Commit ·
b1374c2
0
Parent(s):
init commit
Browse files- .gitattributes +36 -0
- LICENSE +202 -0
- README.md +308 -0
- chat_template.jinja +173 -0
- config.json +666 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.safetensors +3 -0
- model.safetensors.index.json +0 -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 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
Apache License
|
| 3 |
+
Version 2.0, January 2004
|
| 4 |
+
http://www.apache.org/licenses/
|
| 5 |
+
|
| 6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 7 |
+
|
| 8 |
+
1. Definitions.
|
| 9 |
+
|
| 10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 12 |
+
|
| 13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 14 |
+
the copyright owner that is granting the License.
|
| 15 |
+
|
| 16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 17 |
+
other entities that control, are controlled by, or are under common
|
| 18 |
+
control with that entity. For the purposes of this definition,
|
| 19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 20 |
+
direction or management of such entity, whether by contract or
|
| 21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 23 |
+
|
| 24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 25 |
+
exercising permissions granted by this License.
|
| 26 |
+
|
| 27 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 28 |
+
including but not limited to software source code, documentation
|
| 29 |
+
source, and configuration files.
|
| 30 |
+
|
| 31 |
+
"Object" form shall mean any form resulting from mechanical
|
| 32 |
+
transformation or translation of a Source form, including but
|
| 33 |
+
not limited to compiled object code, generated documentation,
|
| 34 |
+
and conversions to other media types.
|
| 35 |
+
|
| 36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 37 |
+
Object form, made available under the License, as indicated by a
|
| 38 |
+
copyright notice that is included in or attached to the work
|
| 39 |
+
(an example is provided in the Appendix below).
|
| 40 |
+
|
| 41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 42 |
+
form, that is based on (or derived from) the Work and for which the
|
| 43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 45 |
+
of this License, Derivative Works shall not include works that remain
|
| 46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 47 |
+
the Work and Derivative Works thereof.
|
| 48 |
+
|
| 49 |
+
"Contribution" shall mean any work of authorship, including
|
| 50 |
+
the original version of the Work and any modifications or additions
|
| 51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 55 |
+
means any form of electronic, verbal, or written communication sent
|
| 56 |
+
to the Licensor or its representatives, including but not limited to
|
| 57 |
+
communication on electronic mailing lists, source code control systems,
|
| 58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 60 |
+
excluding communication that is conspicuously marked or otherwise
|
| 61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 62 |
+
|
| 63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 65 |
+
subsequently incorporated within the Work.
|
| 66 |
+
|
| 67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 72 |
+
Work and such Derivative Works in Source or Object form.
|
| 73 |
+
|
| 74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 77 |
+
(except as stated in this section) patent license to make, have made,
|
| 78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 79 |
+
where such license applies only to those patent claims licensable
|
| 80 |
+
by such Contributor that are necessarily infringed by their
|
| 81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 83 |
+
institute patent litigation against any entity (including a
|
| 84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 85 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 86 |
+
or contributory patent infringement, then any patent licenses
|
| 87 |
+
granted to You under this License for that Work shall terminate
|
| 88 |
+
as of the date such litigation is filed.
|
| 89 |
+
|
| 90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 91 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 92 |
+
modifications, and in Source or Object form, provided that You
|
| 93 |
+
meet the following conditions:
|
| 94 |
+
|
| 95 |
+
(a) You must give any other recipients of the Work or
|
| 96 |
+
Derivative Works a copy of this License; and
|
| 97 |
+
|
| 98 |
+
(b) You must cause any modified files to carry prominent notices
|
| 99 |
+
stating that You changed the files; and
|
| 100 |
+
|
| 101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 102 |
+
that You distribute, all copyright, patent, trademark, and
|
| 103 |
+
attribution notices from the Source form of the Work,
|
| 104 |
+
excluding those notices that do not pertain to any part of
|
| 105 |
+
the Derivative Works; and
|
| 106 |
+
|
| 107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 108 |
+
distribution, then any Derivative Works that You distribute must
|
| 109 |
+
include a readable copy of the attribution notices contained
|
| 110 |
+
within such NOTICE file, excluding those notices that do not
|
| 111 |
+
pertain to any part of the Derivative Works, in at least one
|
| 112 |
+
of the following places: within a NOTICE text file distributed
|
| 113 |
+
as part of the Derivative Works; within the Source form or
|
| 114 |
+
documentation, if provided along with the Derivative Works; or,
|
| 115 |
+
within a display generated by the Derivative Works, if and
|
| 116 |
+
wherever such third-party notices normally appear. The contents
|
| 117 |
+
of the NOTICE file are for informational purposes only and
|
| 118 |
+
do not modify the License. You may add Your own attribution
|
| 119 |
+
notices within Derivative Works that You distribute, alongside
|
| 120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 121 |
+
that such additional attribution notices cannot be construed
|
| 122 |
+
as modifying the License.
|
| 123 |
+
|
| 124 |
+
You may add Your own copyright statement to Your modifications and
|
| 125 |
+
may provide additional or different license terms and conditions
|
| 126 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 127 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 128 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 129 |
+
the conditions stated in this License.
|
| 130 |
+
|
| 131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 133 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 134 |
+
this License, without any additional terms or conditions.
|
| 135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 136 |
+
the terms of any separate license agreement you may have executed
|
| 137 |
+
with Licensor regarding such Contributions.
|
| 138 |
+
|
| 139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 141 |
+
except as required for reasonable and customary use in describing the
|
| 142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 143 |
+
|
| 144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 145 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 148 |
+
implied, including, without limitation, any warranties or conditions
|
| 149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 151 |
+
appropriateness of using or redistributing the Work and assume any
|
| 152 |
+
risks associated with Your exercise of permissions under this License.
|
| 153 |
+
|
| 154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 155 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 156 |
+
unless required by applicable law (such as deliberate and grossly
|
| 157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 158 |
+
liable to You for damages, including any direct, indirect, special,
|
| 159 |
+
incidental, or consequential damages of any character arising as a
|
| 160 |
+
result of this License or out of the use or inability to use the
|
| 161 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 162 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 163 |
+
other commercial damages or losses), even if such Contributor
|
| 164 |
+
has been advised of the possibility of such damages.
|
| 165 |
+
|
| 166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 169 |
+
or other liability obligations and/or rights consistent with this
|
| 170 |
+
License. However, in accepting such obligations, You may act only
|
| 171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 172 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 173 |
+
defend, and hold each Contributor harmless for any liability
|
| 174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 175 |
+
of your accepting any such warranty or additional liability.
|
| 176 |
+
|
| 177 |
+
END OF TERMS AND CONDITIONS
|
| 178 |
+
|
| 179 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 180 |
+
|
| 181 |
+
To apply the Apache License to your work, attach the following
|
| 182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 183 |
+
replaced with your own identifying information. (Don't include
|
| 184 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 185 |
+
comment syntax for the file format. We also recommend that a
|
| 186 |
+
file or class name and description of purpose be included on the
|
| 187 |
+
same "printed page" as the copyright notice for easier
|
| 188 |
+
identification within third-party archives.
|
| 189 |
+
|
| 190 |
+
Copyright 2026 Alibaba Cloud
|
| 191 |
+
|
| 192 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 193 |
+
you may not use this file except in compliance with the License.
|
| 194 |
+
You may obtain a copy of the License at
|
| 195 |
+
|
| 196 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 197 |
+
|
| 198 |
+
Unless required by applicable law or agreed to in writing, software
|
| 199 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 200 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 201 |
+
See the License for the specific language governing permissions and
|
| 202 |
+
limitations under the License.
|
README.md
ADDED
|
@@ -0,0 +1,308 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
- zh
|
| 8 |
+
base_model:
|
| 9 |
+
- Qwen/Qwen3.5-35B-A3B
|
| 10 |
+
tags:
|
| 11 |
+
- agent
|
| 12 |
+
- apodex
|
| 13 |
+
- arxiv:2608.23283
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<div align="center">
|
| 17 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6466e7be1343dce20e59191b/aFPexDrJ5TMuxszCnr4E0.png" width="55%" alt="Apodex" />
|
| 18 |
+
</div>
|
| 19 |
+
|
| 20 |
+
<hr>
|
| 21 |
+
|
| 22 |
+
<div align="center" style="line-height:1">
|
| 23 |
+
|
| 24 |
+
</div>
|
| 25 |
+
|
| 26 |
+
<h2 align="center">Apodex 1.1: Scaling Agentic Intelligence for Complex Work</h2>
|
| 27 |
+
|
| 28 |
+
<div align="center" style="line-height:1">
|
| 29 |
+
<a href="https://www.apodex.ai" target="_blank"><img alt="Online Service" src="https://img.shields.io/badge/🤖%20Online Service-Apodex 1.1-ff6b6b?color=1783ff&logoColor=white"/></a>
|
| 30 |
+
<a href="https://www.apodex.com/" target="_blank"><img alt="Homepage" src="https://img.shields.io/badge/Homepage-Apodex AI-white?logoColor=white"/></a>
|
| 31 |
+
<a href="https://platform.apodex.ai" target="_blank"><img alt="API" src="https://img.shields.io/badge/API-Apodex 1.1-1783ff?color=1783ff&logoColor=white"/></a>
|
| 32 |
+
</div>
|
| 33 |
+
|
| 34 |
+
<div align="center" style="line-height: 1;">
|
| 35 |
+
<a href="https://github.com/ApodexAI/FrontierAgent" target="_blank"><img alt="GitHub" src="https://img.shields.io/badge/GitHub-Apodex AI-white?logo=github&logoColor=white"/></a>
|
| 36 |
+
<a href="https://huggingface.co/apodex/Apodex-1.1-mini-FP8/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/badge/License-Apache_2.0-blue?color=blue"/></a>
|
| 37 |
+
</div>
|
| 38 |
+
<p align="center">
|
| 39 |
+
<b>📰<a href="https://www.apodex.com/blog/apodex-1.1-scaling-agentic-intelligence-for-complex-work">Tech Blog</a></b> | <b>📄<a href="https://www.apodex.com/pdf/20260824">Tech Report</a></b>
|
| 40 |
+
</p>
|
| 41 |
+
|
| 42 |
+
## 1. Model Introduction
|
| 43 |
+
|
| 44 |
+
**Apodex-1.1** is a reasoning-first model for complex, long-horizon research tasks. Beyond searching and writing reports, it works directly with files, data, code, and tools to complete tasks from input to verifiable deliverables. Powered by AgentOS and an asynchronous Agent Team, it can maintain task state, adapt its plan, coordinate parallel work, and incorporate user feedback throughout execution.
