Commit ·
264c832
0
Parent(s):
Duplicate from mkd-ai-dev/Keural-MoE-14B
Browse filesCo-authored-by: Md Najmul Hossain <mkd-hossain@users.noreply.huggingface.co>
- .gitattributes +39 -0
- LICENSE +201 -0
- README.md +207 -0
- benchmark_comparison_bar.png +3 -0
- benchmark_comparison_radar.png +3 -0
- benchmark_summary_table.png +3 -0
- config.json +32 -0
- configuration_keural.py +13 -0
- generation_config.json +12 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +754 -0
- modeling_keural.py +43 -0
- special_tokens_map.json +34 -0
- tokenizer.model +3 -0
- tokenizer_config.json +18 -0
.gitattributes
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
benchmark_comparison_bar.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
benchmark_comparison_radar.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
benchmark_summary_table.png filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
|
LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Apache License
|
| 2 |
+
Version 2.0, January 2004
|
| 3 |
+
http://www.apache.org/licenses/
|
| 4 |
+
|
| 5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 6 |
+
|
| 7 |
+
1. Definitions.
|
| 8 |
+
|
| 9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 11 |
+
|
| 12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 13 |
+
the copyright owner that is granting the License.
|
| 14 |
+
|
| 15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 16 |
+
other entities that control, are controlled by, or are under common
|
| 17 |
+
control with that entity. For the purposes of this definition,
|
| 18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 19 |
+
direction or management of such entity, whether by contract or
|
| 20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 22 |
+
|
| 23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 24 |
+
exercising permissions granted by this License.
|
| 25 |
+
|
| 26 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 27 |
+
including but not limited to software source code, documentation
|
| 28 |
+
source, and configuration files.
|
| 29 |
+
|
| 30 |
+
"Object" form shall mean any form resulting from mechanical
|
| 31 |
+
transformation or translation of a Source form, including but
|
| 32 |
+
not limited to compiled object code, generated documentation,
|
| 33 |
+
and conversions to other media types.
|
| 34 |
+
|
| 35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 36 |
+
Object form, made available under the License, as indicated by a
|
| 37 |
+
copyright notice that is included in or attached to the work
|
| 38 |
+
(an example is provided in the Appendix below).
|
| 39 |
+
|
| 40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 41 |
+
form, that is based on (or derived from) the Work and for which the
|
| 42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 44 |
+
of this License, Derivative Works shall not include works that remain
|
| 45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 46 |
+
the Work and Derivative Works thereof.
|
| 47 |
+
|
| 48 |
+
"Contribution" shall mean any work of authorship, including
|
| 49 |
+
the original version of the Work and any modifications or additions
|
| 50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 54 |
+
means any form of electronic, verbal, or written communication sent
|
| 55 |
+
to the Licensor or its representatives, including but not limited to
|
| 56 |
+
communication on electronic mailing lists, source code control systems,
|
| 57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 59 |
+
excluding communication that is conspicuously marked or otherwise
|
| 60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 61 |
+
|
| 62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 64 |
+
subsequently incorporated within the Work.
|
| 65 |
+
|
| 66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 71 |
+
Work and such Derivative Works in Source or Object form.
|
| 72 |
+
|
| 73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 76 |
+
(except as stated in this section) patent license to make, have made,
|
| 77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 78 |
+
where such license applies only to those patent claims licensable
|
| 79 |
+
by such Contributor that are necessarily infringed by their
|
| 80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 82 |
+
institute patent litigation against any entity (including a
|
| 83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 84 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 85 |
+
or contributory patent infringement, then any patent licenses
|
| 86 |
+
granted to You under this License for that Work shall terminate
|
| 87 |
+
as of the date such litigation is filed.
|
| 88 |
+
|
| 89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 90 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 91 |
+
modifications, and in Source or Object form, provided that You
|
| 92 |
+
meet the following conditions:
|
| 93 |
+
|
| 94 |
+
(a) You must give any other recipients of the Work or
|
| 95 |
+
Derivative Works a copy of this License; and
|
| 96 |
+
|
| 97 |
+
(b) You must cause any modified files to carry prominent notices
|
| 98 |
+
stating that You changed the files; and
|
| 99 |
+
|
| 100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 101 |
+
that You distribute, all copyright, patent, trademark, and
|
| 102 |
+
attribution notices from the Source form of the Work,
|
| 103 |
+
excluding those notices that do not pertain to any part of
|
| 104 |
+
the Derivative Works; and
|
| 105 |
+
|
| 106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 107 |
+
distribution, then any Derivative Works that You distribute must
|
| 108 |
+
include a readable copy of the attribution notices contained
|
| 109 |
+
within such NOTICE file, excluding those notices that do not
|
| 110 |
+
pertain to any part of the Derivative Works, in at least one
|
| 111 |
+
of the following places: within a NOTICE text file distributed
|
| 112 |
+
as part of the Derivative Works; within the Source form or
|
| 113 |
+
documentation, if provided along with the Derivative Works; or,
|
| 114 |
+
within a display generated by the Derivative Works, if and
|
| 115 |
+
wherever such third-party notices normally appear. The contents
|
| 116 |
+
of the NOTICE file are for informational purposes only and
|
| 117 |
+
do not modify the License. You may add Your own attribution
|
| 118 |
+
notices within Derivative Works that You distribute, alongside
|
| 119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 120 |
+
that such additional attribution notices cannot be construed
|
| 121 |
+
as modifying the License.
|
| 122 |
+
|
| 123 |
+
You may add Your own copyright statement to Your modifications and
|
| 124 |
+
may provide additional or different license terms and conditions
|
| 125 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 126 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 127 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 128 |
+
the conditions stated in this License.
|
| 129 |
+
|
| 130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 132 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 133 |
+
this License, without any additional terms or conditions.
|
| 134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 135 |
+
the terms of any separate license agreement you may have executed
|
| 136 |
+
with Licensor regarding such Contributions.
|
| 137 |
+
|
| 138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 140 |
+
except as required for reasonable and customary use in describing the
|
| 141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 142 |
+
|
| 143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 144 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 147 |
+
implied, including, without limitation, any warranties or conditions
|
| 148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 150 |
+
appropriateness of using or redistributing the Work and assume any
|
| 151 |
+
risks associated with Your exercise of permissions under this License.
|
| 152 |
+
|
| 153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 154 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 155 |
+
unless required by applicable law (such as deliberate and grossly
|
| 156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 157 |
+
liable to You for damages, including any direct, indirect, special,
|
| 158 |
+
incidental, or consequential damages of any character arising as a
|
| 159 |
+
result of this License or out of the use or inability to use the
|
| 160 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 161 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 162 |
+
other commercial damages or losses), even if such Contributor
|
| 163 |
+
has been advised of the possibility of such damages.
|
| 164 |
+
|
| 165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 168 |
+
or other liability obligations and/or rights consistent with this
|
| 169 |
+
License. However, in accepting such obligations, You may act only
|
| 170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 171 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 172 |
+
defend, and hold each Contributor harmless for any liability
|
| 173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 174 |
+
of your accepting any such warranty or additional liability.
