.safetensors",
850
- "layers.5.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00039.safetensors",
851
- "layers.5.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00039.safetensors",
852
- "layers.5.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00039.safetensors",
853
- "layers.5.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00039.safetensors",
854
- "layers.5.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00039.safetensors",
855
- "layers.5.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00039.safetensors",
856
- "layers.5.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00039.safetensors",
857
- "layers.5.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00039.safetensors",
858
- "layers.5.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00039.safetensors",
859
- "layers.5.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00039.safetensors",
860
- "layers.5.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00039.safetensors",
861
- "layers.5.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00039.safetensors",
862
- "layers.5.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00039.safetensors",
863
- "layers.5.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00039.safetensors",
864
- "layers.5.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00039.safetensors",
865
- "layers.5.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00039.safetensors",
866
- "layers.5.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00039.safetensors",
867
- "layers.5.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00039.safetensors",
868
- "layers.5.block_sparse_moe.gate.weight": "model-00007-of-00039.safetensors",
869
- "layers.5.input_layernorm.weight": "model-00008-of-00039.safetensors",
870
- "layers.5.post_attention_layernorm.weight": "model-00008-of-00039.safetensors",
871
- "layers.5.self_attn.k_proj.weight": "model-00007-of-00039.safetensors",
872
- "layers.5.self_attn.o_proj.weight": "model-00007-of-00039.safetensors",
873
- "layers.5.self_attn.q_proj.weight": "model-00007-of-00039.safetensors",
874
- "layers.5.self_attn.v_proj.weight": "model-00007-of-00039.safetensors",
875
- "layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00039.safetensors",
876
- "layers.6.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00039.safetensors",
877
- "layers.6.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00039.safetensors",
878
- "layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00039.safetensors",
879
- "layers.6.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00039.safetensors",
880
- "layers.6.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00039.safetensors",
881
- "layers.6.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00039.safetensors",
882
- "layers.6.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00039.safetensors",
883
- "layers.6.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00039.safetensors",
884
- "layers.6.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00039.safetensors",
885
- "layers.6.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00039.safetensors",
886
- "layers.6.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00039.safetensors",
887
- "layers.6.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00039.safetensors",
888
- "layers.6.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00039.safetensors",
889
- "layers.6.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00039.safetensors",
890
- "layers.6.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00039.safetensors",
891
- "layers.6.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00039.safetensors",
892
- "layers.6.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00039.safetensors",
893
- "layers.6.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00039.safetensors",
894
- "layers.6.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00039.safetensors",
895
- "layers.6.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00039.safetensors",
896
- "layers.6.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00039.safetensors",
897
- "layers.6.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00039.safetensors",
898
- "layers.6.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00039.safetensors",
899
- "layers.6.block_sparse_moe.gate.weight": "model-00008-of-00039.safetensors",
900
- "layers.6.input_layernorm.weight": "model-00009-of-00039.safetensors",
901
- "layers.6.post_attention_layernorm.weight": "model-00009-of-00039.safetensors",
902
- "layers.6.self_attn.k_proj.weight": "model-00008-of-00039.safetensors",
903
- "layers.6.self_attn.o_proj.weight": "model-00008-of-00039.safetensors",
904
- "layers.6.self_attn.q_proj.weight": "model-00008-of-00039.safetensors",
905
- "layers.6.self_attn.v_proj.weight": "model-00008-of-00039.safetensors",
906
- "layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00039.safetensors",
907
- "layers.7.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00039.safetensors",
908
- "layers.7.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00039.safetensors",
909
- "layers.7.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00039.safetensors",
910
- "layers.7.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00039.safetensors",
911
- "layers.7.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00039.safetensors",
912
- "layers.7.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00039.safetensors",
913
- "layers.7.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00039.safetensors",
914
- "layers.7.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00039.safetensors",
915
- "layers.7.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00039.safetensors",
916
- "layers.7.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00039.safetensors",
917
- "layers.7.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00039.safetensors",
918
- "layers.7.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00039.safetensors",
919
- "layers.7.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00039.safetensors",
920
- "layers.7.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00039.safetensors",
921
- "layers.7.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00039.safetensors",
922
- "layers.7.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00039.safetensors",
923
- "layers.7.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00039.safetensors",
924
- "layers.7.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00039.safetensors",
925
- "layers.7.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00039.safetensors",
926
- "layers.7.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00039.safetensors",
927
- "layers.7.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00039.safetensors",
928
- "layers.7.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00039.safetensors",
