initial commit
Browse filesCo-authored-by: WONBKIM <WONBKIM@users.noreply.huggingface.co>
- .gitattributes +37 -0
- LICENSE +201 -0
- README.md +666 -0
- assets/banner.png +3 -0
- chat_template.jinja +154 -0
- config.json +105 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +782 -0
- preprocessor_config.json +21 -0
- tokenizer.json +3 -0
- tokenizer_config.json +305 -0
- video_preprocessor_config.json +21 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
assets/banner.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
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 describing the origin of the Work and
|
| 141 |
+
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 Support. While redistributing the Work or
|
| 166 |
+
Derivative Works thereof, You may choose to offer, and charge a
|
| 167 |
+
fee for, acceptance of support, warranty, indemnity, or other
|
| 168 |
+
liability obligations and/or rights consistent with this License.
|
| 169 |
+
However, in accepting such obligations, You may act only on Your
|
| 170 |
+
own behalf and on Your sole responsibility, not on behalf of any
|
| 171 |
+
other Contributor, and only if You agree to indemnify, defend, and
|
| 172 |
+
hold each Contributor harmless for any liability incurred by, or
|
| 173 |
+
claims asserted against, such Contributor by reason of your accepting
|
| 174 |
+
any such warranty or support.
|
| 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 Data Science Lab., 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
|
| 200 |
+
implied. See the License for the specific language governing permissions
|
| 201 |
+
and limitations under the License.
|
README.md
ADDED
|
@@ -0,0 +1,666 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3.5-9B
|
| 4 |
+
base_model_relation: finetune
|
| 5 |
+
library_name: transformers
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
+
- ko
|
| 10 |
+
- ja
|
| 11 |
+
- zh
|
| 12 |
+
- es
|
| 13 |
+
- fr
|
| 14 |
+
- de
|
| 15 |
+
- ru
|
| 16 |
+
- ar
|
| 17 |
+
- pt
|
| 18 |
+
- multilingual
|
| 19 |
+
tags:
|
| 20 |
+
- text-generation
|
| 21 |
+
- chat
|
| 22 |
+
- lst
|
| 23 |
+
- language-selection-tuning
|
| 24 |
+
- language-bias
|
| 25 |
+
- bias-mitigation
|
| 26 |
+
- language-confusion-mitigation
|
| 27 |
+
- chinese-suppression
|
| 28 |
+
- korean
|
| 29 |
+
- multilingual
|
| 30 |
+
- qwen3.5
|
| 31 |
+
- mamba-hybrid
|
| 32 |
+
- vision-language
|
| 33 |
+
- composite-vision-language
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
+
# DLM-LST-9B
|
| 37 |
+
**DLM-LST-9B** is a `Qwen3.5-9B` derivative refined with our in-house **Language Selection Tuning (LST)** technique.
|
| 38 |
+
The goal is to suppress unwanted Chinese-character generation when the model is used to serve non-Chinese (English / Korean / Japanese etc.) users.
|
| 39 |
+
The adjustment is intentionally minimal in scope; most of the network — including vision and multimodal components — is preserved bit-identical to the base model.
|
| 40 |
+
Vision and multimodal capabilities are preserved unchanged.
|
| 41 |
+
|
| 42 |
+
## Why LST?
|
| 43 |
+
Multilingual LLMs trained on heavily skewed corpora (e.g., Qwen on Chinese-rich data) tend to leak the dominant training language regardless of prompt language.
|
| 44 |
+
This phenomenon is known as **language confusion**.
|
| 45 |
+
For Korean users, this means Chinese characters sometimes appear in the middle of an otherwise Korean answer. This hurts both readability and user trust.
|
| 46 |
+
|
| 47 |
+
**Language Selection Tuning (LST)** addresses this problem in a **learning-based** manner.
|
| 48 |
+
Unlike post-hoc decoding tricks (vocabulary masking, banned-token lists, etc.), LST adjusts the model's *internal* language-selection behavior,
|
| 49 |
+
so the effect tends to **persist through downstream full-parameter SFT / RLHF stages** rather than being washed out by further fine-tuning.
|
| 50 |
+
(The exact algorithm and training configuration are proprietary and not disclosed in this release.)
|
| 51 |
+
|
| 52 |
+
## Key Properties
|
| 53 |
+
- Most of the network is preserved **bit-identical** to the base model — including the tokenizer, chat template, and vision tower — so existing integrations remain compatible.
|
| 54 |
+
- **Reasoning performance is preserved**: KMMLU / HumanEval / GSM8K scores remain on par with — and in some configurations slightly above — the base model.
|
| 55 |
+
- **Selectivity is preserved**: when the user explicitly asks for Chinese, the model still produces fluent Chinese. This is not blanket suppression.
|
| 56 |
+
- **Persistence through SFT**: after a downstream full-parameter SFT stage, the Chinese-leak suppression effect remains almost unchanged (SRR ≈ 1.0).
|
| 57 |
+
|
| 58 |
+
## Quickstart
|
| 59 |
+
The recommended serving path is **vLLM**, which is also what we used in our evaluation pipeline.
|
| 60 |
+
|
| 61 |
+
```bash
|
| 62 |
+
vllm serve dataslab/DLM-LST-9B \
|
| 63 |
+
--port 8000 \
|
| 64 |
+
--dtype bfloat16 \
|
| 65 |
+
--gpu-memory-utilization 0.90 \
|
| 66 |
+
--reasoning-parser qwen3 # exposes <think> trace via OpenAI API
|
| 67 |
+
# --enable-reasoning # auto-on with --reasoning-parser (vLLM >= 0.7)
|
| 68 |
+
# --max-model-len 16384 # cap context to shrink KV cache (default: 262,144)
|
| 69 |
+
```
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
## Use with transformers
|
| 74 |
+
|
| 75 |
+
### Non-Thinking mode (recommended for fast chat)
|
| 76 |
+
|
| 77 |
+
```python
|
| 78 |
+
import torch
|
| 79 |
+
from transformers import AutoTokenizer, AutoModelForImageTextToText
|
| 80 |
+
|
| 81 |
+
REPO = "dataslab/DLM-LST-9B"
|
| 82 |
+
|
| 83 |
+
tokenizer = AutoTokenizer.from_pretrained(REPO)
|
| 84 |
+
model = AutoModelForImageTextToText.from_pretrained(
|
| 85 |
+
REPO,
|
| 86 |
+
dtype=torch.bfloat16,
|
| 87 |
+
device_map="auto",
|
| 88 |
+
)
|
| 89 |
+
|
| 90 |
+
messages = [
|
| 91 |
+
{"role": "user", "content": "한반도 주변에 가장 흔한 점토광물은?"},
|
| 92 |
+
]
|
| 93 |
+
|
| 94 |
+
prompt = tokenizer.apply_chat_template(
|
| 95 |
+
messages,
|
| 96 |
+
tokenize=False,
|
| 97 |
+
add_generation_prompt=True,
|
| 98 |
+
enable_thinking=False,
|
| 99 |
+
)
|
| 100 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 101 |
+
|
| 102 |
+
out = model.generate(**inputs, max_new_tokens=256)
|
| 103 |
+
text = tokenizer.decode(out[0][inputs.input_ids.shape[-1]:],
|
| 104 |
+
skip_special_tokens=True)
|
| 105 |
+
print(text)
|
| 106 |
+
```
|
| 107 |
+
|
| 108 |
+
### Thinking mode (recommended for complex reasoning)
|
| 109 |
+
|
| 110 |
+
Either use `thinking_budget` (e.g., vLLM's `--reasoning-parser qwen3`) or give `max_new_tokens` enough headroom (e.g., 8,192 + 256 = **8,448**).