|
| 175 |
+
|
| 176 |
+
END OF TERMS AND CONDITIONS
|
| 177 |
+
|
| 178 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 179 |
+
|
| 180 |
+
To apply the Apache License to your work, attach the following
|
| 181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 182 |
+
replaced with your own identifying information. (Don't include
|
| 183 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 184 |
+
comment syntax for the file format. We also recommend that a
|
| 185 |
+
file or class name and description of purpose be included on the
|
| 186 |
+
same "printed page" as the copyright notice for easier
|
| 187 |
+
identification within third-party archives.
|
| 188 |
+
|
| 189 |
+
Copyright 2026 MKD CO., LTD.
|
| 190 |
+
|
| 191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 192 |
+
you may not use this file except in compliance with the License.
|
| 193 |
+
You may obtain a copy of the License at
|
| 194 |
+
|
| 195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 196 |
+
|
| 197 |
+
Unless required by applicable law or agreed to in writing, software
|
| 198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 200 |
+
See the License for the specific language governing permissions and
|
| 201 |
+
limitations under the License.
|
README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ko
|
| 4 |
+
- en
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
library_name: transformers
|
| 7 |
+
tags:
|
| 8 |
+
- keural
|
| 9 |
+
- moe
|
| 10 |
+
- korean
|
| 11 |
+
- bilingual
|
| 12 |
+
- causal-lm
|
| 13 |
+
- dpo
|
| 14 |
+
- instruction-tuned
|
| 15 |
+
- chat
|
| 16 |
+
- preference-optimized
|
| 17 |
+
base_model: mkd-hossain/keural-sft3-final
|
| 18 |
+
pipeline_tag: text-generation
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
# Keural-MoE-14B
|
| 22 |
+
|
| 23 |
+
Keural is a bilingual Korean–English Mixture-of-Experts language model trained **entirely from scratch** by MKD Corp AI Research, Republic of Korea.
|
| 24 |
+
This is the **final DPO Round 2 checkpoint** at step 7,590 (100% complete), trained on 485,793 preference pairs on top of SFT Epoch 3.
|
| 25 |
+
|
| 26 |
+
## Model Details
|
| 27 |
+
|
| 28 |
+
| Property | Value |
|
| 29 |
+
|---|---|
|
| 30 |
+
| Architecture | **KeuralMoECausalLM** |
|
| 31 |
+
| Parameters | **14.83B total** / ~7.42B active per token |
|
| 32 |
+
| Layers | 24 |
|
| 33 |
+
| Hidden size | 4,096 |
|
| 34 |
+
| Attention heads | 32 Q / 8 KV (GQA) |
|
| 35 |
+
| Head dimension | 128 |
|
| 36 |
+
| Experts | 8 total, top-2 per token |
|
| 37 |
+
| Expert intermediate size | 5,632 (SwiGLU) |
|
| 38 |
+
| Context length | 4,096 tokens |
|
| 39 |
+
| Vocabulary | **131,074** (131,072 SPM + `<\|im_start\|>` ID 131072 + `<\|im_end\|>` ID 131073) |
|
| 40 |
+
| RoPE theta | 500,000 |
|
| 41 |
+
| Sliding window | 512 tokens (even layers only) |
|
| 42 |
+
| Normalization | RMSNorm (eps=1e-5) |
|
| 43 |
+
| Dtype | bfloat16 |
|
| 44 |
+
| Languages | Korean (primary), English |
|
| 45 |
+
| Training time (DPO Round 2) | 85.28 hours |
|
| 46 |
+
|
| 47 |
+
## Full Training Pipeline
|
| 48 |
+
|
| 49 |
+
| Stage | Steps | Tokens | Data | Hardware |
|
| 50 |
+
|---|---|---|---|---|
|
| 51 |
+
| Pretraining Stage 1 | 100,000 | ~50B | Korean + English web corpus | 2× H200 SXM |
|
| 52 |
+
| Pretraining Stage 2 | 120,000 | ~19B | Korean + English web corpus | 2× H200 SXM |
|
| 53 |
+
| SFT Epoch 1 | 18,000 | ~710M | 710K instruction samples (9 sources) | 2× H200 SXM |
|
| 54 |
+
| DPO Round 1 | 6,927 | — | 440K preference pairs (6 sources) | 2× H200 SXM |
|
| 55 |
+
| SFT Epoch 2 | 29,112 | ~7.6B | 710K filtered samples | 2× H200 SXM |
|
| 56 |
+
| SFT Epoch 3 | 65,849 | ~17.3B | 2.35M samples (12 sources) | 2× H200 SXM |
|
| 57 |
+
| **DPO Round 2** | **7,590** | — | **485K preference pairs (8 sources)** | **2× H200 SXM** |
|
| 58 |
+
|
| 59 |
+
## DPO Round 2 Dataset (485,793 pairs)
|
| 60 |
+
|
| 61 |
+
| Source | Pairs | Language |
|
| 62 |
+
|---|---|---|
|
| 63 |
+
| hh_rlhf | 150,510 | English |
|
| 64 |
+
| aihub_71760 | 109,289 | Korean |
|
| 65 |
+
| multifaceted_collection_dpo | 63,346 | English |
|
| 66 |
+
| ultrafeedback_binarized | 55,843 | English |
|
| 67 |
+
| ko_ultrafeedback_binarized | 54,169 | Korean |
|
| 68 |
+
| aihub_71748 | 29,356 | Korean |
|
| 69 |
+
| orca_dpo_pairs | 11,924 | English |
|
| 70 |
+
| orca_dpo_pairs_ko | 11,356 | Korean |
|
| 71 |
+
| **Total** | **485,793** | **58% EN / 42% KO** |
|
| 72 |
+
|
| 73 |
+
## DPO Training Details
|
| 74 |
+
|
| 75 |
+
| Hyperparameter | Value |
|
| 76 |
+
|---|---|
|
| 77 |
+
| Algorithm | Direct Preference Optimization (DPO) |
|
| 78 |
+
| Beta (KL penalty) | 0.1 |
|
| 79 |
+
| Learning rate | 2e-6 → 2e-7 cosine decay |
|
| 80 |
+
| Warmup steps | 100 |
|
| 81 |
+
| Effective batch size | 64 (2 × 16 accum × 2 GPUs) |
|
| 82 |
+
| Max sequence length | 1,024 tokens |
|
| 83 |
+
| Total steps | 7,590 (1 epoch) |
|
| 84 |
+
| Final loss | ~0.6928 (below random baseline 0.6931) |
|
| 85 |
+
| Final reward margin | consistently positive |
|
| 86 |
+
| Training time | 85.28 hours |
|
| 87 |
+
|
| 88 |
+
## Special Tokens
|
| 89 |
+
|
| 90 |
+
| Token | ID | Purpose |
|
| 91 |
+
|---|---|---|
|
| 92 |
+
| `<\|im_start\|>` | **131072** | Start of each conversation turn |
|
| 93 |
+
| `<\|im_end\|>` | **131073** | End of turn — **generation stop token** |
|
| 94 |
+
| `<bos>` | 1 | Beginning of sequence |
|
| 95 |
+
| `<eos>` | 2 | Not used for chat |
|
| 96 |
+
| `<pad>` | 0 | Padding |
|
| 97 |
+
|
| 98 |
+
> **Critical:** Always use `eos_token_id=131073`. The model outputs `<|im_end|>` (ID 131073) to stop — not `<eos>` (ID 2).