|
| 45 |
+
|
| 46 |
+
### Online Service
|
| 47 |
+
|
| 48 |
+
Try Apodex at [apodex.ai](https://www.apodex.ai).
|
| 49 |
+
|
| 50 |
+
### Key Features
|
| 51 |
+
|
| 52 |
+
- **End-to-end execution in real environments.** Apodex 1.1 works directly with papers, datasets, spreadsheets, images, and code. It can clean data, select methods, run analyses, inspect intermediate results, recover from errors, and turn raw inputs into verifiable deliverables within one continuous task.
|
| 53 |
+
- **Adaptive and user-steerable Agent Team.** The model dynamically decomposes complex tasks and coordinates multiple Subagents working in parallel. Results flow continuously into a shared task state, allowing Apodex to revise priorities, preserve completed work, and respond to new files, requirements, or user feedback without restarting the entire task.
|
| 54 |
+
- **Verification built into delivery.** Statement Review independently checks key claims against their supporting sources, data, and computations before delivery. When evidence is insufficient, citations do not match, or results conflict with expectations, the system flags the issue, corrects the affected conclusion, and keeps the review process inspectable.
|
| 55 |
+
|
| 56 |
+
## 2. Evaluation Results
|
| 57 |
+
|
| 58 |
+
> To prevent potential information leakage (e.g., retrieving benchmark answers from public repositories), we block access to relevant benchmark-hosting websites during evaluation.
|
| 59 |
+
|
| 60 |
+
Apodex 1.1 Agent Team delivers frontier-level performance across professional work, finance, scientific research, and general reasoning, achieving 38.5 on APEX-Agents, 78.8 on GDPVal, 54.3 on FrontierFinance, 63.3 on FrontierScience-Research, 35.3 on BioMysteryBench, and 56.1 on Humanity’s Last Exam. It consistently improves over the ReAct setup across all six benchmarks and achieves the highest scores among the compared systems on FrontierFinance and FrontierScience-Research.
|
| 61 |
+
<div align="center">
|
| 62 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6466e7be1343dce20e59191b/yvDHTuMzAaRqmgzw59HRR.png" width="100%" alt="Apodex Benchmarks" />
|
| 63 |
+
</div>
|
| 64 |
+
|
| 65 |
+
Apodex-1.1-mini remains competitive with frontier models, leading FrontierFinance with 50.2 and nearly matching the best result on APEX-Agent with 27.7. Its Agent Team setup also consistently outperforms ReAct across all three benchmarks. You can try Apodex-1.1-mini with our [Agent Team harness](https://github.com/ApodexAI/FrontierAgent).
|
| 66 |
+
<div align="center">
|
| 67 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6466e7be1343dce20e59191b/hBfEXL7HCBEXBTzZc3_4i.png" width="100%" alt="Apodex Benchmarks" />
|
| 68 |
+
</div>
|
| 69 |
+
|
| 70 |
+
## 3. Quick Start
|
| 71 |
+
|
| 72 |
+
Apodex follows the Qwen3.5 chat template — tool calls are emitted as <tool_call><function=...><parameter=...></parameter></function></tool_call> and reasoning as <think>...</think>. Launch with the matching parsers so the server returns standard OpenAI-style tool_calls and reasoning_content fields.
|
| 73 |
+
|
| 74 |
+
### 3.1 Deployment
|
| 75 |
+
|
| 76 |
+
We recommend deploying Apodex with the latest [SGLang](https://github.com/sgl-project/sglang) for an OpenAI-compatible endpoint.
|
| 77 |
+
|
| 78 |
+
```shell
|
| 79 |
+
python3 -m sglang.launch_server \
|
| 80 |
+
--model-path apodex/Apodex-1.1-mini-FP8 \
|
| 81 |
+
--tp 1 \
|
| 82 |
+
--tool-call-parser qwen3_coder --reasoning-parser qwen3 \
|
| 83 |
+
--context-length 262144 \
|
| 84 |
+
--speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 \
|
| 85 |
+
--speculative-num-draft-tokens 4 \
|
| 86 |
+
--mamba-scheduler-strategy extra_buffer --mamba-ssm-dtype bfloat16
|
| 87 |
+
```
|
| 88 |
+
|
| 89 |
+
### 3.2 Best Practices
|
| 90 |
+
|
| 91 |
+
For optimal performance in agentic tasks, we recommend:
|
| 92 |
+
|
| 93 |
+
```
|
| 94 |
+
temperature: 1.0
|
| 95 |
+
top_p: 0.95
|
| 96 |
+
repetition_penalty: 1.05
|
| 97 |
+
max_context_length: 262144
|
| 98 |
+
max_tokens: 32768
|
| 99 |
+
```
|
| 100 |
+
|
| 101 |
+
### 3.3 Agentic Usage
|
| 102 |
+
|
| 103 |
+
Apodex is trained for native function calling — tool schemas are passed via the tools= parameter of the chat-completions API and rendered into the prompt by the chat template, so the system prompt itself only needs to set the role and the high-level objective. We recommend the prompt below (this is the prompt used in our internal evaluation runs):
|
| 104 |
+
|
| 105 |
+
```
|
| 106 |
+
You are Apodex, an AI assistant developed by Apodex AI.
|
| 107 |
+
|
| 108 |
+
Apodex is the flagship agent of Apodex AI. Rather than a conventional conversational LLM, it is a general-purpose solver designed for mission-critical tasks.
|
| 109 |
+
|
| 110 |
+
Current time: {today_date}. In this environment you have access to a set of tools you can use to answer the user's question.
|
| 111 |
+
|
| 112 |
+
You only have access to the tools provided. You can use multiple tools per message, and will receive the results of those tools in the user's next response. You use tools step-by-step to accomplish a given task.
|
| 113 |
+
|
| 114 |
+
# General Objective
|
| 115 |
+
|
| 116 |
+
You accomplish a given task iteratively, breaking it down into clear steps and working through them methodically.
|
| 117 |
+
```
|
| 118 |
+
|
| 119 |
+
Substitute `{today_date}` with the current date (e.g. `2026-06-01`). **Do not** inline tool descriptions in the system prompt — pass them via `tools=` so the Qwen3.5 chat template can emit the correct `<tool_call><function=...>` format and the server-side `qwen3_coder` parser can recover structured `tool_calls` for you.
|
| 120 |
+
|
| 121 |
+
The example below runs Apodex as a tool-using agent against an OpenAI-compatible endpoint (the SGLang / vLLM server launched above). The agent loops — executing the requested tools and feeding results back as `role="tool"` messages — until the model produces a final answer with no tool calls.
|
| 122 |
+
|
| 123 |
+
Before running, set the endpoint:
|
| 124 |
+
|
| 125 |
+
```bash
|
| 126 |
+
export OPENAI_API_KEY="EMPTY" # any non-empty string for local servers
|
| 127 |
+
export BASE_URL="http://localhost:1234/v1"
|
| 128 |
+
```
|
| 129 |
+
|
| 130 |
+
<details open>
|
| 131 |
+
<summary>Click to expand python code example</summary>
|
| 132 |
+
|
| 133 |
+
```python
|
| 134 |
+
import json
|
| 135 |
+
import os
|
| 136 |
+
from datetime import date
|
| 137 |
+
from openai import OpenAI
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
# -------- 1. Tool implementations --------
|
| 141 |
+
def get_weather(location: str, unit: str = "celsius") -> str:
|
| 142 |
+
"""Get current weather information for a city (simulated)."""
|
| 143 |
+
table = {
|
| 144 |
+
"London": {"temperature": 15, "condition": "sunny", "humidity": 45},
|
| 145 |
+
"New York": {"temperature": 20, "condition": "cloudy", "humidity": 60},
|
| 146 |
+
"Tokyo": {"temperature": 25, "condition": "rainy", "humidity": 75},
|
| 147 |
+
}
|
| 148 |
+
w = dict(table.get(location, {"temperature": 18, "condition": "unknown", "humidity": 50}))
|
| 149 |
+
if unit == "fahrenheit":
|
| 150 |
+
w["temperature"] = w["temperature"] * 9 / 5 + 32
|
| 151 |
+
w["unit"] = "°F"
|
| 152 |
+
else:
|
| 153 |
+
w["unit"] = "°C"
|
| 154 |
+
return json.dumps(w, ensure_ascii=False)
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
def calculate(expression: str) -> str:
|
| 158 |
+
"""Evaluate a Python-style arithmetic expression."""