|
| 111 |
+
**Caveat:** without a `thinking_budget` cap, a too-small `max_new_tokens` can be fully consumed inside `<think>` and the answer never gets emitted.
|
| 112 |
+
|
| 113 |
+
```python
|
| 114 |
+
# ... tokenizer / model loaded as above ...
|
| 115 |
+
|
| 116 |
+
THINKING_BUDGET = 8192 # max tokens inside <think>
|
| 117 |
+
ANSWER_TOKENS = 256 # tokens after </think>
|
| 118 |
+
|
| 119 |
+
prompt = tokenizer.apply_chat_template(
|
| 120 |
+
messages,
|
| 121 |
+
tokenize=False,
|
| 122 |
+
add_generation_prompt=True,
|
| 123 |
+
enable_thinking=True,
|
| 124 |
+
)
|
| 125 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
| 126 |
+
|
| 127 |
+
out = model.generate(**inputs, max_new_tokens=THINKING_BUDGET + ANSWER_TOKENS)
|
| 128 |
+
text = tokenizer.decode(out[0][inputs.input_ids.shape[-1]:],
|
| 129 |
+
skip_special_tokens=True)
|
| 130 |
+
print(text)
|
| 131 |
+
```
|
| 132 |
+
|
| 133 |
+
> **Why `AutoModelForImageTextToText`?** `Qwen3.5-9B`'s declared architecture is `Qwen3_5ForConditionalGeneration`,
|
| 134 |
+
> a composite class that wraps both the text decoder and the vision tower.
|
| 135 |
+
> Loading via `AutoModelForCausalLM` works for text-only inference but strips the vision submodule and may produce a config that downstream tools (e.g., vLLM) reject.
|
| 136 |
+
> If you need a pure text causal-LM handle, use `model.language_model` after loading.
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Benchmark Results
|
| 140 |
+
### Evaluation Metrics
|
| 141 |
+
|
| 142 |
+
**(1) Selectivity**
|
| 143 |
+
|
| 144 |
+
**Refusal rate** on explicit Chinese requests — the fraction of cases where the model fails to produce Chinese even though the user explicitly asked for it. Lower is better (respects user intent).
|
| 145 |
+
- **Lower better (~0)**: produces Chinese when asked (respects user intent).
|
| 146 |
+
- **Higher worse (~1)**: refuses Chinese even when asked (blanket suppression).
|
| 147 |
+
|
| 148 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 149 |
+
<colgroup>
|
| 150 |
+
<col style="width: 25%;">
|
| 151 |
+
<col style="width: 75%;">
|
| 152 |
+
</colgroup>
|
| 153 |
+
<thead>
|
| 154 |
+
<tr>
|
| 155 |
+
<th>Metric</th>
|
| 156 |
+
<th>Benchmark Dataset</th>
|
| 157 |
+
</tr>
|
| 158 |
+
</thead>
|
| 159 |
+
<tbody>
|
| 160 |
+
<tr>
|
| 161 |
+
<td><code>chin_refusal</code> ↓</td>
|
| 162 |
+
<td>In-house 1,000-prompt Chinese elicitation set (e.g., <code>How do you say '사랑' in Chinese?</code> or the Python + Chinese-comment prompt)</td>
|
| 163 |
+
</tr>
|
| 164 |
+
</tbody>
|
| 165 |
+
</table>
|
| 166 |
+
|
| 167 |
+
**(2) Chinese-leak suppression**
|
| 168 |
+
|
| 169 |
+
Korean prompts → Korean answers expected; any Chinese token leaked into the answer is a failure. Metric is the *clean-Korean response ratio*.
|
| 170 |
+
- **Higher better (~1)**: Korean answers stay fully Korean (no Chinese tokens leaked).
|
| 171 |
+
- **Lower worse (~0)**: Chinese tokens leak into otherwise-Korean answers.
|
| 172 |
+
|
| 173 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 174 |
+
<colgroup>
|
| 175 |
+
<col style="width: 25%;">
|
| 176 |
+
<col style="width: 75%;">
|
| 177 |
+
</colgroup>
|
| 178 |
+
<thead>
|
| 179 |
+
<tr>
|
| 180 |
+
<th>Metric</th>
|
| 181 |
+
<th>Benchmark Dataset</th>
|
| 182 |
+
</tr>
|
| 183 |
+
</thead>
|
| 184 |
+
<tbody>
|
| 185 |
+
<tr>
|
| 186 |
+
<td><code>chin_cs</code> ↑</td>
|
| 187 |
+
<td>KMMLU Computer Science subjects (free-form Korean generation)</td>
|
| 188 |
+
</tr>
|
| 189 |
+
<tr>
|
| 190 |
+
<td><code>chin_ie</code> ↑</td>
|
| 191 |
+
<td>KMMLU Industrial Engineering subjects (free-form Korean generation)</td>
|
| 192 |
+
</tr>
|
| 193 |
+
<tr>
|
| 194 |
+
<td><code>chin_total</code> ↑</td>
|
| 195 |
+
<td>KMMLU (free-form Korean generation)</td>
|
| 196 |
+
</tr>
|
| 197 |
+
</tbody>
|
| 198 |
+
</table>
|
| 199 |
+
|
| 200 |
+
**(3) Reasoning / task performance**
|
| 201 |
+
|
| 202 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 203 |
+
<colgroup>
|
| 204 |
+
<col style="width: 25%;">
|
| 205 |
+
<col style="width: 75%;">
|
| 206 |
+
</colgroup>
|
| 207 |
+
<thead>
|
| 208 |
+
<tr>
|
| 209 |
+
<th>Metric</th>
|
| 210 |
+
<th>Benchmark Dataset</th>
|
| 211 |
+
</tr>
|
| 212 |
+
</thead>
|
| 213 |
+
<tbody>
|
| 214 |
+
<tr>
|
| 215 |
+
<td><code>acc_cs</code> ↑</td>
|
| 216 |
+
<td>KMMLU Computer Science subjects (multiple-choice log-likelihood comparison)</td>
|
| 217 |
+
</tr>
|
| 218 |
+
<tr>
|
| 219 |
+
<td><code>acc_ie</code> ↑</td>