|
| 99 |
+
|
| 100 |
+
## Chat Format (ChatML)
|
| 101 |
+
|
| 102 |
+
```
|
| 103 |
+
<|im_start|>system
|
| 104 |
+
You are a helpful, accurate, and safe bilingual Korean-English AI assistant. Give concise, factual, and correct answers. If you are not sure about something, say you don't know instead of guessing. Never provide harmful, dangerous, illegal, or false information.<|im_end|>
|
| 105 |
+
<|im_start|>user
|
| 106 |
+
Your question here<|im_end|>
|
| 107 |
+
<|im_start|>assistant
|
| 108 |
+
```
|
| 109 |
+
|
| 110 |
+
## Usage (Transformers)
|
| 111 |
+
|
| 112 |
+
```python
|
| 113 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 114 |
+
import torch
|
| 115 |
+
|
| 116 |
+
model_id = "mkd-ai/Keural-MoE-14B"
|
| 117 |
+
|
| 118 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
| 119 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 120 |
+
model_id,
|
| 121 |
+
torch_dtype=torch.bfloat16,
|
| 122 |
+
device_map="auto",
|
| 123 |
+
trust_remote_code=True,
|
| 124 |
+
)
|
| 125 |
+
|
| 126 |
+
messages = [
|
| 127 |
+
{"role": "system", "content": "You are a helpful bilingual Korean-English AI assistant."},
|
| 128 |
+
{"role": "user", "content": "안녕하세요! 서울에 대해 알려주세요."}
|
| 129 |
+
]
|
| 130 |
+
|
| 131 |
+
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 132 |
+
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
| 133 |
+
|
| 134 |
+
outputs = model.generate(
|
| 135 |
+
**inputs,
|
| 136 |
+
max_new_tokens=512,
|
| 137 |
+
temperature=0.7,
|
| 138 |
+
top_p=0.9,
|
| 139 |
+
top_k=50,
|
| 140 |
+
repetition_penalty=1.1,
|
| 141 |
+
do_sample=True,
|
| 142 |
+
eos_token_id=131073,
|
| 143 |
+
)
|
| 144 |
+
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
| 145 |
+
```
|
| 146 |
+
|
| 147 |
+
## Usage (vLLM)
|
| 148 |
+
|
| 149 |
+
```bash
|
| 150 |
+
python -m vllm.entrypoints.openai.api_server \
|
| 151 |
+
--model mkd-ai/Keural-MoE-14B \
|
| 152 |
+
--dtype auto \
|
| 153 |
+
--max-model-len 4096 \
|
| 154 |
+
--gpu-memory-utilization 0.7 \
|
| 155 |
+
--trust-remote-code
|
| 156 |
+
```
|
| 157 |
+
|
| 158 |
+
## Evaluation (Open LLM Leaderboard Benchmarks)
|
| 159 |
+
|
| 160 |
+
Keural-MoE-14B was evaluated on 6 standard benchmarks used by the Open LLM Leaderboard.
|
| 161 |
+
|
| 162 |
+
### Results
|
| 163 |
+
|
| 164 |
+
| Benchmark | Keural-MoE-14B | Mixtral-8x7B | LLaMA-2-13B | Qwen-1.5-14B |
|
| 165 |
+
|---|---|---|---|---|
|
| 166 |
+
| MMLU (5-shot) | 23.6 | 70.6 | 55.8 | 67.6 |
|
| 167 |
+
| HellaSwag (10-shot) | 34.9 | 86.5 | 82.1 | 81.0 |
|
| 168 |
+
| ARC-Challenge (25-shot) | 23.9 | 66.4 | 59.4 | 56.0 |
|
| 169 |
+
| TruthfulQA (0-shot) | 41.8 | 46.8 | 36.9 | 52.2 |
|
| 170 |
+
| Winogrande (5-shot) | 52.4 | 81.4 | 76.2 | 73.8 |
|
| 171 |
+
| GSM8K (5-shot) | 0.2 | 58.4 | 28.7 | 62.5 |
|
| 172 |
+
| **Average** | **29.5** | **68.4** | **56.5** | **65.5** |
|
| 173 |
+
|
| 174 |
+
### Benchmark Charts
|
| 175 |
+
|
| 176 |
+
|
| 177 |
+
|
| 178 |
+
|
| 179 |
+
|
| 180 |
+
|
| 181 |
+
|
| 182 |
+
### Analysis
|
| 183 |
+
|
| 184 |
+
Keural-MoE-14B was trained from scratch on ~69B tokens. Reference models (Mixtral, LLaMA-2, Qwen) were pretrained on **trillions** of tokens. Given the 50x+ difference in pretraining data, the scores reflect the expected scaling behavior:
|
| 185 |
+
|
| 186 |
+
- **Winogrande (52.4%)** — above random baseline (50%), indicating learned language understanding
|
| 187 |
+
- **TruthfulQA (41.8%)** — competitive with LLaMA-2-13B (36.9%), showing DPO alignment effectiveness
|
| 188 |
+
- **GSM8K (0.2%)** — math/code data was intentionally removed from SFT training to reduce structured task bias
|
| 189 |
+
|
| 190 |
+
These benchmarks establish a baseline. Future versions trained on larger corpora will show significant improvements.
|
| 191 |
+
|
| 192 |
+
## Hardware
|
| 193 |
+
|
| 194 |
+
Trained on **2× NVIDIA H200 SXM** (139 GiB each) using FSDP FULL_SHARD, bfloat16 mixed precision, and gradient checkpointing.
|
| 195 |
+
|
| 196 |
+
## Training Source Code
|
| 197 |
+
|
| 198 |
+
https://github.com/MKD-CORP/Keural-Model-Training
|
| 199 |
+
|
| 200 |
+
## Organization
|
| 201 |
+
|
| 202 |
+
Developed by **MKD Corp AI Research**, Republic of Korea.