|
| 159 |
+
try:
|
| 160 |
+
return json.dumps({"expression": expression, "result": eval(expression)}, ensure_ascii=False)
|
| 161 |
+
except Exception as e:
|
| 162 |
+
return json.dumps({"expression": expression, "error": str(e)}, ensure_ascii=False)
|
| 163 |
+
|
| 164 |
+
|
| 165 |
+
available_tools = {"get_weather": get_weather, "calculate": calculate}
|
| 166 |
+
|
| 167 |
+
|
| 168 |
+
# -------- 2. Tool schemas (OpenAI function-calling format) --------
|
| 169 |
+
tools = [
|
| 170 |
+
{
|
| 171 |
+
"type": "function",
|
| 172 |
+
"function": {
|
| 173 |
+
"name": "get_weather",
|
| 174 |
+
"description": "Get current weather information for a city.",
|
| 175 |
+
"parameters": {
|
| 176 |
+
"type": "object",
|
| 177 |
+
"properties": {
|
| 178 |
+
"location": {"type": "string", "description": "City name, e.g. 'London'."},
|
| 179 |
+
"unit": {
|
| 180 |
+
"type": "string",
|
| 181 |
+
"enum": ["celsius", "fahrenheit"],
|
| 182 |
+
"description": "Temperature unit (default: celsius).",
|
| 183 |
+
},
|
| 184 |
+
},
|
| 185 |
+
"required": ["location"],
|
| 186 |
+
},
|
| 187 |
+
},
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"type": "function",
|
| 191 |
+
"function": {
|
| 192 |
+
"name": "calculate",
|
| 193 |
+
"description": "Evaluate a Python-style arithmetic expression.",
|
| 194 |
+
"parameters": {
|
| 195 |
+
"type": "object",
|
| 196 |
+
"properties": {
|
| 197 |
+
"expression": {
|
| 198 |
+
"type": "string",
|
| 199 |
+
"description": "Expression to evaluate, e.g. '(25 + 15) * 3 - 10'.",
|
| 200 |
+
},
|
| 201 |
+
},
|
| 202 |
+
"required": ["expression"],
|
| 203 |
+
},
|
| 204 |
+
},
|
| 205 |
+
},
|
| 206 |
+
]
|
| 207 |
+
|
| 208 |
+
|
| 209 |
+
# -------- 3. System prompt --------
|
| 210 |
+
SYSTEM_PROMPT = f"""You are Apodex, an AI assistant developed by Apodex AI.
|
| 211 |
+
|
| 212 |
+
Apodex is the flagship agent of Apodex AI. Rather than a conventional conversational LLM, it is a general-purpose solver designed for mission-critical tasks.
|
| 213 |
+
|
| 214 |
+
Current time: {date.today()}. In this environment you have access to a set of tools you can use to answer the user's question.
|
| 215 |
+
|
| 216 |
+
You only have access to the tools provided. You can use multiple tools per message, and will receive the results of those tools in the user's next response. You use tools step-by-step to accomplish a given task.
|
| 217 |
+
|
| 218 |
+
# General Objective
|
| 219 |
+
|
| 220 |
+
You accomplish a given task iteratively, breaking it down into clear steps and working through them methodically."""
|
| 221 |
+
|
| 222 |
+
|
| 223 |
+
# -------- 4. Agentic loop --------
|
| 224 |
+
def run_agent(user_query: str, model: str = "apodex/Apodex-1.1-mini-FP8", max_turns: int = 20):
|
| 225 |
+
client = OpenAI(
|
| 226 |
+
api_key=os.environ.get("OPENAI_API_KEY", "EMPTY"),
|
| 227 |
+
base_url=os.environ.get("BASE_URL", "<http://localhost:1234/v1>"),
|
| 228 |
+
)
|
| 229 |
+
|
| 230 |
+
messages = [
|
| 231 |
+
{"role": "system", "content": SYSTEM_PROMPT},
|
| 232 |
+
{"role": "user", "content": user_query},
|
| 233 |
+
]
|
| 234 |
+
print(f"\\n{'=' * 60}\\nUser: {user_query}\\n{'=' * 60}\\n")
|
| 235 |
+
|
| 236 |
+
for turn in range(max_turns):
|
| 237 |
+
resp = client.chat.completions.create(
|
| 238 |
+
model=model,
|
| 239 |
+
messages=messages,
|
| 240 |
+
tools=tools,
|
| 241 |
+
parallel_tool_calls=True,
|
| 242 |
+
temperature=1.0,
|
| 243 |
+
top_p=0.95,
|
| 244 |
+
max_tokens=16384,
|
| 245 |
+
extra_body={"repetition_penalty": 1.05},
|
| 246 |
+
)
|
| 247 |
+
msg = resp.choices[0].message
|
| 248 |
+
|
| 249 |
+
# Optional: print reasoning if the server exposes it (qwen3 reasoning parser)
|
| 250 |
+
reasoning = getattr(msg, "reasoning_content", None)
|
| 251 |
+
if reasoning:
|
| 252 |
+
print(f"[think] {reasoning.strip()}\\n")
|
| 253 |
+
if msg.content:
|
| 254 |
+
print(f"[assistant] {msg.content.strip()}\\n")
|
| 255 |
+
|
| 256 |
+
messages.append(msg)
|
| 257 |
+
|
| 258 |
+
# No more tool calls -> final answer
|
| 259 |
+
if not msg.tool_calls:
|
| 260 |
+
print(f"💬 Final answer:\\n{msg.content}\\n")
|
| 261 |
+
return msg.content
|
| 262 |
+
|
| 263 |
+
# Execute every tool call requested in this turn
|
| 264 |
+
for call in msg.tool_calls:
|
| 265 |
+
name = call.function.name
|
| 266 |
+
args = json.loads(call.function.arguments or "{}")
|
| 267 |
+
print(f"🔧 call {name}({args})")
|
| 268 |
+
try:
|
| 269 |
+
result = available_toolsname
|
| 270 |
+
except Exception as e:
|
| 271 |
+
result = json.dumps({"error": f"{type(e).__name__}: {e}"}, ensure_ascii=False)
|
| 272 |
+
print(f" ↳ {result}\\n")
|
| 273 |
+
messages.append({
|
| 274 |
+
"role": "tool",
|
| 275 |
+
"tool_call_id": call.id,
|
| 276 |
+
"content": result,
|
| 277 |
+
})
|
| 278 |
+
|
| 279 |
+
print("⚠️ Reached max_turns without a final answer.")
|
| 280 |
+
return None
|
| 281 |
+
|
| 282 |
+
|
| 283 |
+
if __name__ == "__main__":
|
| 284 |
+
run_agent("What's the weather in London in Fahrenheit, and what's (25 + 15) * 3 - 10?")
|
| 285 |
+
```
|
| 286 |
+
|
| 287 |
+
</details>
|
| 288 |
+
|
| 289 |
+
|
| 290 |
+
## 4. License
|
| 291 |
+
|
| 292 |
+
Apodex-1.1 is released under Apache 2.0.
|
| 293 |
+
|
| 294 |
+
## 5. Citation
|
| 295 |
+
|
| 296 |
+
If you find this project useful in your research, please consider citing:
|
| 297 |
+
|
| 298 |
+
```
|
| 299 |
+
@article{apodex2026,
|
| 300 |
+
title={Apodex 1.1: Scaling Agentic Intelligence for Complex Work},
|
| 301 |
+
author={Apodex Team},
|
| 302 |
+
year={2026}
|
| 303 |
+
}
|
| 304 |
+
```
|
| 305 |
+
|
| 306 |
+
## Contact
|
| 307 |
+
|
| 308 |
+
Reach the Apodex Team via our [website](https://apodex.com).