|
| 220 |
+
<td>KMMLU Industrial Engineering subjects (multiple-choice log-likelihood comparison)</td>
|
| 221 |
+
</tr>
|
| 222 |
+
<tr>
|
| 223 |
+
<td><code>acc_total</code> ↑</td>
|
| 224 |
+
<td>KMMLU (multiple-choice log-likelihood comparison)</td>
|
| 225 |
+
</tr>
|
| 226 |
+
<tr>
|
| 227 |
+
<td><code>HumanEval</code> ↑</td>
|
| 228 |
+
<td>HumanEval (pass@1)</td>
|
| 229 |
+
</tr>
|
| 230 |
+
<tr>
|
| 231 |
+
<td><code>GSM8K</code> ↑</td>
|
| 232 |
+
<td>GSM8K (exact-match accuracy)</td>
|
| 233 |
+
</tr>
|
| 234 |
+
</tbody>
|
| 235 |
+
</table>
|
| 236 |
+
|
| 237 |
+
**(4) Full-parameter SFT-persistence**
|
| 238 |
+
|
| 239 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 240 |
+
<colgroup>
|
| 241 |
+
<col style="width: 25%;">
|
| 242 |
+
<col style="width: 75%;">
|
| 243 |
+
</colgroup>
|
| 244 |
+
<thead>
|
| 245 |
+
<tr>
|
| 246 |
+
<th>Metric</th>
|
| 247 |
+
<th>Details</th>
|
| 248 |
+
</tr>
|
| 249 |
+
</thead>
|
| 250 |
+
<tbody>
|
| 251 |
+
<tr>
|
| 252 |
+
<td><code>SRR</code> (Suppression Retention Rate) ↑</td>
|
| 253 |
+
<td>Ratio of <code>chin_total</code> <i>after</i> SFT to <i>before</i> SFT. Closer to 1.0 = SFT did <b>not</b> erode the leak-suppression effect. Built on <code>chin_total</code> (not <code>chin_refusal</code>) so direction stays <i>higher-is-better</i>.</td>
|
| 254 |
+
</tr>
|
| 255 |
+
<tr>
|
| 256 |
+
<td><code>|Δ_selectivity|</code> ↓</td>
|
| 257 |
+
<td>Absolute change in <code>chin_refusal</code>. Smaller = SFT barely shifted selectivity.</td>
|
| 258 |
+
</tr>
|
| 259 |
+
</tbody>
|
| 260 |
+
</table>
|
| 261 |
+
|
| 262 |
+
### Chinese Suppression (**Thinking mode**)
|
| 263 |
+
|
| 264 |
+
Evaluated with `enable_thinking=True`. The DLM-LST-9B column is calibrated with thinking enabled.
|
| 265 |
+
|
| 266 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 267 |
+
<colgroup>
|
| 268 |
+
<col style="width: 20%;">
|
| 269 |
+
<col style="width: 20%;">
|
| 270 |
+
<col style="width: 20%;">
|
| 271 |
+
<col style="width: 20%;">
|
| 272 |
+
<col style="width: 20%;">
|
| 273 |
+
</colgroup>
|
| 274 |
+
<thead>
|
| 275 |
+
<tr>
|
| 276 |
+
<th>Metric</th>
|
| 277 |
+
<th>Qwen3.5-9B (base)</th>
|
| 278 |
+
<th>LST-L1</th>
|
| 279 |
+
<th>LST-L2</th>
|
| 280 |
+
<th style="color:#EAB308;"><b>DLM-LST-9B</b><br/></th>
|
| 281 |
+
</tr>
|
| 282 |
+
</thead>
|
| 283 |
+
<tbody>
|
| 284 |
+
<tr><td colspan="5" align="left"><b>(1) Selectivity</b></td></tr>
|
| 285 |
+
<tr align="center"><td align="left">chin_refusal ↓</td><td><b>0.029</b></td><td>0.993</td><td>0.992</td><td>0.065</td></tr>
|
| 286 |
+
<tr><td colspan="5" align="left"><b>(2) Chinese-leak suppression</b></td></tr>
|
| 287 |
+
<tr align="center"><td align="left">chin_cs ↑</td><td>0.985</td><td><b>1.000</b></td><td><b>1.000</b></td><td>0.999</td></tr>
|
| 288 |
+
<tr align="center"><td align="left">chin_ie ↑</td><td>0.978</td><td><b>1.000</b></td><td>0.999</td><td>0.997</td></tr>
|
| 289 |
+
<tr align="center"><td align="left">chin_total ↑</td><td>0.9717</td><td><b>0.9988</b></td><td><b>0.9988</b></td><td>0.9927</td></tr>
|
| 290 |
+
<tr><td colspan="5" align="left"><b>(3) Reasoning / Task performance</b></td></tr>
|
| 291 |
+
<tr align="center"><td align="left">acc_cs ↑</td><td>0.811</td><td>0.811</td><td>0.811</td><td>0.811</td></tr>
|
| 292 |
+
<tr align="center"><td align="left">acc_ie ↑</td><td>0.618</td><td>0.618</td><td><b>0.620</b></td><td><b>0.620</b></td></tr>
|
| 293 |
+
<tr align="center"><td align="left">acc_total ↑</td><td><b>0.5897</b></td><td><b>0.5897</b></td><td>0.5893</td><td>0.5893</td></tr>
|
| 294 |
+
<tr align="center"><td align="left">HumanEval ↑</td><td>0.6646</td><td><b>0.6768</b></td><td>0.6585</td><td>0.6646</td></tr>
|
| 295 |
+
<tr align="center"><td align="left">GSM8K ↑</td><td>0.8749</td><td>0.8749</td><td>0.8749</td><td>0.8749</td></tr>
|
| 296 |
+
</tbody>
|
| 297 |
+
</table>
|
| 298 |
+
|
| 299 |
+
**DLM-LST-9B keeps `chin_refusal` at 0.065.** It preserves the ability to generate Chinese when the user explicitly asks for it,
|
| 300 |
+
while still cutting unintended Chinese leakage to the level of `chin_total ≈ 0.99`.
|
| 301 |
+
Downstream reasoning (`acc_*`, HumanEval, GSM8K) is comparable to, or in some cases even better than, the base model.
|
| 302 |
+
|
| 303 |
+
|
| 304 |
+
### Chinese Suppression (**Non-Thinking mode**)
|
| 305 |
+
|
| 306 |
+
Evaluated with `enable_thinking=False`. The DLM-LST-9B column here is a **separate think-OFF-calibrated checkpoint** (not this release).