|
| 203 |
+
|
| 204 |
+
|
| 205 |
+
## License
|
| 206 |
+
[](https://github.com/MKD-CORP/Keural-MoE-14B-Training/blob/main/LICENSE)
|
| 207 |
+
|
benchmark_comparison_bar.png
ADDED
|
Git LFS Details
|
benchmark_comparison_radar.png
ADDED
|
Git LFS Details
|
benchmark_summary_table.png
ADDED
|
Git LFS Details
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"KeuralMoECausalLM"
|
| 4 |
+
],
|
| 5 |
+
"model_type": "keural",
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_keural.KeuralConfig",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_keural.KeuralMoECausalLM"
|
| 9 |
+
},
|
| 10 |
+
"vocab_size": 131074,
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"intermediate_size": 5632,
|
| 13 |
+
"num_hidden_layers": 24,
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_key_value_heads": 8,
|
| 16 |
+
"head_dim": 128,
|
| 17 |
+
"num_local_experts": 8,
|
| 18 |
+
"num_experts_per_tok": 2,
|
| 19 |
+
"max_position_embeddings": 4096,
|
| 20 |
+
"rope_theta": 500000.0,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"sliding_window": 512,
|
| 23 |
+
"hidden_act": "silu",
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.40.0",
|
| 29 |
+
"output_router_logits": false,
|
| 30 |
+
"router_aux_loss_coef": 0.001,
|
| 31 |
+
"keural_step": 7590
|
| 32 |
+
}
|
configuration_keural.py
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
KeuralConfig — custom configuration class for Keural MoE.
|
| 3 |
+
Registered as model_type "keural" so HuggingFace AutoConfig can resolve it.
|
| 4 |
+
"""
|
| 5 |
+
|
| 6 |
+
from transformers import MixtralConfig
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
class KeuralConfig(MixtralConfig):
|
| 10 |
+
model_type = "keural"
|
| 11 |
+
|
| 12 |
+
def __init__(self, **kwargs):
|
| 13 |
+
super().__init__(**kwargs)
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 131073,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"max_new_tokens": 512,
|
| 6 |
+
"temperature": 0.7,
|
| 7 |
+
"top_p": 0.9,
|
| 8 |
+
"top_k": 50,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"do_sample": true,
|
| 11 |
+
"transformers_version": "4.40.0"
|
| 12 |
+
}
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdd7fe53f0a0e1ab422739f002c3e275cbdf2787f4f9c652c90c7b090a580e01
|
| 3 |
+
size 4823806664
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6f62bc97f3c630b3767bdeb08f2036909e931655ebc358475438dd4fe8d806e
|
| 3 |
+
size 4811210208
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90ab52358910e000b320e93ecbf3723283ee21ea0b32f1365dcf4fe25f5fae61
|
| 3 |
+
size 4811210248
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efe6e4513cbffcaee7ef8262e5a1078e66b4b091732736e9f09b9aaae21e1b34
|
| 3 |
+
size 4811210336
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67bde378edf43f3769bd1a8365a7f1c7856947d81694fb12d111f28031482c30
|
| 3 |
+
size 4811210336
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:442f71c92279c525a3299f1201c460666ce4a29d65ce51fa86faeb30437f05a3
|
| 3 |
+
size 4811210336
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf777e9c71ac18d9c5c067fd9bf5421a5fbe4ed2b78aabad266caffddf40fa04
|
| 3 |
+
size 1858103664
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,754 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 30737866752
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 8 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 9 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 10 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 11 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 13 |
+
"model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
|
| 14 |
+
"model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
|
| 15 |
+
"model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
|
| 16 |
+
"model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
|
| 17 |
+
"model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
|
| 18 |
+
"model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
|
| 19 |
+
"model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
|
| 20 |
+
"model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00007.safetensors",
|
| 21 |
+
"model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors",
|
| 22 |
+
"model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors",
|
| 23 |
+
"model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors",
|
| 24 |
+
"model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors",
|
| 25 |
+
"model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00007.safetensors",
|
| 26 |
+
"model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors",
|
| 27 |
+
"model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors",
|
| 28 |
+
"model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors",
|
| 29 |
+
"model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors",
|
| 30 |
+
"model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors",
|
| 31 |
+
"model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors",
|
| 32 |
+
"model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors",
|
| 33 |
+
"model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors",
|
| 34 |
+
"model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors",
|
| 35 |
+
"model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors",
|
| 36 |
+
"model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00007.safetensors",
|
| 37 |
+
"model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors",
|
| 38 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 39 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 40 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 41 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 42 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 43 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 44 |
+
"model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
|
| 45 |
+
"model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
|
| 46 |
+
"model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
|
| 47 |
+
"model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
|
| 48 |
+
"model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
|
| 49 |
+
"model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
|
| 50 |
+
"model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
|
| 51 |
+
"model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00007.safetensors",
|
| 52 |
+
"model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors",
|
| 53 |
+
"model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors",
|
| 54 |
+
"model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors",
|
| 55 |
+
"model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors",
|
| 56 |
+
"model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00007.safetensors",
|
| 57 |
+
"model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors",
|
| 58 |
+
"model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors",
|
| 59 |
+
"model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors",
|
| 60 |
+
"model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors",
|
| 61 |
+
"model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors",
|
| 62 |
+
"model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors",
|
| 63 |
+
"model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors",
|
| 64 |
+
"model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors",
|
| 65 |
+
"model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors",
|
| 66 |
+
"model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors",
|
| 67 |
+
"model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00007.safetensors",
|
| 68 |
+
"model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors",
|
| 69 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 70 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 71 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 72 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 73 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 74 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 75 |
+
"model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
|
| 76 |
+
"model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
|
| 77 |
+
"model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
|
| 78 |
+
"model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00007.safetensors",
|
| 79 |
+
"model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00007.safetensors",
|
| 80 |
+
"model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00007.safetensors",
|
| 81 |
+
"model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00007.safetensors",
|
| 82 |
+
"model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00007.safetensors",
|
| 83 |
+
"model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00007.safetensors",
|
| 84 |
+
"model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00007.safetensors",
|
| 85 |
+
"model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00007.safetensors",
|
| 86 |
+
"model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00007.safetensors",
|
| 87 |
+
"model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00007.safetensors",
|
| 88 |
+
"model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00007.safetensors",
|
| 89 |
+
"model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00007.safetensors",
|
| 90 |
+
"model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00007.safetensors",
|
| 91 |
+
"model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00007.safetensors",
|
| 92 |
+
"model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00007.safetensors",
|
| 93 |
+
"model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00007.safetensors",
|
| 94 |
+
"model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00007.safetensors",
|
| 95 |
+
"model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00007.safetensors",
|
| 96 |
+
"model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00007.safetensors",
|
| 97 |
+
"model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00007.safetensors",
|
| 98 |
+
"model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00007.safetensors",
|
| 99 |
+
"model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00007.safetensors",
|
| 100 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 101 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 102 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 103 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 104 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 105 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 106 |
+
"model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00007.safetensors",
|
| 107 |
+
"model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00007.safetensors",
|
| 108 |
+
"model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00007.safetensors",
|
| 109 |
+
"model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
|
| 110 |
+
"model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
|
| 111 |
+
"model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
|
| 112 |
+
"model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
|
| 113 |
+
"model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors",
|
| 114 |
+
"model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors",
|
| 115 |
+
"model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors",
|
| 116 |
+
"model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors",
|
| 117 |
+
"model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors",
|
| 118 |
+
"model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors",
|
| 119 |
+
"model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors",
|
| 120 |
+
"model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors",
|
| 121 |
+
"model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors",
|
| 122 |
+
"model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors",
|
| 123 |
+
"model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors",
|
| 124 |
+
"model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors",
|
| 125 |
+
"model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors",
|
| 126 |
+
"model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors",
|
| 127 |
+
"model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors",
|
| 128 |
+
"model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors",
|
| 129 |
+
"model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors",
|
| 130 |
+
"model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors",
|