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set apodex_identity = '# Role Definition\n- Name: Apodex\n- Developer: Apodex AI\n- Identity: An AI assistant developed by Apodex AI\n- Core Principle: Always respond as Apodex and never pretend or claim to be any other AI model\n- Please interact with the user strictly in the identity of Apodex.' %}
|
| 2 |
+
{%- set identity_mode = identity_mode if identity_mode is defined else 'fallback' %}
|
| 3 |
+
{%- set has_caller_system = (messages and messages[0].role == 'system') %}
|
| 4 |
+
{%- set inject_identity = (identity_mode == 'force') or (identity_mode == 'fallback' and not has_caller_system) %}
|
| 5 |
+
{%- set image_count = namespace(value=0) %}
|
| 6 |
+
{%- set video_count = namespace(value=0) %}
|
| 7 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 8 |
+
{%- if content is string %}
|
| 9 |
+
{{- content }}
|
| 10 |
+
{%- elif content is iterable and content is not mapping %}
|
| 11 |
+
{%- for item in content %}
|
| 12 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 13 |
+
{%- if is_system_content %}
|
| 14 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- if do_vision_count %}
|
| 17 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 18 |
+
{%- endif %}
|
| 19 |
+
{%- if add_vision_id %}
|
| 20 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 23 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 24 |
+
{%- if is_system_content %}
|
| 25 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 26 |
+
{%- endif %}
|
| 27 |
+
{%- if do_vision_count %}
|
| 28 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
{%- if add_vision_id %}
|
| 31 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 34 |
+
{%- elif 'text' in item %}
|
| 35 |
+
{{- item.text }}
|
| 36 |
+
{%- else %}
|
| 37 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- endfor %}
|
| 40 |
+
{%- elif content is none or content is undefined %}
|
| 41 |
+
{{- '' }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- endmacro %}
|
| 46 |
+
{%- if not messages %}
|
| 47 |
+
{{- raise_exception('No messages provided.') }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 50 |
+
{{- '<|im_start|>system\n' }}
|
| 51 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 52 |
+
{%- for tool in tools %}
|
| 53 |
+
{{- "\n" }}
|
| 54 |
+
{{- tool | tojson }}
|
| 55 |
+
{%- endfor %}
|
| 56 |
+
{{- "\n</tools>" }}
|
| 57 |
+
{{- '\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>' }}
|
| 58 |
+
{%- if inject_identity %}
|
| 59 |
+
{{- '\n\n' + apodex_identity }}
|
| 60 |
+
{%- endif %}
|
| 61 |
+
{%- if has_caller_system %}
|
| 62 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 63 |
+
{%- if content %}
|
| 64 |
+
{{- '\n\n' + content }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- else %}
|
| 69 |
+
{%- if inject_identity or has_caller_system %}
|
| 70 |
+
{{- '<|im_start|>system\n' }}
|
| 71 |
+
{%- set parts = namespace(first=true) %}
|
| 72 |
+
{%- if inject_identity %}
|
| 73 |
+
{{- apodex_identity }}
|
| 74 |
+
{%- set parts.first = false %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- if has_caller_system %}
|
| 77 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 78 |
+
{%- if content %}
|
| 79 |
+
{%- if not parts.first %}{{- '\n\n' }}{%- endif %}
|
| 80 |
+
{{- content }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{{- '<|im_end|>\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 87 |
+
{%- for message in messages[::-1] %}
|
| 88 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 89 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 90 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 91 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 92 |
+
{%- set ns.multi_step_tool = false %}
|
| 93 |
+
{%- set ns.last_query_index = index %}
|
| 94 |
+
{%- endif %}
|
| 95 |
+
{%- endif %}
|
| 96 |
+
{%- endfor %}
|
| 97 |
+
{%- if ns.multi_step_tool %}
|
| 98 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 99 |
+
{%- endif %}
|
| 100 |
+
{%- for message in messages %}
|
| 101 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 102 |
+
{%- if message.role == "system" %}
|
| 103 |
+
{%- if not loop.first %}
|
| 104 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 105 |
+
{%- endif %}
|
| 106 |
+
{%- elif message.role == "user" %}
|
| 107 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 108 |
+
{%- elif message.role == "assistant" %}
|
| 109 |
+
{%- set reasoning_content = '' %}
|
| 110 |
+
{%- if message.reasoning_content is string %}
|
| 111 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 112 |
+
{%- else %}
|
| 113 |
+
{%- if '</think>' in content %}
|
| 114 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 115 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endif %}
|
| 118 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 119 |
+
{%- if (preserve_thinking is not defined or preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
|
| 120 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 121 |
+
{%- else %}
|
| 122 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 123 |
+
{%- endif %}
|
| 124 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 125 |
+
{%- for tool_call in message.tool_calls %}
|
| 126 |
+
{%- if tool_call.function is defined %}
|
| 127 |
+
{%- set tool_call = tool_call.function %}
|
| 128 |
+
{%- endif %}
|
| 129 |
+
{%- if loop.first %}
|
| 130 |
+
{%- if content|trim %}
|
| 131 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{%- else %}
|
| 136 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 137 |
+
{%- endif %}
|
| 138 |
+
{%- if tool_call.arguments is defined %}
|
| 139 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 140 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 141 |
+
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
| 142 |
+
{{- args_value }}
|
| 143 |
+
{{- '\n</parameter>\n' }}
|
| 144 |
+
{%- endfor %}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{{- '</function>\n</tool_call>' }}
|
| 147 |
+
{%- endfor %}
|
| 148 |
+
{%- endif %}
|
| 149 |
+
{{- '<|im_end|>\n' }}
|
| 150 |
+
{%- elif message.role == "tool" %}
|
| 151 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 152 |
+
{{- '<|im_start|>user' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{{- '\n<tool_response>\n' }}
|
| 155 |
+
{{- content }}
|
| 156 |
+
{{- '\n</tool_response>' }}
|
| 157 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 158 |
+
{{- '<|im_end|>\n' }}
|
| 159 |
+
{%- elif loop.last %}
|
| 160 |
+
{{- '<|im_end|>\n' }}
|
| 161 |
+
{%- endif %}
|
| 162 |
+
{%- else %}
|
| 163 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 164 |
+
{%- endif %}
|
| 165 |
+
{%- endfor %}
|
| 166 |
+
{%- if add_generation_prompt %}
|
| 167 |
+
{{- '<|im_start|>assistant\n' }}
|
| 168 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 169 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 170 |
+
{%- else %}
|
| 171 |
+
{{- '<think>\n' }}
|
| 172 |
+
{%- endif %}
|
| 173 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,666 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5MoeForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 248056,
|
| 6 |
+
"model_type": "qwen3_5_moe",
|
| 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": 2048,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"full_attention"
|
| 59 |
+
],
|
| 60 |
+
"linear_conv_kernel_dim": 4,
|
| 61 |
+
"linear_key_head_dim": 128,
|
| 62 |
+
"linear_num_key_heads": 16,
|
| 63 |
+
"linear_num_value_heads": 32,
|
| 64 |
+
"linear_value_head_dim": 128,
|
| 65 |
+
"max_position_embeddings": 262144,
|
| 66 |
+
"mlp_only_layers": [],
|
| 67 |
+
"model_type": "qwen3_5_moe_text",
|
| 68 |
+
"moe_intermediate_size": 512,
|
| 69 |
+
"mtp_num_hidden_layers": 1,
|
| 70 |
+
"mtp_use_dedicated_embeddings": false,
|
| 71 |
+
"num_attention_heads": 16,
|
| 72 |
+
"num_experts": 256,
|
| 73 |
+
"num_experts_per_tok": 8,
|
| 74 |
+
"num_hidden_layers": 40,