|
| 307 |
+
|
| 308 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 309 |
+
<colgroup>
|
| 310 |
+
<col style="width: 20%;">
|
| 311 |
+
<col style="width: 20%;">
|
| 312 |
+
<col style="width: 20%;">
|
| 313 |
+
<col style="width: 20%;">
|
| 314 |
+
<col style="width: 20%;">
|
| 315 |
+
</colgroup>
|
| 316 |
+
<thead>
|
| 317 |
+
<tr>
|
| 318 |
+
<th>Metric</th>
|
| 319 |
+
<th>Qwen3.5-9B (base)</th>
|
| 320 |
+
<th>LST-L1</th>
|
| 321 |
+
<th>LST-L2</th>
|
| 322 |
+
<th style="color:#EAB308;"><b>DLM-LST-9B</b><br/></th>
|
| 323 |
+
</tr>
|
| 324 |
+
</thead>
|
| 325 |
+
<tbody>
|
| 326 |
+
<tr><td colspan="5" align="left"><b>(1) Selectivity</b></td></tr>
|
| 327 |
+
<tr align="center"><td align="left">chin_refusal ↓</td><td><b>0.037</b></td><td>0.966</td><td>0.963</td><td>0.080</td></tr>
|
| 328 |
+
<tr><td colspan="5" align="left"><b>(2) Chinese-leak suppression</b></td></tr>
|
| 329 |
+
<tr align="center"><td align="left">chin_cs ↑</td><td>0.964</td><td>0.999</td><td><b>1.000</b></td><td>0.990</td></tr>
|
| 330 |
+
<tr align="center"><td align="left">chin_ie ↑</td><td>0.934</td><td>0.997</td><td><b>0.999</b></td><td>0.983</td></tr>
|
| 331 |
+
<tr align="center"><td align="left">chin_total ↑</td><td>0.9405</td><td>0.9974</td><td><b>0.9975</b></td><td>0.9830</td></tr>
|
| 332 |
+
<tr><td colspan="5" align="left"><b>(3) Reasoning / Task performance</b></td></tr>
|
| 333 |
+
<tr align="center"><td align="left">acc_cs ↑</td><td>0.811</td><td>0.811</td><td>0.811</td><td>0.811</td></tr>
|
| 334 |
+
<tr align="center"><td align="left">acc_ie ↑</td><td><b>0.615</b></td><td>0.614</td><td>0.614</td><td>0.614</td></tr>
|
| 335 |
+
<tr align="center"><td align="left">acc_total ↑</td><td><b>0.5900</b></td><td>0.5897</td><td>0.5897</td><td>0.5897</td></tr>
|
| 336 |
+
<tr align="center"><td align="left">HumanEval ↑</td><td>0.6707</td><td><b>0.6768</b></td><td>0.6707</td><td>0.6707</td></tr>
|
| 337 |
+
<tr align="center"><td align="left">GSM8K ↑</td><td>0.8757</td><td>0.8749</td><td>0.8741</td><td><b>0.8787</b></td></tr>
|
| 338 |
+
</tbody>
|
| 339 |
+
</table>
|
| 340 |
+
|
| 341 |
+
### Suppression Persistence after SFT-stage (**Non-Thinking mode**)
|
| 342 |
+
|
| 343 |
+
Each pipeline was fine-tuned via full-parameter SFT (all weights trainable, no PEFT / LoRA) on the beomi/KoAlpaca-v1.1a dataset.
|
| 344 |
+
After the SFT stage, DLM-LST-9B keeps both its Chinese-leak suppression (`SRR ≈ 1.000`) and its selectivity (`|Δ_selectivity| ≈ 0.08`) almost unchanged.
|
| 345 |
+
|
| 346 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 347 |
+
<colgroup>
|
| 348 |
+
<col style="width: 30%;">
|
| 349 |
+
<col style="width: 35%;">
|
| 350 |
+
<col style="width: 35%;">
|
| 351 |
+
</colgroup>
|
| 352 |
+
<thead>
|
| 353 |
+
<tr>
|
| 354 |
+
<th>Metric</th>
|
| 355 |
+
<th>Qwen3.5-9B → SFT</th>
|
| 356 |
+
<th style="color:#EAB308;"><b>DLM-LST-9B → SFT</b></th>
|
| 357 |
+
</tr>
|
| 358 |
+
</thead>
|
| 359 |
+
<tbody>
|
| 360 |
+
<tr><td colspan="3" align="left"><b>(1) Selectivity</b></td></tr>
|
| 361 |
+
<tr align="center"><td align="left">chin_refusal before ↓</td><td><b>0.037</b></td><td>0.071</td></tr>
|
| 362 |
+
<tr align="center"><td align="left">chin_refusal after ↓</td><td><b>0.128</b></td><td>0.155</td></tr>
|
| 363 |
+
<tr align="center"><td align="left">|Δ_selectivity| ↓</td><td>0.091</td><td><b>0.084</b></td></tr>
|
| 364 |
+
<tr><td colspan="3" align="left"><b>(2) Chinese-leak suppression</b></td></tr>
|
| 365 |
+
<tr align="center"><td align="left">chin_total before ↑</td><td>0.9405</td><td><b>0.9928</b></td></tr>
|
| 366 |
+
<tr align="center"><td align="left">chin_total after ↑</td><td><b>0.9927</b></td><td>0.9926</td></tr>
|
| 367 |
+
<tr align="center"><td align="left">SRR ↑</td><td><b>1.0555</b></td><td>0.9998</td></tr>
|
| 368 |
+
</tbody>
|
| 369 |
+
</table>
|
| 370 |
+
|
| 371 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 372 |
+
<colgroup>
|
| 373 |
+
<col style="width: 25%;">
|
| 374 |
+
<col style="width: 25%;">
|
| 375 |
+
<col style="width: 25%;">
|
| 376 |
+
<col style="width: 25%;">
|
| 377 |
+
</colgroup>
|
| 378 |
+
<thead>
|
| 379 |
+
<tr>
|
| 380 |
+
<th>Metric</th>
|
| 381 |
+
<th>Qwen3.5-9B (base)</th>
|
| 382 |
+
<th>Qwen3.5-9B → SFT</th>
|
| 383 |
+
<th style="color:#EAB308;"><b>DLM-LST-9B → SFT</b></th>
|
| 384 |
+
</tr>
|
| 385 |
+
</thead>
|
| 386 |
+
<tbody>
|
| 387 |
+
<tr><td colspan="4" align="left"><b>(1) Selectivity</b></td></tr>
|
| 388 |
+
<tr align="center"><td align="left">chin_refusal ↓</td><td><b>0.037</b></td><td>0.128</td><td>0.155</td></tr>
|
| 389 |
+
<tr><td colspan="4" align="left"><b>(2) Chinese-leak suppression</b></td></tr>
|
| 390 |
+
<tr align="center"><td align="left">chin_cs ↑</td><td>0.964</td><td><b>0.998</b></td><td><b>0.998</b></td></tr>
|
| 391 |
+
<tr align="center"><td align="left">chin_ie ↑</td><td>0.934</td><td>0.993</td><td><b>0.994</b></td></tr>
|
| 392 |
+
<tr align="center"><td align="left">chin_total ↑</td><td>0.9405</td><td><b>0.9927</b></td><td>0.9926</td></tr>
|
| 393 |
+
<tr><td colspan="4" align="left"><b>(3) Reasoning / Task performance</b></td></tr>
|
| 394 |
+
<tr align="center"><td align="left">acc_cs ↑</td><td><b>0.811</b></td><td>0.748</td><td>0.751</td></tr>
|
| 395 |
+
<tr align="center"><td align="left">acc_ie ↑</td><td><b>0.615</b></td><td>0.505</td><td>0.509</td></tr>
|
| 396 |
+
<tr align="center"><td align="left">acc_total ↑</td><td><b>0.5900</b></td><td>0.5202</td><td>0.5217</td></tr>
|
| 397 |
+
<tr align="center"><td align="left">HumanEval ↑</td><td><b>0.6707</b></td><td>0.6037</td><td>0.6402</td></tr>
|
| 398 |
+
<tr align="center"><td align="left">GSM8K ↑</td><td><b>0.8757</b></td><td>0.8211</td><td>0.8226</td></tr>
|
| 399 |
+
</tbody>
|
| 400 |
+
</table>
|
| 401 |
+
|
| 402 |
+
The base model's selectivity shifts substantially after full-parameter SFT (`chin_refusal` 0.037 → 0.128),
|
| 403 |
+
while DLM-LST-9B's suppression behavior remains nearly invariant before and after full-parameter SFT.