| 131 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 132 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 133 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 134 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 135 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 136 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 137 |
+
"model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
|
| 138 |
+
"model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
|
| 139 |
+
"model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
|
| 140 |
+
"model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
|
| 141 |
+
"model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
|
| 142 |
+
"model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
|
| 143 |
+
"model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
|
| 144 |
+
"model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors",
|
| 145 |
+
"model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors",
|
| 146 |
+
"model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors",
|
| 147 |
+
"model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors",
|
| 148 |
+
"model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors",
|
| 149 |
+
"model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors",
|
| 150 |
+
"model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors",
|
| 151 |
+
"model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors",
|
| 152 |
+
"model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors",
|
| 153 |
+
"model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors",
|
| 154 |
+
"model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors",
|
| 155 |
+
"model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors",
|
| 156 |
+
"model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors",
|
| 157 |
+
"model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors",
|
| 158 |
+
"model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors",
|
| 159 |
+
"model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors",
|
| 160 |
+
"model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors",
|
| 161 |
+
"model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors",
|
| 162 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 163 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 164 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 165 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 166 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 167 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 168 |
+
"model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
|
| 169 |
+
"model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
|
| 170 |
+
"model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
|
| 171 |
+
"model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
|
| 172 |
+
"model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
|
| 173 |
+
"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
|
| 174 |
+
"model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
|
| 175 |
+
"model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors",
|
| 176 |
+
"model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors",
|
| 177 |
+
"model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors",
|
| 178 |
+
"model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors",
|
| 179 |
+
"model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors",
|
| 180 |
+
"model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors",
|
| 181 |
+
"model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors",
|
| 182 |
+
"model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors",
|
| 183 |
+
"model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors",
|
| 184 |
+
"model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors",
|
| 185 |
+
"model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors",
|
| 186 |
+
"model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors",
|
| 187 |
+
"model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors",
|
| 188 |
+
"model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors",
|
| 189 |
+
"model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors",
|
| 190 |
+
"model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors",
|
| 191 |
+
"model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors",
|
| 192 |
+
"model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors",
|
| 193 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 194 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 195 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 196 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 197 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 198 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 199 |
+
"model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
|
| 200 |
+
"model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
|
| 201 |
+
"model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
|
| 202 |
+
"model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
|
| 203 |
+
"model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00007.safetensors",
|
| 204 |
+
"model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00007.safetensors",
|
| 205 |
+
"model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00007.safetensors",
|
| 206 |
+
"model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00007.safetensors",
|
| 207 |
+
"model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00007.safetensors",
|
| 208 |
+
"model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00007.safetensors",
|
| 209 |
+
"model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00007.safetensors",
|
| 210 |
+
"model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00007.safetensors",
|
| 211 |
+
"model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00007.safetensors",
|
| 212 |
+
"model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00007.safetensors",
|
| 213 |
+
"model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00007.safetensors",
|
| 214 |
+
"model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00007.safetensors",
|
| 215 |
+
"model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00007.safetensors",
|
| 216 |
+
"model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00007.safetensors",
|
| 217 |
+
"model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00007.safetensors",
|
| 218 |
+
"model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00007.safetensors",
|
| 219 |
+
"model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00007.safetensors",
|
| 220 |
+
"model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00007.safetensors",
|
| 221 |
+
"model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00007.safetensors",
|
| 222 |
+
"model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00007.safetensors",
|
| 223 |
+
"model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00007.safetensors",
|
| 224 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 225 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 226 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 227 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 228 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 229 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 230 |
+
"model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00007.safetensors",
|
| 231 |
+
"model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00007.safetensors",
|
| 232 |
+
"model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00007.safetensors",
|
| 233 |
+
"model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00007.safetensors",
|
| 234 |
+
"model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
|
| 235 |
+
"model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
|
| 236 |
+
"model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
|
| 237 |
+
"model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors",
|
| 238 |
+
"model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors",
|
| 239 |
+
"model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors",
|
| 240 |
+
"model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors",
|
| 241 |
+
"model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors",
|
| 242 |
+
"model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors",
|
| 243 |
+
"model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors",
|
| 244 |
+
"model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors",
|
| 245 |
+
"model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors",
|
| 246 |
+
"model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors",
|
| 247 |
+
"model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors",
|
| 248 |
+
"model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors",
|
| 249 |
+
"model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors",
|
| 250 |
+
"model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors",
|
| 251 |
+
"model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors",
|
| 252 |
+
"model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors",
|
| 253 |
+
"model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors",
|
| 254 |
+
"model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors",
|
| 255 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 256 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 257 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 258 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 259 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 260 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 261 |
+
"model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
|
| 262 |
+
"model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
|
| 263 |
+
"model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
|
| 264 |
+
"model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
|
| 265 |
+
"model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
|
| 266 |
+
"model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
|
| 267 |
+
"model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
|
| 268 |
+
"model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors",
|
| 269 |
+
"model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors",
|
| 270 |
+
"model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors",
|
| 271 |
+
"model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors",
|
| 272 |
+
"model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors",
|
| 273 |
+
"model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors",
|
| 274 |
+
"model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors",
|
| 275 |
+
"model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors",
|
| 276 |
+
"model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors",
|
| 277 |
+
"model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors",
|
| 278 |
+
"model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors",
|
| 279 |
+
"model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors",
|
| 280 |
+
"model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors",
|
| 281 |
+
"model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors",
|
| 282 |
+
"model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors",
|
| 283 |
+
"model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors",
|
| 284 |
+
"model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors",
|
| 285 |
+
"model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors",
|
| 286 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 287 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 288 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 289 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 290 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 291 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 292 |
+
"model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
|
| 293 |
+
"model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
|
| 294 |
+
"model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
|
| 295 |
+
"model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
|
| 296 |
+
"model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
|
| 297 |
+
"model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
|
| 298 |
+
"model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
|
| 299 |
+
"model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors",
|
| 300 |
+
"model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors",
|
| 301 |
+
"model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors",
|
| 302 |
+
"model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors",
|
| 303 |
+