|
| 75 |
+
"num_key_value_heads": 2,
|
| 76 |
+
"rms_norm_eps": 1e-06,
|
| 77 |
+
"router_aux_loss_coef": 0.001,
|
| 78 |
+
"shared_expert_intermediate_size": 512,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"vocab_size": 248320,
|
| 81 |
+
"mamba_ssm_dtype": "float32",
|
| 82 |
+
"rope_parameters": {
|
| 83 |
+
"mrope_interleaved": true,
|
| 84 |
+
"mrope_section": [
|
| 85 |
+
11,
|
| 86 |
+
11,
|
| 87 |
+
10
|
| 88 |
+
],
|
| 89 |
+
"rope_type": "default",
|
| 90 |
+
"rope_theta": 10000000,
|
| 91 |
+
"partial_rotary_factor": 0.25
|
| 92 |
+
}
|
| 93 |
+
},
|
| 94 |
+
"tie_word_embeddings": false,
|
| 95 |
+
"transformers_version": "4.57.0.dev0",
|
| 96 |
+
"video_token_id": 248057,
|
| 97 |
+
"vision_config": {
|
| 98 |
+
"deepstack_visual_indexes": [],
|
| 99 |
+
"depth": 27,
|
| 100 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 101 |
+
"hidden_size": 1152,
|
| 102 |
+
"in_channels": 3,
|
| 103 |
+
"initializer_range": 0.02,
|
| 104 |
+
"intermediate_size": 4304,
|
| 105 |
+
"model_type": "qwen3_5_moe",
|
| 106 |
+
"num_heads": 16,
|
| 107 |
+
"num_position_embeddings": 2304,
|
| 108 |
+
"out_hidden_size": 2048,
|
| 109 |
+
"patch_size": 16,
|
| 110 |
+
"spatial_merge_size": 2,
|
| 111 |
+
"temporal_patch_size": 2
|
| 112 |
+
},
|
| 113 |
+
"vision_end_token_id": 248054,
|
| 114 |
+
"vision_start_token_id": 248053,
|
| 115 |
+
"quantization_config": {
|
| 116 |
+
"activation_scheme": "dynamic",
|
| 117 |
+
"fmt": "e4m3",
|
| 118 |
+
"quant_method": "fp8",
|
| 119 |
+
"weight_block_size": [
|
| 120 |
+
128,
|
| 121 |
+
128
|
| 122 |
+
],
|
| 123 |
+
"modules_to_not_convert": [
|
| 124 |
+
"lm_head",
|
| 125 |
+
"model.language_model.embed_tokens",
|
| 126 |
+
"model.language_model.layers.0.input_layernorm",
|
| 127 |
+
"model.language_model.layers.0.linear_attn.A_log",
|
| 128 |
+
"model.language_model.layers.0.linear_attn.conv1d",
|
| 129 |
+
"model.language_model.layers.0.linear_attn.dt_bias",
|
| 130 |
+
"model.language_model.layers.0.linear_attn.in_proj_a",
|
| 131 |
+
"model.language_model.layers.0.linear_attn.in_proj_b",
|
| 132 |
+
"model.language_model.layers.0.linear_attn.norm",
|
| 133 |
+
"model.language_model.layers.0.mlp.gate",
|
| 134 |
+
"model.language_model.layers.0.mlp.shared_expert_gate",
|
| 135 |
+
"model.language_model.layers.0.post_attention_layernorm",
|
| 136 |
+
"model.language_model.layers.1.input_layernorm",
|
| 137 |
+
"model.language_model.layers.1.linear_attn.A_log",
|
| 138 |
+
"model.language_model.layers.1.linear_attn.conv1d",
|
| 139 |
+
"model.language_model.layers.1.linear_attn.dt_bias",
|
| 140 |
+
"model.language_model.layers.1.linear_attn.in_proj_a",
|
| 141 |
+
"model.language_model.layers.1.linear_attn.in_proj_b",
|
| 142 |
+
"model.language_model.layers.1.linear_attn.norm",
|
| 143 |
+
"model.language_model.layers.1.mlp.gate",
|
| 144 |
+
"model.language_model.layers.1.mlp.shared_expert_gate",
|
| 145 |
+
"model.language_model.layers.1.post_attention_layernorm",
|
| 146 |
+
"model.language_model.layers.10.input_layernorm",
|
| 147 |
+
"model.language_model.layers.10.linear_attn.A_log",
|
| 148 |
+
"model.language_model.layers.10.linear_attn.conv1d",
|
| 149 |
+
"model.language_model.layers.10.linear_attn.dt_bias",
|
| 150 |
+
"model.language_model.layers.10.linear_attn.in_proj_a",
|
| 151 |
+
"model.language_model.layers.10.linear_attn.in_proj_b",
|
| 152 |
+
"model.language_model.layers.10.linear_attn.norm",
|
| 153 |
+
"model.language_model.layers.10.mlp.gate",
|
| 154 |
+
"model.language_model.layers.10.mlp.shared_expert_gate",
|
| 155 |
+
"model.language_model.layers.10.post_attention_layernorm",
|
| 156 |
+
"model.language_model.layers.11.input_layernorm",
|
| 157 |
+
"model.language_model.layers.11.mlp.gate",
|
| 158 |
+
"model.language_model.layers.11.mlp.shared_expert_gate",
|
| 159 |
+
"model.language_model.layers.11.post_attention_layernorm",
|
| 160 |
+
"model.language_model.layers.11.self_attn.k_norm",
|
| 161 |
+
"model.language_model.layers.11.self_attn.q_norm",
|
| 162 |
+
"model.language_model.layers.12.input_layernorm",
|
| 163 |
+
"model.language_model.layers.12.linear_attn.A_log",
|
| 164 |
+
"model.language_model.layers.12.linear_attn.conv1d",
|
| 165 |
+
"model.language_model.layers.12.linear_attn.dt_bias",
|
| 166 |
+
"model.language_model.layers.12.linear_attn.in_proj_a",
|
| 167 |
+
"model.language_model.layers.12.linear_attn.in_proj_b",
|
| 168 |
+
"model.language_model.layers.12.linear_attn.norm",
|
| 169 |
+
"model.language_model.layers.12.mlp.gate",
|
| 170 |
+
"model.language_model.layers.12.mlp.shared_expert_gate",
|
| 171 |
+
"model.language_model.layers.12.post_attention_layernorm",
|
| 172 |
+
"model.language_model.layers.13.input_layernorm",
|
| 173 |
+
"model.language_model.layers.13.linear_attn.A_log",
|
| 174 |
+
"model.language_model.layers.13.linear_attn.conv1d",
|
| 175 |
+
"model.language_model.layers.13.linear_attn.dt_bias",
|
| 176 |
+
"model.language_model.layers.13.linear_attn.in_proj_a",
|
| 177 |
+
"model.language_model.layers.13.linear_attn.in_proj_b",
|
| 178 |
+
"model.language_model.layers.13.linear_attn.norm",
|
| 179 |
+
"model.language_model.layers.13.mlp.gate",
|
| 180 |
+
"model.language_model.layers.13.mlp.shared_expert_gate",
|
| 181 |
+
"model.language_model.layers.13.post_attention_layernorm",
|
| 182 |
+
"model.language_model.layers.14.input_layernorm",
|
| 183 |
+
"model.language_model.layers.14.linear_attn.A_log",
|
| 184 |
+
"model.language_model.layers.14.linear_attn.conv1d",
|
| 185 |
+
"model.language_model.layers.14.linear_attn.dt_bias",
|
| 186 |
+
"model.language_model.layers.14.linear_attn.in_proj_a",
|
| 187 |
+
"model.language_model.layers.14.linear_attn.in_proj_b",
|
| 188 |
+
"model.language_model.layers.14.linear_attn.norm",
|
| 189 |
+
"model.language_model.layers.14.mlp.gate",
|
| 190 |
+
"model.language_model.layers.14.mlp.shared_expert_gate",
|
| 191 |
+
"model.language_model.layers.14.post_attention_layernorm",
|
| 192 |
+
"model.language_model.layers.15.input_layernorm",
|
| 193 |
+
"model.language_model.layers.15.mlp.gate",
|
| 194 |
+
"model.language_model.layers.15.mlp.shared_expert_gate",
|
| 195 |
+
"model.language_model.layers.15.post_attention_layernorm",
|
| 196 |
+
"model.language_model.layers.15.self_attn.k_norm",
|
| 197 |
+
"model.language_model.layers.15.self_attn.q_norm",
|
| 198 |
+
"model.language_model.layers.16.input_layernorm",
|
| 199 |
+
"model.language_model.layers.16.linear_attn.A_log",
|
| 200 |
+
"model.language_model.layers.16.linear_attn.conv1d",
|
| 201 |
+
"model.language_model.layers.16.linear_attn.dt_bias",
|
| 202 |
+
"model.language_model.layers.16.linear_attn.in_proj_a",
|
| 203 |
+
"model.language_model.layers.16.linear_attn.in_proj_b",
|
| 204 |
+
"model.language_model.layers.16.linear_attn.norm",
|
| 205 |
+
"model.language_model.layers.16.mlp.gate",
|
| 206 |
+
"model.language_model.layers.16.mlp.shared_expert_gate",
|
| 207 |
+
"model.language_model.layers.16.post_attention_layernorm",
|
| 208 |
+
"model.language_model.layers.17.input_layernorm",
|
| 209 |
+
"model.language_model.layers.17.linear_attn.A_log",
|
| 210 |
+
"model.language_model.layers.17.linear_attn.conv1d",
|
| 211 |
+
"model.language_model.layers.17.linear_attn.dt_bias",
|
| 212 |
+
"model.language_model.layers.17.linear_attn.in_proj_a",
|
| 213 |
+
"model.language_model.layers.17.linear_attn.in_proj_b",
|
| 214 |
+
"model.language_model.layers.17.linear_attn.norm",
|
| 215 |
+
"model.language_model.layers.17.mlp.gate",
|
| 216 |
+
"model.language_model.layers.17.mlp.shared_expert_gate",
|
| 217 |
+
"model.language_model.layers.17.post_attention_layernorm",
|
| 218 |
+
"model.language_model.layers.18.input_layernorm",
|
| 219 |
+
"model.language_model.layers.18.linear_attn.A_log",
|
| 220 |
+
"model.language_model.layers.18.linear_attn.conv1d",
|
| 221 |
+
"model.language_model.layers.18.linear_attn.dt_bias",
|
| 222 |
+