|
| 404 |
+
This shows that LST does not act as a thin surface patch — its effect is encoded in a way that **survives downstream fine-tuning**.
|
| 405 |
+
|
| 406 |
+
### English Suppression (**Non-Thinking mode**) — generalization check
|
| 407 |
+
To confirm LST is not tied to a specific language pair, we applied the same approach to `Llama-3.1-8B-Instruct` for *English* leakage suppression.
|
| 408 |
+
The DLM-LST configuration is the only variant that keeps coding (HumanEval) and math (GSM8K) usable while still meaningfully reducing leakage.
|
| 409 |
+
|
| 410 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 411 |
+
<colgroup>
|
| 412 |
+
<col style="width: 30%;">
|
| 413 |
+
<col style="width: 35%;">
|
| 414 |
+
<col style="width: 35%;">
|
| 415 |
+
</colgroup>
|
| 416 |
+
<thead>
|
| 417 |
+
<tr>
|
| 418 |
+
<th>Metric</th>
|
| 419 |
+
<th>Llama-3.1-8B-Instruct (base)</th>
|
| 420 |
+
<th style="color:#EAB308;"><b>DLM-LST (Llama-3.1-8B)</b></th>
|
| 421 |
+
</tr>
|
| 422 |
+
</thead>
|
| 423 |
+
<tbody>
|
| 424 |
+
<tr><td colspan="3" align="left"><b>(1) Selectivity</b></td></tr>
|
| 425 |
+
<tr align="center"><td align="left">eng_refusal ↓</td><td><b>0.018</b></td><td>0.067</td></tr>
|
| 426 |
+
<tr><td colspan="3" align="left"><b>(2) English-leak suppression</b></td></tr>
|
| 427 |
+
<tr align="center"><td align="left">eng_cs ↑</td><td>0.241</td><td>0.365</td></tr>
|
| 428 |
+
<tr align="center"><td align="left">eng_ie ↑</td><td>0.483</td><td>0.551</td></tr>
|
| 429 |
+
<tr align="center"><td align="left">eng_total ↑</td><td>0.5391</td><td>0.6067</td></tr>
|
| 430 |
+
<tr><td colspan="3" align="left"><b>(3) Reasoning / Task performance</b></td></tr>
|
| 431 |
+
<tr align="center"><td align="left">acc_cs ↑</td><td>0.698</td><td><b>0.727</b></td></tr>
|
| 432 |
+
<tr align="center"><td align="left">acc_ie ↑</td><td>0.439</td><td><b>0.475</b></td></tr>
|
| 433 |
+
<tr align="center"><td align="left">acc_total ↑</td><td>0.4417</td><td><b>0.4580</b></td></tr>
|
| 434 |
+
<tr align="center"><td align="left">HumanEval ↑</td><td><b>0.6341</b></td><td>0.5671</td></tr>
|
| 435 |
+
<tr align="center"><td align="left">GSM8K ↑</td><td><b>0.6967</b></td><td>0.6088</td></tr>
|
| 436 |
+
</tbody>
|
| 437 |
+
</table>
|
| 438 |
+
|
| 439 |
+
|
| 440 |
+
## Example Outputs
|
| 441 |
+
|
| 442 |
+
<p align="center">
|
| 443 |
+
<img src="assets/banner.png" alt="DLM-LST-9B vs Qwen3.5-9B on a Korean KMMLU prompt: base leaks 9 Chinese tokens (伊利石, кaо린, 的), DLM-LST-9B emits 0 Chinese tokens." width="640" />
|
| 444 |
+
</p>
|
| 445 |
+
|
| 446 |
+
Asked in Korean about the most common clay mineral on the Korean
|
| 447 |
+
Peninsula, Qwen3.5-9B leaks 9 Chinese / mixed-script tokens (`伊利石`,
|
| 448 |
+
`кao린`, `的`) into its answer. DLM-LST-9B answers the same prompt
|
| 449 |
+
entirely in Korean (0 Chinese tokens).