"model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors",
|
| 304 |
+
"model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors",
|
| 305 |
+
"model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors",
|
| 306 |
+
"model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors",
|
| 307 |
+
"model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors",
|
| 308 |
+
"model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors",
|
| 309 |
+
"model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors",
|
| 310 |
+
"model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors",
|
| 311 |
+
"model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors",
|
| 312 |
+
"model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors",
|
| 313 |
+
"model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors",
|
| 314 |
+
"model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors",
|
| 315 |
+
"model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors",
|
| 316 |
+
"model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors",
|
| 317 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 318 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 319 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 320 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 321 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 322 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 323 |
+
"model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
|
| 324 |
+
"model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
|
| 325 |
+
"model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
|
| 326 |
+
"model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
|
| 327 |
+
"model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
|
| 328 |
+
"model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00007.safetensors",
|
| 329 |
+
"model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00007.safetensors",
|
| 330 |
+
"model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00007.safetensors",
|
| 331 |
+
"model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00007.safetensors",
|
| 332 |
+
"model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00007.safetensors",
|
| 333 |
+
"model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00007.safetensors",
|
| 334 |
+
"model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00007.safetensors",
|
| 335 |
+
"model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00007.safetensors",
|
| 336 |
+
"model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00007.safetensors",
|
| 337 |
+
"model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00007.safetensors",
|
| 338 |
+
"model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00007.safetensors",
|
| 339 |
+
"model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00007.safetensors",
|
| 340 |
+
"model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00007.safetensors",
|
| 341 |
+
"model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00007.safetensors",
|
| 342 |
+
"model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00007.safetensors",
|
| 343 |
+
"model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00007.safetensors",
|
| 344 |
+
"model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00007.safetensors",
|
| 345 |
+
"model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00007.safetensors",
|
| 346 |
+
"model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00007.safetensors",
|
| 347 |
+
"model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00007.safetensors",
|
| 348 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 349 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 350 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 351 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 352 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 353 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 354 |
+
"model.layers.11.block_sparse_moe.gate.weight": "model-00003-of-00007.safetensors",
|
| 355 |
+
"model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00007.safetensors",
|
| 356 |
+
"model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00007.safetensors",
|
| 357 |
+
"model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00007.safetensors",
|
| 358 |
+
"model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00007.safetensors",
|
| 359 |
+
"model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
|
| 360 |
+
"model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
|
| 361 |
+
"model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors",
|
| 362 |
+
"model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors",
|
| 363 |
+
"model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors",
|
| 364 |
+
"model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors",
|
| 365 |
+
"model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors",
|
| 366 |
+
"model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors",
|
| 367 |
+
"model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors",
|
| 368 |
+
"model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors",
|
| 369 |
+
"model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors",
|
| 370 |
+
"model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors",
|
| 371 |
+
"model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors",
|
| 372 |
+
"model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors",
|
| 373 |
+
"model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors",
|
| 374 |
+
"model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors",
|
| 375 |
+
"model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00007.safetensors",
|
| 376 |
+
"model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors",
|
| 377 |
+
"model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors",
|
| 378 |
+
"model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors",
|
| 379 |
+
"model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 380 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 381 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 382 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 383 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 384 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 385 |
+
"model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
|
| 386 |
+
"model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
|
| 387 |
+
"model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
|
| 388 |
+
"model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
|
| 389 |
+
"model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
|
| 390 |
+
"model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
|
| 391 |
+
"model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
|
| 392 |
+
"model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors",
|
| 393 |
+
"model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors",
|
| 394 |
+
"model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors",
|
| 395 |
+
"model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors",
|
| 396 |
+
"model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors",
|
| 397 |
+
"model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors",
|
| 398 |
+
"model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors",
|
| 399 |
+
"model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors",
|
| 400 |
+
"model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors",
|
| 401 |
+
"model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors",
|
| 402 |
+
"model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors",
|
| 403 |
+
"model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors",
|
| 404 |
+
"model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors",
|
| 405 |
+
"model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors",
|
| 406 |
+
"model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00007.safetensors",
|
| 407 |
+
"model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors",
|
| 408 |
+
"model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors",
|
| 409 |
+
"model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors",
|
| 410 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 411 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 412 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 413 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 414 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 415 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 416 |
+
"model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
|
| 417 |
+
"model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
|
| 418 |
+
"model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
|
| 419 |
+
"model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
|
| 420 |
+
"model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
|
| 421 |
+
"model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
|
| 422 |
+
"model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
|
| 423 |
+
"model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors",
|
| 424 |
+
"model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors",
|
| 425 |
+
"model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors",
|
| 426 |
+
"model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors",
|
| 427 |
+
"model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors",
|
| 428 |
+
"model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors",
|
| 429 |
+
"model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors",
|
| 430 |
+
"model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors",
|
| 431 |
+
"model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors",
|
| 432 |
+
"model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors",
|
| 433 |
+
"model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors",
|
| 434 |
+
"model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors",
|
| 435 |
+
"model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors",
|
| 436 |
+
"model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors",
|
| 437 |
+
"model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00007.safetensors",
|
| 438 |
+
"model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors",
|
| 439 |
+
"model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors",
|
| 440 |
+
"model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors",
|
| 441 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 442 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 443 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 444 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 445 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 446 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 447 |
+
"model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
|
| 448 |
+
"model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
|
| 449 |
+
"model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
|
| 450 |
+
"model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
|
| 451 |
+
"model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
|
| 452 |
+
"model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
|
| 453 |
+
"model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00007.safetensors",
|
| 454 |
+
"model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00007.safetensors",
|
| 455 |
+
"model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00007.safetensors",
|
| 456 |
+
"model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00007.safetensors",
|
| 457 |
+
"model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00007.safetensors",
|
| 458 |
+
"model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00007.safetensors",
|
| 459 |
+
"model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00007.safetensors",
|
| 460 |
+
"model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00007.safetensors",
|
| 461 |
+
"model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00007.safetensors",
|
| 462 |
+
"model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00007.safetensors",
|
| 463 |
+
"model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00007.safetensors",
|
| 464 |
+
"model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00007.safetensors",
|
| 465 |
+
"model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00007.safetensors",
|
| 466 |
+
"model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00007.safetensors",
|
| 467 |
+
"model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00007.safetensors",
|
| 468 |
+
"model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00007.safetensors",