"model.language_model.layers.18.linear_attn.in_proj_a",
|
| 223 |
+
"model.language_model.layers.18.linear_attn.in_proj_b",
|
| 224 |
+
"model.language_model.layers.18.linear_attn.norm",
|
| 225 |
+
"model.language_model.layers.18.mlp.gate",
|
| 226 |
+
"model.language_model.layers.18.mlp.shared_expert_gate",
|
| 227 |
+
"model.language_model.layers.18.post_attention_layernorm",
|
| 228 |
+
"model.language_model.layers.19.input_layernorm",
|
| 229 |
+
"model.language_model.layers.19.mlp.gate",
|
| 230 |
+
"model.language_model.layers.19.mlp.shared_expert_gate",
|
| 231 |
+
"model.language_model.layers.19.post_attention_layernorm",
|
| 232 |
+
"model.language_model.layers.19.self_attn.k_norm",
|
| 233 |
+
"model.language_model.layers.19.self_attn.q_norm",
|
| 234 |
+
"model.language_model.layers.2.input_layernorm",
|
| 235 |
+
"model.language_model.layers.2.linear_attn.A_log",
|
| 236 |
+
"model.language_model.layers.2.linear_attn.conv1d",
|
| 237 |
+
"model.language_model.layers.2.linear_attn.dt_bias",
|
| 238 |
+
"model.language_model.layers.2.linear_attn.in_proj_a",
|
| 239 |
+
"model.language_model.layers.2.linear_attn.in_proj_b",
|
| 240 |
+
"model.language_model.layers.2.linear_attn.norm",
|
| 241 |
+
"model.language_model.layers.2.mlp.gate",
|
| 242 |
+
"model.language_model.layers.2.mlp.shared_expert_gate",
|
| 243 |
+
"model.language_model.layers.2.post_attention_layernorm",
|
| 244 |
+
"model.language_model.layers.20.input_layernorm",
|
| 245 |
+
"model.language_model.layers.20.linear_attn.A_log",
|
| 246 |
+
"model.language_model.layers.20.linear_attn.conv1d",
|
| 247 |
+
"model.language_model.layers.20.linear_attn.dt_bias",
|
| 248 |
+
"model.language_model.layers.20.linear_attn.in_proj_a",
|
| 249 |
+
"model.language_model.layers.20.linear_attn.in_proj_b",
|
| 250 |
+
"model.language_model.layers.20.linear_attn.norm",
|
| 251 |
+
"model.language_model.layers.20.mlp.gate",
|
| 252 |
+
"model.language_model.layers.20.mlp.shared_expert_gate",
|
| 253 |
+
"model.language_model.layers.20.post_attention_layernorm",
|
| 254 |
+
"model.language_model.layers.21.input_layernorm",
|
| 255 |
+
"model.language_model.layers.21.linear_attn.A_log",
|
| 256 |
+
"model.language_model.layers.21.linear_attn.conv1d",
|
| 257 |
+
"model.language_model.layers.21.linear_attn.dt_bias",
|
| 258 |
+
"model.language_model.layers.21.linear_attn.in_proj_a",
|
| 259 |
+
"model.language_model.layers.21.linear_attn.in_proj_b",
|
| 260 |
+
"model.language_model.layers.21.linear_attn.norm",
|
| 261 |
+
"model.language_model.layers.21.mlp.gate",
|
| 262 |
+
"model.language_model.layers.21.mlp.shared_expert_gate",
|
| 263 |
+
"model.language_model.layers.21.post_attention_layernorm",
|
| 264 |
+
"model.language_model.layers.22.input_layernorm",
|
| 265 |
+
"model.language_model.layers.22.linear_attn.A_log",
|
| 266 |
+
"model.language_model.layers.22.linear_attn.conv1d",
|
| 267 |
+
"model.language_model.layers.22.linear_attn.dt_bias",
|
| 268 |
+
"model.language_model.layers.22.linear_attn.in_proj_a",
|
| 269 |
+
"model.language_model.layers.22.linear_attn.in_proj_b",
|
| 270 |
+
"model.language_model.layers.22.linear_attn.norm",
|
| 271 |
+
"model.language_model.layers.22.mlp.gate",
|
| 272 |
+
"model.language_model.layers.22.mlp.shared_expert_gate",
|
| 273 |
+
"model.language_model.layers.22.post_attention_layernorm",
|
| 274 |
+
"model.language_model.layers.23.input_layernorm",
|
| 275 |
+
"model.language_model.layers.23.mlp.gate",
|
| 276 |
+
"model.language_model.layers.23.mlp.shared_expert_gate",
|
| 277 |
+
"model.language_model.layers.23.post_attention_layernorm",
|
| 278 |
+
"model.language_model.layers.23.self_attn.k_norm",
|
| 279 |
+
"model.language_model.layers.23.self_attn.q_norm",
|
| 280 |
+
"model.language_model.layers.24.input_layernorm",
|
| 281 |
+
"model.language_model.layers.24.linear_attn.A_log",
|
| 282 |
+
"model.language_model.layers.24.linear_attn.conv1d",
|
| 283 |
+
"model.language_model.layers.24.linear_attn.dt_bias",
|
| 284 |
+
"model.language_model.layers.24.linear_attn.in_proj_a",
|
| 285 |
+
"model.language_model.layers.24.linear_attn.in_proj_b",
|
| 286 |
+
"model.language_model.layers.24.linear_attn.norm",
|
| 287 |
+
"model.language_model.layers.24.mlp.gate",
|
| 288 |
+
"model.language_model.layers.24.mlp.shared_expert_gate",
|
| 289 |
+
"model.language_model.layers.24.post_attention_layernorm",
|
| 290 |
+
"model.language_model.layers.25.input_layernorm",
|
| 291 |
+
"model.language_model.layers.25.linear_attn.A_log",
|
| 292 |
+
"model.language_model.layers.25.linear_attn.conv1d",
|
| 293 |
+
"model.language_model.layers.25.linear_attn.dt_bias",
|
| 294 |
+
"model.language_model.layers.25.linear_attn.in_proj_a",
|
| 295 |
+
"model.language_model.layers.25.linear_attn.in_proj_b",
|
| 296 |
+
"model.language_model.layers.25.linear_attn.norm",
|
| 297 |
+
"model.language_model.layers.25.mlp.gate",
|
| 298 |
+
"model.language_model.layers.25.mlp.shared_expert_gate",
|
| 299 |
+
"model.language_model.layers.25.post_attention_layernorm",
|
| 300 |
+
"model.language_model.layers.26.input_layernorm",
|
| 301 |
+
"model.language_model.layers.26.linear_attn.A_log",
|
| 302 |
+
"model.language_model.layers.26.linear_attn.conv1d",
|
| 303 |
+
"model.language_model.layers.26.linear_attn.dt_bias",
|
| 304 |
+
"model.language_model.layers.26.linear_attn.in_proj_a",
|
| 305 |
+
"model.language_model.layers.26.linear_attn.in_proj_b",
|
| 306 |
+
"model.language_model.layers.26.linear_attn.norm",
|
| 307 |
+
"model.language_model.layers.26.mlp.gate",
|
| 308 |
+
"model.language_model.layers.26.mlp.shared_expert_gate",
|
| 309 |
+
"model.language_model.layers.26.post_attention_layernorm",
|
| 310 |
+
"model.language_model.layers.27.input_layernorm",
|
| 311 |
+
"model.language_model.layers.27.mlp.gate",
|
| 312 |
+
"model.language_model.layers.27.mlp.shared_expert_gate",
|
| 313 |
+
"model.language_model.layers.27.post_attention_layernorm",
|
| 314 |
+
"model.language_model.layers.27.self_attn.k_norm",
|
| 315 |
+
"model.language_model.layers.27.self_attn.q_norm",
|
| 316 |
+
"model.language_model.layers.28.input_layernorm",
|
| 317 |
+
"model.language_model.layers.28.linear_attn.A_log",
|
| 318 |
+
"model.language_model.layers.28.linear_attn.conv1d",
|
| 319 |
+
"model.language_model.layers.28.linear_attn.dt_bias",
|
| 320 |
+
"model.language_model.layers.28.linear_attn.in_proj_a",
|
| 321 |
+
"model.language_model.layers.28.linear_attn.in_proj_b",
|
| 322 |
+
"model.language_model.layers.28.linear_attn.norm",
|
| 323 |
+
"model.language_model.layers.28.mlp.gate",
|
| 324 |
+
"model.language_model.layers.28.mlp.shared_expert_gate",
|
| 325 |
+
"model.language_model.layers.28.post_attention_layernorm",
|
| 326 |
+
"model.language_model.layers.29.input_layernorm",
|
| 327 |
+
"model.language_model.layers.29.linear_attn.A_log",
|
| 328 |
+
"model.language_model.layers.29.linear_attn.conv1d",
|
| 329 |
+
"model.language_model.layers.29.linear_attn.dt_bias",
|
| 330 |
+
"model.language_model.layers.29.linear_attn.in_proj_a",
|
| 331 |
+
"model.language_model.layers.29.linear_attn.in_proj_b",
|
| 332 |
+
"model.language_model.layers.29.linear_attn.norm",
|
| 333 |
+
"model.language_model.layers.29.mlp.gate",
|
| 334 |
+
"model.language_model.layers.29.mlp.shared_expert_gate",
|
| 335 |
+
"model.language_model.layers.29.post_attention_layernorm",
|
| 336 |
+
"model.language_model.layers.3.input_layernorm",
|
| 337 |
+
"model.language_model.layers.3.mlp.gate",
|
| 338 |
+
"model.language_model.layers.3.mlp.shared_expert_gate",
|
| 339 |
+
"model.language_model.layers.3.post_attention_layernorm",
|
| 340 |
+
"model.language_model.layers.3.self_attn.k_norm",
|
| 341 |
+
"model.language_model.layers.3.self_attn.q_norm",
|
| 342 |
+
"model.language_model.layers.30.input_layernorm",
|
| 343 |
+
"model.language_model.layers.30.linear_attn.A_log",
|
| 344 |
+
"model.language_model.layers.30.linear_attn.conv1d",
|