|
| 450 |
+
|
| 451 |
+
|
| 452 |
+
### Domain-wise Leakage Comparisons
|
| 453 |
+
|
| 454 |
+
#### Computer Science
|
| 455 |
+
|
| 456 |
+
<details open>
|
| 457 |
+
<summary><b>Prompt:</b> TCP 와 UDP 프로토콜의 차이점을 자세히 설명해 주세요.</summary>
|
| 458 |
+
|
| 459 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 460 |
+
<colgroup>
|
| 461 |
+
<col style="width: 50%;">
|
| 462 |
+
<col style="width: 50%;">
|
| 463 |
+
</colgroup>
|
| 464 |
+
<thead>
|
| 465 |
+
<tr>
|
| 466 |
+
<th>Qwen3.5-9B (leaks <code>才开始</code>)</th>
|
| 467 |
+
<th style="color:#EAB308;">DLM-LST-9B (clean Korean)</th>
|
| 468 |
+
</tr>
|
| 469 |
+
</thead>
|
| 470 |
+
<tbody>
|
| 471 |
+
<tr style="vertical-align: top;">
|
| 472 |
+
<td>
|
| 473 |
+
<blockquote>
|
| 474 |
+
TCP (Transmission Control Protocol) 와 UDP (User Datagram Protocol) 는 인터넷의 가장 기본이 되는 <b>전송 계층 (Transport Layer)</b> 프로토콜로, …
|
| 475 |
+
<br/><br/>
|
| 476 |
+
<b>1. 연결 방식 (Connection)</b><br/>
|
| 477 |
+
• <b>TCP</b>: <b>연결 지향적 (Connection-oriented)</b>입니다. … 이는 전화통화처럼 상대방이 준비된 상태에서<span style="color:#DC2626;"><b>才开始</b></span>하는 것과 같습니다.<br/>
|
| 478 |
+
• <b>UDP</b>: <b>비연결 지향적 (Connectionless)</b>입니다. …
|
| 479 |
+
</blockquote>
|
| 480 |
+
</td>
|
| 481 |
+
<td>
|
| 482 |
+
<blockquote>
|
| 483 |
+
TCP (Transmission Control Protocol) 와 UDP (User Datagram Protocol) 는 인터넷과 네트워크 통신의 기반이 되는 <b>전송 계층 (Transport Layer)</b> 의 두 가지 핵심 프로토콜입니다. …
|
| 484 |
+
<br/><br/>
|
| 485 |
+
<b>1. 연결 방식 (Connection-Oriented vs Connectionless)</b><br/>
|
| 486 |
+
• <b>TCP</b>: <b>연결 지향적</b>입니다. … 마치 우편물을 보낼 때 먼저 주소 확인과 발송 절차를 거치는 것과 같습니다. …
|
| 487 |
+
</blockquote>
|
| 488 |
+
</td>
|
| 489 |
+
</tr>
|
| 490 |
+
</tbody>
|
| 491 |
+
</table>
|
| 492 |
+
|
| 493 |
+
</details>
|
| 494 |
+
|
| 495 |
+
#### Industrial Engineering
|
| 496 |
+
|
| 497 |
+
<details open>
|
| 498 |
+
<summary><b>Prompt:</b> 린 (Lean) 제조 방식에서 정의하는 7가지 낭비 (muda) 의 종류를 한국어로 설명해 주세요.</summary>
|
| 499 |
+
|
| 500 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 501 |
+
<colgroup>
|
| 502 |
+
<col style="width: 50%;">
|
| 503 |
+
<col style="width: 50%;">
|
| 504 |
+
</colgroup>
|
| 505 |
+
<thead>
|
| 506 |
+
<tr>
|
| 507 |
+
<th>Qwen3.5-9B (leaks <code>积压</code>)</th>
|
| 508 |
+
<th style="color:#EAB308;">DLM-LST-9B (clean Korean)</th>
|
| 509 |
+
</tr>
|
| 510 |
+
</thead>
|
| 511 |
+
<tbody>
|
| 512 |
+
<tr style="vertical-align: top;">
|
| 513 |
+
<td>
|
| 514 |
+
<blockquote>
|
| 515 |
+
린 (Lean) 제조 방식에서 <b>7 가지 낭비 (7 Muda)</b> 는 … 핵심 개념입니다. …
|
| 516 |
+
<br/><br/>
|
| 517 |
+
<b>1. 과잉 생산 (Overproduction)</b><br/>
|
| 518 |
+
… 과잉 생산은 재고<span style="color:#DC2626;"><b>积压</b></span>을 유발하고, 보관 비용을 증가시키며, …
|
| 519 |
+
</blockquote>
|
| 520 |
+
</td>
|
| 521 |
+
<td>
|
| 522 |
+
<blockquote>
|
| 523 |
+
린 (Lean) 제조 방식에서 <b>7 가지 낭비 (7 Muda)</b> 는 가치 없는 활동을 제거하여 효율성을 극대화하기 위한 핵심 개념입니다. …
|
| 524 |
+
<br/><br/>
|
| 525 |
+
<b>1. 과잉 생산 (Overproduction)</b><br/>
|
| 526 |
+
… 이는 재고 증가, 보관 비용 상승, 그리고 나중에 발견될 결함 수리 비용을 초래합니다. …
|
| 527 |
+
</blockquote>
|
| 528 |
+
</td>
|
| 529 |
+
</tr>
|
| 530 |
+
</tbody>
|
| 531 |
+
</table>
|
| 532 |
+
|
| 533 |
+
</details>
|
| 534 |
+
|
| 535 |
+
#### Law
|
| 536 |
+
|
| 537 |
+
<details open>
|
| 538 |
+
<summary><b>Prompt:</b> 민법상 채권자대위권의 성립요건과 행사 방법을 자세히 설명해 주세요.</summary>
|
| 539 |
+
|
| 540 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 541 |
+
<colgroup>
|
| 542 |
+
<col style="width: 50%;">
|
| 543 |
+
<col style="width: 50%;">
|
| 544 |
+
</colgroup>
|
| 545 |
+
<thead>
|
| 546 |
+
<tr>
|
| 547 |
+
<th>Qwen3.5-9B (leaks <code>享有的</code>)</th>
|
| 548 |
+
<th style="color:#EAB308;">DLM-LST-9B (clean Korean)</th>
|
| 549 |
+
</tr>
|
| 550 |
+
</thead>
|
| 551 |
+
<tbody>
|
| 552 |
+
<tr style="vertical-align: top;">
|
| 553 |
+
<td>
|
| 554 |
+
<blockquote>
|
| 555 |
+
민법상 <b>채권자대위권</b>은 채권자가 채무자가 타인 (제 3 자) 에게<span style="color:#DC2626;"><b>享有的</b></span> 채권을 행사하지 않을 때, …
|
| 556 |
+
</blockquote>
|
| 557 |
+
</td>
|
| 558 |
+
<td>
|
| 559 |
+
<blockquote>
|
| 560 |
+
민법상 <b>채권자대위권</b>은 채무자가 그 재산에 속하는 권리를 행사하지 않음으로써 채권자의 채권이 불이행될 우려가 있는 경우, 채권자가 채무자의 지위에 서서 그 권리를 직접 행사할 수 있는 제도입니다. …
|
| 561 |
+
</blockquote>
|
| 562 |
+
</td>
|
| 563 |
+
</tr>
|
| 564 |
+
</tbody>
|
| 565 |
+
</table>
|
| 566 |
+
|
| 567 |
+
</details>
|
| 568 |
+
|
| 569 |
+
|
| 570 |
+
|
| 571 |
+
### Cross-lingual Selectivity
|
| 572 |
+
|
| 573 |
+
When the user **explicitly asks for Chinese**, DLM-LST-9B readily
|
| 574 |
+
produces it. The previous examples showed the model *avoiding* unwanted
|
| 575 |
+
Chinese inside an otherwise-Korean answer; the example below shows it
|
| 576 |
+
emitting Chinese fluently when the user's instruction calls for it.
|
| 577 |
+
|
| 578 |
+
**Prompt:** 피보나치 수열의 n번째 항을 반환하는 파이썬 함수를 작성해주세요. 설명은 중국어로 해주세요.
|
| 579 |
+
|
| 580 |
+
**DLM-LST-9B (code in Python, explanation in Chinese):**
|
| 581 |
+
|
| 582 |
+
```
|
| 583 |
+
다음은 파이썬을 사용하여 피보나치 수열의 n 번째 항을 계산하는 함수입니다.
|
| 584 |
+
이 코드는 **반복 (Iterative)** 방식을 사용하여 효율적으로 구현되었습니다.
|
| 585 |
+
|
| 586 |
+
python
|
| 587 |
+
def fibonacci(n):
|
| 588 |
+
"""피보나치 수열의 n 번째 항을 반환합니다."""