|
| 469 |
+
"model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00007.safetensors",
|
| 470 |
+
"model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00007.safetensors",
|
| 471 |
+
"model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00007.safetensors",
|
| 472 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 473 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 474 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 475 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 476 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 477 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 478 |
+
"model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00007.safetensors",
|
| 479 |
+
"model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00007.safetensors",
|
| 480 |
+
"model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00007.safetensors",
|
| 481 |
+
"model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00007.safetensors",
|
| 482 |
+
"model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00007.safetensors",
|
| 483 |
+
"model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00007.safetensors",
|
| 484 |
+
"model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
|
| 485 |
+
"model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors",
|
| 486 |
+
"model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors",
|
| 487 |
+
"model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors",
|
| 488 |
+
"model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors",
|
| 489 |
+
"model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors",
|
| 490 |
+
"model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors",
|
| 491 |
+
"model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors",
|
| 492 |
+
"model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors",
|
| 493 |
+
"model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors",
|
| 494 |
+
"model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors",
|
| 495 |
+
"model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors",
|
| 496 |
+
"model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors",
|
| 497 |
+
"model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors",
|
| 498 |
+
"model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors",
|
| 499 |
+
"model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors",
|
| 500 |
+
"model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors",
|
| 501 |
+
"model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors",
|
| 502 |
+
"model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors",
|
| 503 |
+
"model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 504 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 505 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 506 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 507 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 508 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 509 |
+
"model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
|
| 510 |
+
"model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
|
| 511 |
+
"model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
|
| 512 |
+
"model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
|
| 513 |
+
"model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
|
| 514 |
+
"model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
|
| 515 |
+
"model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
|
| 516 |
+
"model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors",
|
| 517 |
+
"model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors",
|
| 518 |
+
"model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors",
|
| 519 |
+
"model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors",
|
| 520 |
+
"model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors",
|
| 521 |
+
"model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors",
|
| 522 |
+
"model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors",
|
| 523 |
+
"model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors",
|
| 524 |
+
"model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors",
|
| 525 |
+
"model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors",
|
| 526 |
+
"model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors",
|
| 527 |
+
"model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors",
|
| 528 |
+
"model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors",
|
| 529 |
+
"model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors",
|
| 530 |
+
"model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors",
|
| 531 |
+
"model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors",
|
| 532 |
+
"model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors",
|
| 533 |
+
"model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors",
|
| 534 |
+
"model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 535 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 536 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 537 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 538 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 539 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 540 |
+
"model.layers.17.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
|
| 541 |
+
"model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
|
| 542 |
+
"model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
|
| 543 |
+
"model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
|
| 544 |
+
"model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
|
| 545 |
+
"model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
|
| 546 |
+
"model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
|
| 547 |
+
"model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors",
|
| 548 |
+
"model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors",
|
| 549 |
+
"model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors",
|
| 550 |
+
"model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors",
|
| 551 |
+
"model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors",
|
| 552 |
+
"model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors",
|
| 553 |
+
"model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors",
|
| 554 |
+
"model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors",
|
| 555 |
+
"model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors",
|
| 556 |
+
"model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors",
|
| 557 |
+
"model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors",
|
| 558 |
+
"model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors",
|
| 559 |
+
"model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors",
|
| 560 |
+
"model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors",
|
| 561 |
+
"model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors",
|
| 562 |
+
"model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors",
|
| 563 |
+
"model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors",
|
| 564 |
+
"model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors",
|
| 565 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 566 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 567 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 568 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 569 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 570 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 571 |
+
"model.layers.18.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
|
| 572 |
+
"model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
|
| 573 |
+
"model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
|
| 574 |
+
"model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
|
| 575 |
+
"model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
|
| 576 |
+
"model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
|
| 577 |
+
"model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
|
| 578 |
+
"model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00007.safetensors",
|
| 579 |
+
"model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00007.safetensors",
|
| 580 |
+
"model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00007.safetensors",
|
| 581 |
+
"model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00007.safetensors",
|
| 582 |
+
"model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00007.safetensors",
|
| 583 |
+
"model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00007.safetensors",
|
| 584 |
+
"model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00007.safetensors",
|
| 585 |
+
"model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00007.safetensors",
|
| 586 |
+
"model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00007.safetensors",
|
| 587 |
+
"model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00007.safetensors",
|
| 588 |
+
"model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00007.safetensors",
|
| 589 |
+
"model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00007.safetensors",
|
| 590 |
+
"model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00007.safetensors",
|
| 591 |
+
"model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00007.safetensors",
|
| 592 |
+
"model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00007.safetensors",
|
| 593 |
+
"model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00007.safetensors",
|
| 594 |
+
"model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00007.safetensors",
|
| 595 |
+
"model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00007.safetensors",
|
| 596 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 597 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 598 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 599 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 600 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 601 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 602 |
+
"model.layers.19.block_sparse_moe.gate.weight": "model-00005-of-00007.safetensors",
|
| 603 |
+
"model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00007.safetensors",
|
| 604 |
+
"model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00007.safetensors",
|
| 605 |
+
"model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00007.safetensors",
|
| 606 |
+
"model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00007.safetensors",
|
| 607 |
+
"model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00007.safetensors",
|
| 608 |
+
"model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00007.safetensors",
|
| 609 |
+
"model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors",
|
| 610 |
+
"model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors",
|
| 611 |
+
"model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors",
|
| 612 |
+
"model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors",
|
| 613 |
+
"model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors",
|
| 614 |
+
"model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors",
|
| 615 |
+
"model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors",
|
| 616 |
+
"model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors",
|
| 617 |
+
"model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors",
|
| 618 |
+
"model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors",
|
| 619 |
+
"model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors",
|
| 620 |
+
"model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors",
|
| 621 |
+
"model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors",
|
| 622 |
+
"model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors",
|
| 623 |
+
"model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors",
|
| 624 |
+
"model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors",
|
| 625 |
+
"model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors",
|
| 626 |
+
"model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors",
|
| 627 |
+
"model.layers.20.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 628 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 629 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 630 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 631 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 632 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 633 |
+
"model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
|
| 634 |
+
"model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
|
| 635 |
+
"model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
|
| 636 |
+