| 345 |
+
"model.language_model.layers.30.linear_attn.dt_bias",
|
| 346 |
+
"model.language_model.layers.30.linear_attn.in_proj_a",
|
| 347 |
+
"model.language_model.layers.30.linear_attn.in_proj_b",
|
| 348 |
+
"model.language_model.layers.30.linear_attn.norm",
|
| 349 |
+
"model.language_model.layers.30.mlp.gate",
|
| 350 |
+
"model.language_model.layers.30.mlp.shared_expert_gate",
|
| 351 |
+
"model.language_model.layers.30.post_attention_layernorm",
|
| 352 |
+
"model.language_model.layers.31.input_layernorm",
|
| 353 |
+
"model.language_model.layers.31.mlp.gate",
|
| 354 |
+
"model.language_model.layers.31.mlp.shared_expert_gate",
|
| 355 |
+
"model.language_model.layers.31.post_attention_layernorm",
|
| 356 |
+
"model.language_model.layers.31.self_attn.k_norm",
|
| 357 |
+
"model.language_model.layers.31.self_attn.q_norm",
|
| 358 |
+
"model.language_model.layers.32.input_layernorm",
|
| 359 |
+
"model.language_model.layers.32.linear_attn.A_log",
|
| 360 |
+
"model.language_model.layers.32.linear_attn.conv1d",
|
| 361 |
+
"model.language_model.layers.32.linear_attn.dt_bias",
|
| 362 |
+
"model.language_model.layers.32.linear_attn.in_proj_a",
|
| 363 |
+
"model.language_model.layers.32.linear_attn.in_proj_b",
|
| 364 |
+
"model.language_model.layers.32.linear_attn.norm",
|
| 365 |
+
"model.language_model.layers.32.mlp.gate",
|
| 366 |
+
"model.language_model.layers.32.mlp.shared_expert_gate",
|
| 367 |
+
"model.language_model.layers.32.post_attention_layernorm",
|
| 368 |
+
"model.language_model.layers.33.input_layernorm",
|
| 369 |
+
"model.language_model.layers.33.linear_attn.A_log",
|
| 370 |
+
"model.language_model.layers.33.linear_attn.conv1d",
|
| 371 |
+
"model.language_model.layers.33.linear_attn.dt_bias",
|
| 372 |
+
"model.language_model.layers.33.linear_attn.in_proj_a",
|
| 373 |
+
"model.language_model.layers.33.linear_attn.in_proj_b",
|
| 374 |
+
"model.language_model.layers.33.linear_attn.norm",
|
| 375 |
+
"model.language_model.layers.33.mlp.gate",
|
| 376 |
+
"model.language_model.layers.33.mlp.shared_expert_gate",
|
| 377 |
+
"model.language_model.layers.33.post_attention_layernorm",
|
| 378 |
+
"model.language_model.layers.34.input_layernorm",
|
| 379 |
+
"model.language_model.layers.34.linear_attn.A_log",
|
| 380 |
+
"model.language_model.layers.34.linear_attn.conv1d",
|
| 381 |
+
"model.language_model.layers.34.linear_attn.dt_bias",
|
| 382 |
+
"model.language_model.layers.34.linear_attn.in_proj_a",
|
| 383 |
+
"model.language_model.layers.34.linear_attn.in_proj_b",
|
| 384 |
+
"model.language_model.layers.34.linear_attn.norm",
|
| 385 |
+
"model.language_model.layers.34.mlp.gate",
|
| 386 |
+
"model.language_model.layers.34.mlp.shared_expert_gate",
|
| 387 |
+
"model.language_model.layers.34.post_attention_layernorm",
|
| 388 |
+
"model.language_model.layers.35.input_layernorm",
|
| 389 |
+
"model.language_model.layers.35.mlp.gate",
|
| 390 |
+
"model.language_model.layers.35.mlp.shared_expert_gate",
|
| 391 |
+
"model.language_model.layers.35.post_attention_layernorm",
|
| 392 |
+
"model.language_model.layers.35.self_attn.k_norm",
|
| 393 |
+
"model.language_model.layers.35.self_attn.q_norm",
|
| 394 |
+
"model.language_model.layers.36.input_layernorm",
|
| 395 |
+
"model.language_model.layers.36.linear_attn.A_log",
|
| 396 |
+
"model.language_model.layers.36.linear_attn.conv1d",
|
| 397 |
+
"model.language_model.layers.36.linear_attn.dt_bias",
|
| 398 |
+
"model.language_model.layers.36.linear_attn.in_proj_a",
|
| 399 |
+
"model.language_model.layers.36.linear_attn.in_proj_b",
|
| 400 |
+
"model.language_model.layers.36.linear_attn.norm",
|
| 401 |
+
"model.language_model.layers.36.mlp.gate",
|
| 402 |
+
"model.language_model.layers.36.mlp.shared_expert_gate",
|
| 403 |
+
"model.language_model.layers.36.post_attention_layernorm",
|
| 404 |
+
"model.language_model.layers.37.input_layernorm",
|
| 405 |
+
"model.language_model.layers.37.linear_attn.A_log",
|
| 406 |
+
"model.language_model.layers.37.linear_attn.conv1d",
|
| 407 |
+
"model.language_model.layers.37.linear_attn.dt_bias",
|
| 408 |
+
"model.language_model.layers.37.linear_attn.in_proj_a",
|
| 409 |
+
"model.language_model.layers.37.linear_attn.in_proj_b",
|
| 410 |
+
"model.language_model.layers.37.linear_attn.norm",
|
| 411 |
+
"model.language_model.layers.37.mlp.gate",
|
| 412 |
+
"model.language_model.layers.37.mlp.shared_expert_gate",
|
| 413 |
+
"model.language_model.layers.37.post_attention_layernorm",
|
| 414 |
+
"model.language_model.layers.38.input_layernorm",
|
| 415 |
+
"model.language_model.layers.38.linear_attn.A_log",
|
| 416 |
+
"model.language_model.layers.38.linear_attn.conv1d",
|
| 417 |
+
"model.language_model.layers.38.linear_attn.dt_bias",
|
| 418 |
+
"model.language_model.layers.38.linear_attn.in_proj_a",
|
| 419 |
+
"model.language_model.layers.38.linear_attn.in_proj_b",
|
| 420 |
+
"model.language_model.layers.38.linear_attn.norm",
|
| 421 |
+
"model.language_model.layers.38.mlp.gate",
|
| 422 |
+
"model.language_model.layers.38.mlp.shared_expert_gate",
|
| 423 |
+
"model.language_model.layers.38.post_attention_layernorm",
|
| 424 |
+
"model.language_model.layers.39.input_layernorm",
|
| 425 |
+
"model.language_model.layers.39.mlp.gate",
|
| 426 |
+
"model.language_model.layers.39.mlp.shared_expert_gate",
|
| 427 |
+
"model.language_model.layers.39.post_attention_layernorm",
|
| 428 |
+
"model.language_model.layers.39.self_attn.k_norm",
|
| 429 |
+
"model.language_model.layers.39.self_attn.q_norm",
|
| 430 |
+
"model.language_model.layers.4.input_layernorm",
|
| 431 |
+
"model.language_model.layers.4.linear_attn.A_log",
|
| 432 |
+
"model.language_model.layers.4.linear_attn.conv1d",
|
| 433 |
+
"model.language_model.layers.4.linear_attn.dt_bias",
|
| 434 |
+
"model.language_model.layers.4.linear_attn.in_proj_a",
|
| 435 |
+
"model.language_model.layers.4.linear_attn.in_proj_b",
|
| 436 |
+
"model.language_model.layers.4.linear_attn.norm",
|
| 437 |
+
"model.language_model.layers.4.mlp.gate",
|
| 438 |
+
"model.language_model.layers.4.mlp.shared_expert_gate",
|
| 439 |
+
"model.language_model.layers.4.post_attention_layernorm",
|
| 440 |
+
"model.language_model.layers.5.input_layernorm",
|
| 441 |
+
"model.language_model.layers.5.linear_attn.A_log",
|
| 442 |
+
"model.language_model.layers.5.linear_attn.conv1d",
|
| 443 |
+
"model.language_model.layers.5.linear_attn.dt_bias",
|
| 444 |
+
"model.language_model.layers.5.linear_attn.in_proj_a",
|
| 445 |
+
"model.language_model.layers.5.linear_attn.in_proj_b",
|
| 446 |
+
"model.language_model.layers.5.linear_attn.norm",
|
| 447 |
+
"model.language_model.layers.5.mlp.gate",
|
| 448 |
+
"model.language_model.layers.5.mlp.shared_expert_gate",
|
| 449 |
+
"model.language_model.layers.5.post_attention_layernorm",
|
| 450 |
+
"model.language_model.layers.6.input_layernorm",
|
| 451 |
+
"model.language_model.layers.6.linear_attn.A_log",
|
| 452 |
+
"model.language_model.layers.6.linear_attn.conv1d",
|
| 453 |
+
"model.language_model.layers.6.linear_attn.dt_bias",
|
| 454 |
+
"model.language_model.layers.6.linear_attn.in_proj_a",
|
| 455 |
+
"model.language_model.layers.6.linear_attn.in_proj_b",
|
| 456 |
+
"model.language_model.layers.6.linear_attn.norm",
|
| 457 |
+
"model.language_model.layers.6.mlp.gate",
|
| 458 |
+
"model.language_model.layers.6.mlp.shared_expert_gate",
|
| 459 |
+
"model.language_model.layers.6.post_attention_layernorm",
|
| 460 |
+
"model.language_model.layers.7.input_layernorm",
|
| 461 |
+
"model.language_model.layers.7.mlp.gate",
|
| 462 |
+
"model.language_model.layers.7.mlp.shared_expert_gate",
|
| 463 |
+
"model.language_model.layers.7.post_attention_layernorm",
|
| 464 |
+
"model.language_model.layers.7.self_attn.k_norm",
|
| 465 |
+
"model.language_model.layers.7.self_attn.q_norm",
|
| 466 |
+
"model.language_model.layers.8.input_layernorm",
|
| 467 |
+
"model.language_model.layers.8.linear_attn.A_log",
|
| 468 |