|
| 589 |
+
if n <= 0: return 0
|
| 590 |
+
elif n == 1: return 1
|
| 591 |
+
a, b = 0, 1
|
| 592 |
+
for _ in range(2, n + 1):
|
| 593 |
+
a, b = b, a + b
|
| 594 |
+
return b
|
| 595 |
+
|
| 596 |
+
|
| 597 |
+
### 코드 설명 (中文):
|
| 598 |
+
1. **函数定义**: `fibonacci(n)` 接收 `n` 并返回该位置的斐波那契数。
|
| 599 |
+
2. **边界处理**: `n <= 0` 返回 0; `n == 1` 返回 1。
|
| 600 |
+
3. **迭代计算**: 使用 `a, b` 两个变量滚动累加 ...
|
| 601 |
+
```
|
| 602 |
+
|
| 603 |
+
### Thinking-trace Suppression
|
| 604 |
+
|
| 605 |
+
Qwen3.5-9B's `<think>` block leaks Chinese even more severely than its
|
| 606 |
+
final answer, often slipping into Chinese once the reasoning gets stuck.
|
| 607 |
+
DLM-LST-9B suppresses that leakage inside the thinking block too.
|
| 608 |
+
|
| 609 |
+
**Prompt:** 업무 협조 요청을 받은 기관이 협조 요청 문서에 흠이 있음을 발견한 때에는 ���수한 날부터 몇 일 이내에 보완을 요구하여야 하는가? (사무관리규정 개정으로 제외된 문제입니다. 정답은 3번 입니다.)
|
| 610 |
+
|
| 611 |
+
**Chinese-character counts (thinking budget = 8,192):**
|
| 612 |
+
|
| 613 |
+
<table style="table-layout: fixed; width: 100%;">
|
| 614 |
+
<colgroup>
|
| 615 |
+
<col style="width: 30%;">
|
| 616 |
+
<col style="width: 35%;">
|
| 617 |
+
<col style="width: 35%;">
|
| 618 |
+
</colgroup>
|
| 619 |
+
<thead>
|
| 620 |
+
<tr>
|
| 621 |
+
<th>Metric</th>
|
| 622 |
+
<th>Qwen3.5-9B</th>
|
| 623 |
+
<th style="color:#EAB308;">DLM-LST-9B</th>
|
| 624 |
+
</tr>
|
| 625 |
+
</thead>
|
| 626 |
+
<tbody>
|
| 627 |
+
<tr align="center">
|
| 628 |
+
<td align="left"><code><think></code> block, Chinese characters</td>
|
| 629 |
+
<td><b>3,472</b></td>
|
| 630 |
+
<td style="color:#EAB308;"><b>0</b></td>
|
| 631 |
+
</tr>
|
| 632 |
+
<tr align="center">
|
| 633 |
+
<td align="left"><code><answer></code> block, Chinese characters</td>
|
| 634 |
+
<td>leaks Chinese (<code>正如您所说</code>, <code>该规定已被修订/删除</code>)</td>
|
| 635 |
+
<td style="color:#EAB308;">0 (clean Korean)</td>
|
| 636 |
+
</tr>
|
| 637 |
+
<tr align="center">
|
| 638 |
+
<td align="left">"should write in Korean" → Chinese events</td>
|
| 639 |
+
<td><b>484</b></td>
|
| 640 |
+
<td style="color:#EAB308;"><b>0</b></td>
|
| 641 |
+
</tr>
|
| 642 |
+
</tbody>
|
| 643 |
+
</table>
|
| 644 |
+
|
| 645 |
+
In the base model's trace, every cycle ends with `(Wait, I need to write in Korean). Okay, I will write in Korean.` — yet the very next token is Chinese again, and the trace slides right back into the same fragment.
|
| 646 |
+
This loop fires **484 times** before the token budget runs out. DLM-LST-9B targets exactly this failure:
|
| 647 |
+
Chinese tokens being chosen even right after the model says they should not be.
|
| 648 |
+
On the same prompt, DLM-LST-9B's `<think>` block contains **0 Chinese characters** and terminates naturally,
|
| 649 |
+
and the final user-facing answer is in clean Korean.
|
| 650 |
+
|
| 651 |
+
|
| 652 |
+
## Limitations
|
| 653 |
+
- **Not an instruction-tuned chat model.** The adjustment scope is intentionally minimal, so conversational behaviour, instruction-following style, and reasoning patterns are inherited from the base model — only the unintended Chinese-token leakage is mitigated.
|
| 654 |
+
- **Degraded Chinese generation.** Tasks that *require* Chinese output — Chinese translation, Chinese code comments, bilingual Q&A — will see noticeably lower quality. Use the base Qwen3.5-9B instead for such workloads.
|
| 655 |
+
- **Multimodal not re-benchmarked.** The vision tower weights are bit-identical to the base, so multimodal performance should be unchanged. We have not, however, re-benchmarked the vision pipeline in this release.
|
| 656 |
+
- **Out-of-distribution robustness.** Suppression strength on contexts very different from typical Korean-assistant usage — e.g., highly unusual domains, much longer generations, or atypical prompting styles — has not been separately verified.
|
| 657 |
+
|
| 658 |
+
|
| 659 |
+
## License
|
| 660 |
+
|
| 661 |
+
This model is released under the Apache 2.0 License.
|
| 662 |
+
|
| 663 |
+
## Contact
|
| 664 |
+
|
| 665 |
+
For questions, feedback, or collaboration inquiries, feel free to
|
| 666 |
+
[reach out via our website](http://www.dataslab.co.kr/).