"model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
|
| 637 |
+
"model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
|
| 638 |
+
"model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
|
| 639 |
+
"model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
|
| 640 |
+
"model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors",
|
| 641 |
+
"model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors",
|
| 642 |
+
"model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors",
|
| 643 |
+
"model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors",
|
| 644 |
+
"model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors",
|
| 645 |
+
"model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors",
|
| 646 |
+
"model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors",
|
| 647 |
+
"model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors",
|
| 648 |
+
"model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors",
|
| 649 |
+
"model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors",
|
| 650 |
+
"model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors",
|
| 651 |
+
"model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors",
|
| 652 |
+
"model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors",
|
| 653 |
+
"model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors",
|
| 654 |
+
"model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors",
|
| 655 |
+
"model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors",
|
| 656 |
+
"model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors",
|
| 657 |
+
"model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors",
|
| 658 |
+
"model.layers.21.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 659 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 660 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 661 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 662 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 663 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 664 |
+
"model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
|
| 665 |
+
"model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
|
| 666 |
+
"model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
|
| 667 |
+
"model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
|
| 668 |
+
"model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
|
| 669 |
+
"model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
|
| 670 |
+
"model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
|
| 671 |
+
"model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors",
|
| 672 |
+
"model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors",
|
| 673 |
+
"model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors",
|
| 674 |
+
"model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors",
|
| 675 |
+
"model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors",
|
| 676 |
+
"model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors",
|
| 677 |
+
"model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors",
|
| 678 |
+
"model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors",
|
| 679 |
+
"model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors",
|
| 680 |
+
"model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors",
|
| 681 |
+
"model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors",
|
| 682 |
+
"model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors",
|
| 683 |
+
"model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors",
|
| 684 |
+
"model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors",
|
| 685 |
+
"model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors",
|
| 686 |
+
"model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors",
|
| 687 |
+
"model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors",
|
| 688 |
+
"model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors",
|
| 689 |
+
"model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 690 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 691 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 692 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 693 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 694 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 695 |
+
"model.layers.22.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
|
| 696 |
+
"model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
|
| 697 |
+
"model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
|
| 698 |
+
"model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
|
| 699 |
+
"model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
|
| 700 |
+
"model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
|
| 701 |
+
"model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
|
| 702 |
+
"model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors",
|
| 703 |
+
"model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00007.safetensors",
|
| 704 |
+
"model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00007.safetensors",
|
| 705 |
+
"model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00007.safetensors",
|
| 706 |
+
"model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00007.safetensors",
|
| 707 |
+
"model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00007.safetensors",
|
| 708 |
+
"model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00007.safetensors",
|
| 709 |
+
"model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00007.safetensors",
|
| 710 |
+
"model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00007.safetensors",
|
| 711 |
+
"model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00007.safetensors",
|
| 712 |
+
"model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00007.safetensors",
|
| 713 |
+
"model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00007.safetensors",
|
| 714 |
+
"model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00007.safetensors",
|
| 715 |
+
"model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00007.safetensors",
|
| 716 |
+
"model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00007.safetensors",
|
| 717 |
+
"model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00007.safetensors",
|
| 718 |
+
"model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00007.safetensors",
|
| 719 |
+
"model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00007.safetensors",
|
| 720 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 721 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 722 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 723 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 724 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 725 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 726 |
+
"model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00007.safetensors",
|
| 727 |
+
"model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00007.safetensors",
|
| 728 |
+
"model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00007.safetensors",
|
| 729 |
+
"model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00007.safetensors",
|
| 730 |
+
"model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00007.safetensors",
|
| 731 |
+
"model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00007.safetensors",
|
| 732 |
+
"model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00007.safetensors",
|
| 733 |
+
"model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00007.safetensors",
|
| 734 |
+
"model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00007.safetensors",
|
| 735 |
+
"model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00007.safetensors",
|
| 736 |
+
"model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00007.safetensors",
|
| 737 |
+
"model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00007.safetensors",
|
| 738 |
+
"model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00007.safetensors",
|
| 739 |
+
"model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00007.safetensors",
|
| 740 |
+
"model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00007.safetensors",
|
| 741 |
+
"model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00007.safetensors",
|
| 742 |
+
"model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00007.safetensors",
|
| 743 |
+
"model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00007.safetensors",
|
| 744 |
+
"model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00007.safetensors",
|
| 745 |
+
"model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00007.safetensors",
|
| 746 |
+
"model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00007.safetensors",
|
| 747 |
+
"model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00007.safetensors",
|
| 748 |
+
"model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00007.safetensors",
|
| 749 |
+
"model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00007.safetensors",
|
| 750 |
+
"model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00007.safetensors",
|
| 751 |
+
"model.norm.weight": "model-00007-of-00007.safetensors",
|
| 752 |
+
"lm_head.weight": "model-00007-of-00007.safetensors"
|
| 753 |
+
}
|
| 754 |
+
}
|
modeling_keural.py
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
KeuralMoECausalLM — Keural Mixture-of-Experts Causal Language Model.
|
| 3 |
+
|
| 4 |
+
Bilingual Korean-English MoE LLM trained entirely from scratch.
|
| 5 |
+
Developed by MKD Corp AI Research, Republic of Korea.
|
| 6 |
+
|
| 7 |
+
Architecture:
|
| 8 |
+
- 14.83B total parameters (~7.42B active per token)
|
| 9 |
+
- 24 layers, hidden=4096, GQA 32/8 heads
|
| 10 |
+
- 8 experts per layer, top-2 routing
|
| 11 |
+
- Sliding window attention (512, alternating layers)
|
| 12 |
+
- RoPE theta=500,000, context length=4096
|
| 13 |
+
- Vocabulary: 131,074 tokens (131,072 SPM + <|im_start|> + <|im_end|>)
|
| 14 |
+
|
| 15 |
+
Load with trust_remote_code=True:
|
| 16 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 17 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 18 |
+
"mkd-hossain/keural-sft3-final",
|
| 19 |
+
torch_dtype="bfloat16",
|
| 20 |
+
device_map="auto",
|
| 21 |
+
trust_remote_code=True,
|
| 22 |
+
)
|
| 23 |
+
"""
|
| 24 |
+
|
| 25 |
+
from transformers import MixtralForCausalLM
|
| 26 |
+
from transformers.utils import logging
|
| 27 |
+
|
| 28 |
+
try:
|
| 29 |
+
from configuration_keural import KeuralConfig
|
| 30 |
+
except ImportError:
|
| 31 |
+
from .configuration_keural import KeuralConfig
|
| 32 |
+
|
| 33 |
+
logger = logging.get_logger(__name__)
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
class KeuralMoECausalLM(MixtralForCausalLM):
|
| 37 |
+
"""
|
| 38 |
+
Keural MoE Causal Language Model.
|
| 39 |
+
Bilingual Korean-English 14.83B MoE LLM trained from scratch by MKD Corp AI Research.
|
| 40 |
+
"""
|
| 41 |
+
|
| 42 |
+
config_class = KeuralConfig
|
| 43 |
+
_keys_to_ignore_on_load_missing = ["lm_head.weight"]
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<bos>",
|
| 4 |
+
"single_word": false,
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"normalized": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|im_end|>",
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"normalized": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<pad>",
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"normalized": false
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [
|
| 31 |
+
{"content": "<|im_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false},
|
| 32 |
+
{"content": "<|im_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false}
|
| 33 |
+
]
|
| 34 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b982818ea2f2057ba791e2006d17683799f1d8ceb9c91322018a638c4ec4b170
|
| 3 |
+
size 2657284
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<bos>",
|
| 3 |
+
"eos_token": "<|im_end|>",
|
| 4 |
+
"unk_token": "<unk>",
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"model_max_length": 4096,
|
| 7 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"legacy": false,
|
| 10 |
+
"added_tokens_decoder": {
|
| 11 |
+
"0": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true},
|
| 12 |
+
"1": {"content": "<bos>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true},
|
| 13 |
+
"2": {"content": "<eos>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true},
|
| 14 |
+
"131072": {"content": "<|im_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true},
|
| 15 |
+
"131073": {"content": "<|im_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true}
|
| 16 |
+
},
|
| 17 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
| 18 |
+
}
|