929
- "layers.7.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00039.safetensors",
930
- "layers.7.block_sparse_moe.gate.weight": "model-00009-of-00039.safetensors",
931
- "layers.7.input_layernorm.weight": "model-00010-of-00039.safetensors",
932
- "layers.7.post_attention_layernorm.weight": "model-00010-of-00039.safetensors",
933
- "layers.7.self_attn.k_proj.weight": "model-00009-of-00039.safetensors",
934
- "layers.7.self_attn.o_proj.weight": "model-00009-of-00039.safetensors",
935
- "layers.7.self_attn.q_proj.weight": "model-00009-of-00039.safetensors",
936
- "layers.7.self_attn.v_proj.weight": "model-00009-of-00039.safetensors",
937
- "layers.8.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00039.safetensors",
938
- "layers.8.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00039.safetensors",
939
- "layers.8.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00039.safetensors",
940
- "layers.8.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00039.safetensors",
941
- "layers.8.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00039.safetensors",
942
- "layers.8.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00039.safetensors",
943
- "layers.8.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00039.safetensors",
944
- "layers.8.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00039.safetensors",
945
- "layers.8.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00039.safetensors",
946
- "layers.8.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00039.safetensors",
947
- "layers.8.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00039.safetensors",
948
- "layers.8.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00039.safetensors",
949
- "layers.8.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00039.safetensors",
950
- "layers.8.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00039.safetensors",
951
- "layers.8.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00039.safetensors",
952
- "layers.8.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00039.safetensors",
953
- "layers.8.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00039.safetensors",
954
- "layers.8.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00039.safetensors",
955
- "layers.8.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00039.safetensors",
956
- "layers.8.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00039.safetensors",
957
- "layers.8.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00039.safetensors",
958
- "layers.8.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00039.safetensors",
959
- "layers.8.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00039.safetensors",
960
- "layers.8.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00039.safetensors",
961
- "layers.8.block_sparse_moe.gate.weight": "model-00010-of-00039.safetensors",
962
- "layers.8.input_layernorm.weight": "model-00011-of-00039.safetensors",
963
- "layers.8.post_attention_layernorm.weight": "model-00011-of-00039.safetensors",
964
- "layers.8.self_attn.k_proj.weight": "model-00010-of-00039.safetensors",
965
- "layers.8.self_attn.o_proj.weight": "model-00010-of-00039.safetensors",
966
- "layers.8.self_attn.q_proj.weight": "model-00010-of-00039.safetensors",
967
- "layers.8.self_attn.v_proj.weight": "model-00010-of-00039.safetensors",
968
- "layers.9.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00039.safetensors",
969
- "layers.9.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00039.safetensors",
970
- "layers.9.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00039.safetensors",
971
- "layers.9.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00039.safetensors",
972
- "layers.9.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00039.safetensors",
973
- "layers.9.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00039.safetensors",
974
- "layers.9.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00039.safetensors",
975
- "layers.9.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00039.safetensors",
976
- "layers.9.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00039.safetensors",
977
- "layers.9.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00039.safetensors",
978
- "layers.9.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00039.safetensors",
979
- "layers.9.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00039.safetensors",
980
- "layers.9.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00039.safetensors",
981
- "layers.9.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00039.safetensors",
982
- "layers.9.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00039.safetensors",
983
- "layers.9.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00039.safetensors",
984
- "layers.9.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00039.safetensors",
985
- "layers.9.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00039.safetensors",
986
- "layers.9.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00039.safetensors",
987
- "layers.9.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00039.safetensors",
988
- "layers.9.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00039.safetensors",
989
- "layers.9.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00039.safetensors",
990
- "layers.9.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00039.safetensors",
991
- "layers.9.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00039.safetensors",
992
- "layers.9.block_sparse_moe.gate.weight": "model-00011-of-00039.safetensors",
993
- "layers.9.input_layernorm.weight": "model-00012-of-00039.safetensors",
994
- "layers.9.post_attention_layernorm.weight": "model-00012-of-00039.safetensors",
995
- "layers.9.self_attn.k_proj.weight": "model-00011-of-00039.safetensors",
996
- "layers.9.self_attn.o_proj.weight": "model-00011-of-00039.safetensors",
997
- "layers.9.self_attn.q_proj.weight": "model-00011-of-00039.safetensors",
998
- "layers.9.self_attn.v_proj.weight": "model-00011-of-00039.safetensors",
999
- "norm.weight": "model-00039-of-00039.safetensors"
1000
- }
1001
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<unk>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
 
 
 
tokenizer_config.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- }
29
- },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
- "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
- "clean_up_tokenization_spaces": false,
34
- "eos_token": "</s>",
35
- "legacy": true,
36
- "model_max_length": 1000000000000000019884624838656,
37
- "pad_token": "</s>",
38
- "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
- "tokenizer_class": "LlamaTokenizer",
41
- "trust_remote_code": true,
42
- "unk_token": "<unk>",
43
- "use_default_system_prompt": false,
44
- "use_fast": true
45
- }