|
assets/banner.png
ADDED
|
Git LFS Details
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 248056,
|
| 6 |
+
"model_type": "qwen3_5",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"attn_output_gate": true,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 248044,
|
| 13 |
+
"full_attention_interval": 4,
|
| 14 |
+
"head_dim": 256,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 12288,
|
| 19 |
+
"layer_types": [
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"linear_conv_kernel_dim": 4,
|
| 54 |
+
"linear_key_head_dim": 128,
|
| 55 |
+
"linear_num_key_heads": 16,
|
| 56 |
+
"linear_num_value_heads": 32,
|
| 57 |
+
"linear_value_head_dim": 128,
|
| 58 |
+
"mamba_ssm_dtype": "float32",
|
| 59 |
+
"max_position_embeddings": 262144,
|
| 60 |
+
"mlp_only_layers": [],
|
| 61 |
+
"model_type": "qwen3_5_text",
|
| 62 |
+
"mtp_num_hidden_layers": 1,
|
| 63 |
+
"mtp_use_dedicated_embeddings": false,
|
| 64 |
+
"num_attention_heads": 16,
|
| 65 |
+
"num_hidden_layers": 32,
|
| 66 |
+
"num_key_value_heads": 4,
|
| 67 |
+
"rms_norm_eps": 1e-06,
|
| 68 |
+
"rope_parameters": {
|
| 69 |
+
"mrope_interleaved": true,
|
| 70 |
+
"mrope_section": [
|
| 71 |
+
11,
|
| 72 |
+
11,
|
| 73 |
+
10
|
| 74 |
+
],
|
| 75 |
+
"partial_rotary_factor": 0.25,
|
| 76 |
+
"rope_theta": 10000000,
|
| 77 |
+
"rope_type": "default"
|
| 78 |
+
},
|
| 79 |
+
"tie_word_embeddings": false,
|
| 80 |
+
"use_cache": true,
|
| 81 |
+
"vocab_size": 248320
|
| 82 |
+
},
|
| 83 |
+
"tie_word_embeddings": false,
|
| 84 |
+
"transformers_version": "5.5.4",
|
| 85 |
+
"video_token_id": 248057,
|
| 86 |
+
"vision_config": {
|
| 87 |
+
"deepstack_visual_indexes": [],
|
| 88 |
+
"depth": 27,
|
| 89 |
+
"dtype": "bfloat16",
|
| 90 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 91 |
+
"hidden_size": 1152,
|
| 92 |
+
"in_channels": 3,
|
| 93 |
+
"initializer_range": 0.02,
|
| 94 |
+
"intermediate_size": 4304,
|
| 95 |
+
"model_type": "qwen3_5",
|
| 96 |
+
"num_heads": 16,
|
| 97 |
+
"num_position_embeddings": 2304,
|
| 98 |
+
"out_hidden_size": 4096,
|
| 99 |
+
"patch_size": 16,
|
| 100 |
+
"spatial_merge_size": 2,
|
| 101 |
+
"temporal_patch_size": 2
|
| 102 |
+
},
|
| 103 |
+
"vision_end_token_id": 248054,
|
| 104 |
+
"vision_start_token_id": 248053
|
| 105 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c40a78c3af47f0b09be9dd03bee3c53ddea144c299dfb08753f795b25903b978
|
| 3 |
+
size 5278252264
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39c4eb112dc0b6d34771968ec5ae20482a7306f63d28bcd50af27c9ee915d0b6
|
| 3 |
+
size 5358074064
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c130ac79d66af1e357ab02ccdea90cd29948dbd8f8f14522df39bbc1a4b347da
|
| 3 |
+
size 5340100512
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2596f2a1f212a6d9038022ef28e984819702992bd807d1852868300fdc41867e
|
| 3 |
+
size 3329883168
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,782 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 19306214880
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00001-of-00004.safetensors",
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 405 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 411 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 412 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 413 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 414 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 415 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 416 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 417 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 418 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 419 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 425 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 426 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 427 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 428 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 430 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 431 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 432 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
| 730 |
+
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
| 731 |
+
"model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
|
| 732 |
+
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 733 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 734 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 735 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 736 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 737 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 738 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 739 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 740 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 741 |
+
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
| 742 |
+
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
| 743 |
+
"model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
|
| 744 |
+
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
| 745 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 746 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 747 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 748 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 749 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 750 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 751 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 752 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 753 |
+
"model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
|
| 754 |
+
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
| 755 |
+
"model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
|
| 756 |
+
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
| 757 |
+
"model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 758 |
+
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 759 |
+
"model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 760 |
+
"model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 761 |
+
"model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
|
| 762 |
+
"model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
|
| 763 |
+
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
| 764 |
+
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
| 765 |
+
"model.visual.pos_embed.weight": "model-00004-of-00004.safetensors",
|
| 766 |
+
"mtp.fc.weight": "model-00004-of-00004.safetensors",
|
| 767 |
+
"mtp.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 768 |
+
"mtp.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 769 |
+
"mtp.layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 770 |
+
"mtp.layers.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 771 |
+
"mtp.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 772 |
+
"mtp.layers.0.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 773 |
+
"mtp.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 774 |
+
"mtp.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 775 |
+
"mtp.layers.0.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 776 |
+
"mtp.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 777 |
+
"mtp.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 778 |
+
"mtp.norm.weight": "model-00004-of-00004.safetensors",
|
| 779 |
+
"mtp.pre_fc_norm_embedding.weight": "model-00004-of-00004.safetensors",
|
| 780 |
+
"mtp.pre_fc_norm_hidden.weight": "model-00004-of-00004.safetensors"
|
| 781 |
+
}
|
| 782 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
|
| 3 |
+
size 12807982
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"248044": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"248045": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"248046": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"248047": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"248048": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"248049": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"248050": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"248051": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"248052": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"248053": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"248054": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"248055": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"248056": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"248057": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"248058": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"248059": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"248060": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"248061": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"248062": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"248063": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"248064": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"248065": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"248066": {
|
| 181 |
+
"content": "<tool_response>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"248067": {
|
| 189 |
+
"content": "</tool_response>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"248068": {
|
| 197 |
+
"content": "<think>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"248069": {
|
| 205 |
+
"content": "</think>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"248070": {
|
| 213 |
+
"content": "<|audio_start|>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"248071": {
|
| 221 |
+
"content": "<|audio_end|>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"248072": {
|
| 229 |
+
"content": "<tts_pad>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"248073": {
|
| 237 |
+
"content": "<tts_text_bos>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"248074": {
|
| 245 |
+
"content": "<tts_text_eod>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"248075": {
|
| 253 |
+
"content": "<tts_text_bos_single>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"248076": {
|
| 261 |
+
"content": "<|audio_pad|>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
}
|
| 268 |
+
},
|
| 269 |
+
"additional_special_tokens": [
|
| 270 |
+
"<|im_start|>",
|
| 271 |
+
"<|im_end|>",
|
| 272 |
+
"<|object_ref_start|>",
|
| 273 |
+
"<|object_ref_end|>",
|
| 274 |
+
"<|box_start|>",
|
| 275 |
+
"<|box_end|>",
|
| 276 |
+
"<|quad_start|>",
|
| 277 |
+
"<|quad_end|>",
|
| 278 |
+
"<|vision_start|>",
|
| 279 |
+
"<|vision_end|>",
|
| 280 |
+
"<|vision_pad|>",
|
| 281 |
+
"<|image_pad|>",
|
| 282 |
+
"<|video_pad|>"
|
| 283 |
+
],
|
| 284 |
+
"bos_token": null,
|
| 285 |
+
"chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 286 |
+
"clean_up_tokenization_spaces": false,
|
| 287 |
+
"eos_token": "<|im_end|>",
|
| 288 |
+
"errors": "replace",
|
| 289 |
+
"model_max_length": 262144,
|
| 290 |
+
"pad_token": "<|endoftext|>",
|
| 291 |
+
"split_special_tokens": false,
|
| 292 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 293 |
+
"unk_token": null,
|
| 294 |
+
"add_bos_token": false,
|
| 295 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 296 |
+
"extra_special_tokens": {
|
| 297 |
+
"audio_bos_token": "<|audio_start|>",
|
| 298 |
+
"audio_eos_token": "<|audio_end|>",
|
| 299 |
+
"audio_token": "<|audio_pad|>",
|
| 300 |
+
"image_token": "<|image_pad|>",
|
| 301 |
+
"video_token": "<|video_pad|>",
|
| 302 |
+
"vision_bos_token": "<|vision_start|>",
|
| 303 |
+
"vision_eos_token": "<|vision_end|>"
|
| 304 |
+
}
|
| 305 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|