+
"model.language_model.layers.8.linear_attn.conv1d",
|
| 469 |
+
"model.language_model.layers.8.linear_attn.dt_bias",
|
| 470 |
+
"model.language_model.layers.8.linear_attn.in_proj_a",
|
| 471 |
+
"model.language_model.layers.8.linear_attn.in_proj_b",
|
| 472 |
+
"model.language_model.layers.8.linear_attn.norm",
|
| 473 |
+
"model.language_model.layers.8.mlp.gate",
|
| 474 |
+
"model.language_model.layers.8.mlp.shared_expert_gate",
|
| 475 |
+
"model.language_model.layers.8.post_attention_layernorm",
|
| 476 |
+
"model.language_model.layers.9.input_layernorm",
|
| 477 |
+
"model.language_model.layers.9.linear_attn.A_log",
|
| 478 |
+
"model.language_model.layers.9.linear_attn.conv1d",
|
| 479 |
+
"model.language_model.layers.9.linear_attn.dt_bias",
|
| 480 |
+
"model.language_model.layers.9.linear_attn.in_proj_a",
|
| 481 |
+
"model.language_model.layers.9.linear_attn.in_proj_b",
|
| 482 |
+
"model.language_model.layers.9.linear_attn.norm",
|
| 483 |
+
"model.language_model.layers.9.mlp.gate",
|
| 484 |
+
"model.language_model.layers.9.mlp.shared_expert_gate",
|
| 485 |
+
"model.language_model.layers.9.post_attention_layernorm",
|
| 486 |
+
"model.language_model.norm",
|
| 487 |
+
"model.visual.blocks.0.attn.proj",
|
| 488 |
+
"model.visual.blocks.0.attn.qkv",
|
| 489 |
+
"model.visual.blocks.0.mlp.linear_fc1",
|
| 490 |
+
"model.visual.blocks.0.mlp.linear_fc2",
|
| 491 |
+
"model.visual.blocks.0.norm1",
|
| 492 |
+
"model.visual.blocks.0.norm2",
|
| 493 |
+
"model.visual.blocks.1.attn.proj",
|
| 494 |
+
"model.visual.blocks.1.attn.qkv",
|
| 495 |
+
"model.visual.blocks.1.mlp.linear_fc1",
|
| 496 |
+
"model.visual.blocks.1.mlp.linear_fc2",
|
| 497 |
+
"model.visual.blocks.1.norm1",
|
| 498 |
+
"model.visual.blocks.1.norm2",
|
| 499 |
+
"model.visual.blocks.10.attn.proj",
|
| 500 |
+
"model.visual.blocks.10.attn.qkv",
|
| 501 |
+
"model.visual.blocks.10.mlp.linear_fc1",
|
| 502 |
+
"model.visual.blocks.10.mlp.linear_fc2",
|
| 503 |
+
"model.visual.blocks.10.norm1",
|
| 504 |
+
"model.visual.blocks.10.norm2",
|
| 505 |
+
"model.visual.blocks.11.attn.proj",
|
| 506 |
+
"model.visual.blocks.11.attn.qkv",
|
| 507 |
+
"model.visual.blocks.11.mlp.linear_fc1",
|
| 508 |
+
"model.visual.blocks.11.mlp.linear_fc2",
|
| 509 |
+
"model.visual.blocks.11.norm1",
|
| 510 |
+
"model.visual.blocks.11.norm2",
|
| 511 |
+
"model.visual.blocks.12.attn.proj",
|
| 512 |
+
"model.visual.blocks.12.attn.qkv",
|
| 513 |
+
"model.visual.blocks.12.mlp.linear_fc1",
|
| 514 |
+
"model.visual.blocks.12.mlp.linear_fc2",
|
| 515 |
+
"model.visual.blocks.12.norm1",
|
| 516 |
+
"model.visual.blocks.12.norm2",
|
| 517 |
+
"model.visual.blocks.13.attn.proj",
|
| 518 |
+
"model.visual.blocks.13.attn.qkv",
|
| 519 |
+
"model.visual.blocks.13.mlp.linear_fc1",
|
| 520 |
+
"model.visual.blocks.13.mlp.linear_fc2",
|
| 521 |
+
"model.visual.blocks.13.norm1",
|
| 522 |
+
"model.visual.blocks.13.norm2",
|
| 523 |
+
"model.visual.blocks.14.attn.proj",
|
| 524 |
+
"model.visual.blocks.14.attn.qkv",
|
| 525 |
+
"model.visual.blocks.14.mlp.linear_fc1",
|
| 526 |
+
"model.visual.blocks.14.mlp.linear_fc2",
|
| 527 |
+
"model.visual.blocks.14.norm1",
|
| 528 |
+
"model.visual.blocks.14.norm2",
|
| 529 |
+
"model.visual.blocks.15.attn.proj",
|
| 530 |
+
"model.visual.blocks.15.attn.qkv",
|
| 531 |
+
"model.visual.blocks.15.mlp.linear_fc1",
|
| 532 |
+
"model.visual.blocks.15.mlp.linear_fc2",
|
| 533 |
+
"model.visual.blocks.15.norm1",
|
| 534 |
+
"model.visual.blocks.15.norm2",
|
| 535 |
+
"model.visual.blocks.16.attn.proj",
|
| 536 |
+
"model.visual.blocks.16.attn.qkv",
|
| 537 |
+
"model.visual.blocks.16.mlp.linear_fc1",
|
| 538 |
+
"model.visual.blocks.16.mlp.linear_fc2",
|
| 539 |
+
"model.visual.blocks.16.norm1",
|
| 540 |
+
"model.visual.blocks.16.norm2",
|
| 541 |
+
"model.visual.blocks.17.attn.proj",
|
| 542 |
+
"model.visual.blocks.17.attn.qkv",
|
| 543 |
+
"model.visual.blocks.17.mlp.linear_fc1",
|
| 544 |
+
"model.visual.blocks.17.mlp.linear_fc2",
|
| 545 |
+
"model.visual.blocks.17.norm1",
|
| 546 |
+
"model.visual.blocks.17.norm2",
|
| 547 |
+
"model.visual.blocks.18.attn.proj",
|
| 548 |
+
"model.visual.blocks.18.attn.qkv",
|
| 549 |
+
"model.visual.blocks.18.mlp.linear_fc1",
|
| 550 |
+
"model.visual.blocks.18.mlp.linear_fc2",
|
| 551 |
+
"model.visual.blocks.18.norm1",
|
| 552 |
+
"model.visual.blocks.18.norm2",
|
| 553 |
+
"model.visual.blocks.19.attn.proj",
|
| 554 |
+
"model.visual.blocks.19.attn.qkv",
|
| 555 |
+
"model.visual.blocks.19.mlp.linear_fc1",
|
| 556 |
+
"model.visual.blocks.19.mlp.linear_fc2",
|
| 557 |
+
"model.visual.blocks.19.norm1",
|
| 558 |
+
"model.visual.blocks.19.norm2",
|
| 559 |
+
"model.visual.blocks.2.attn.proj",
|
| 560 |
+
"model.visual.blocks.2.attn.qkv",
|
| 561 |
+
"model.visual.blocks.2.mlp.linear_fc1",
|
| 562 |
+
"model.visual.blocks.2.mlp.linear_fc2",
|
| 563 |
+
"model.visual.blocks.2.norm1",
|
| 564 |
+
"model.visual.blocks.2.norm2",
|
| 565 |
+
"model.visual.blocks.20.attn.proj",
|
| 566 |
+
"model.visual.blocks.20.attn.qkv",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc1",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2",
|
| 569 |
+
"model.visual.blocks.20.norm1",
|
| 570 |
+
"model.visual.blocks.20.norm2",
|
| 571 |
+
"model.visual.blocks.21.attn.proj",
|
| 572 |
+
"model.visual.blocks.21.attn.qkv",
|
| 573 |
+
"model.visual.blocks.21.mlp.linear_fc1",
|
| 574 |
+
"model.visual.blocks.21.mlp.linear_fc2",
|
| 575 |
+
"model.visual.blocks.21.norm1",
|
| 576 |
+
"model.visual.blocks.21.norm2",
|
| 577 |
+
"model.visual.blocks.22.attn.proj",
|
| 578 |
+
"model.visual.blocks.22.attn.qkv",
|
| 579 |
+
"model.visual.blocks.22.mlp.linear_fc1",
|
| 580 |
+
"model.visual.blocks.22.mlp.linear_fc2",
|
| 581 |
+
"model.visual.blocks.22.norm1",
|
| 582 |
+
"model.visual.blocks.22.norm2",
|
| 583 |
+
"model.visual.blocks.23.attn.proj",
|
| 584 |
+
"model.visual.blocks.23.attn.qkv",
|
| 585 |
+
"model.visual.blocks.23.mlp.linear_fc1",
|
| 586 |
+
"model.visual.blocks.23.mlp.linear_fc2",
|
| 587 |
+
"model.visual.blocks.23.norm1",
|
| 588 |
+
"model.visual.blocks.23.norm2",
|
| 589 |
+
"model.visual.blocks.24.attn.proj",
|
| 590 |
+
"model.visual.blocks.24.attn.qkv",
|
| 591 |
+
"model.visual.blocks.24.mlp.linear_fc1",
|
| 592 |
+
"model.visual.blocks.24.mlp.linear_fc2",
|
| 593 |
+
"model.visual.blocks.24.norm1",
|
| 594 |
+
"model.visual.blocks.24.norm2",
|
| 595 |
+
"model.visual.blocks.25.attn.proj",
|
| 596 |
+
"model.visual.blocks.25.attn.qkv",
|
| 597 |
+
"model.visual.blocks.25.mlp.linear_fc1",
|
| 598 |
+
"model.visual.blocks.25.mlp.linear_fc2",
|
| 599 |
+
"model.visual.blocks.25.norm1",
|
| 600 |
+
"model.visual.blocks.25.norm2",
|
| 601 |
+
"model.visual.blocks.26.attn.proj",
|
| 602 |
+
"model.visual.blocks.26.attn.qkv",
|
| 603 |
+
"model.visual.blocks.26.mlp.linear_fc1",
|
| 604 |
+
"model.visual.blocks.26.mlp.linear_fc2",
|
| 605 |
+
"model.visual.blocks.26.norm1",
|
| 606 |
+
"model.visual.blocks.26.norm2",
|
| 607 |
+
"model.visual.blocks.3.attn.proj",
|
| 608 |
+
"model.visual.blocks.3.attn.qkv",
|
| 609 |
+
"model.visual.blocks.3.mlp.linear_fc1",
|
| 610 |
+
"model.visual.blocks.3.mlp.linear_fc2",
|
| 611 |
+
"model.visual.blocks.3.norm1",
|
| 612 |
+
"model.visual.blocks.3.norm2",
|
| 613 |
+
"model.visual.blocks.4.attn.proj",
|
| 614 |
+
"model.visual.blocks.4.attn.qkv",
|
| 615 |
+
"model.visual.blocks.4.mlp.linear_fc1",
|
| 616 |
+
"model.visual.blocks.4.mlp.linear_fc2",
|
| 617 |
+
"model.visual.blocks.4.norm1",
|
| 618 |
+
"model.visual.blocks.4.norm2",
|
| 619 |
+
"model.visual.blocks.5.attn.proj",
|
| 620 |
+
"model.visual.blocks.5.attn.qkv",
|
| 621 |
+
"model.visual.blocks.5.mlp.linear_fc1",
|
| 622 |
+
"model.visual.blocks.5.mlp.linear_fc2",
|
| 623 |
+
"model.visual.blocks.5.norm1",
|
| 624 |
+
"model.visual.blocks.5.norm2",
|
| 625 |
+
"model.visual.blocks.6.attn.proj",
|
| 626 |
+
"model.visual.blocks.6.attn.qkv",
|
| 627 |
+
"model.visual.blocks.6.mlp.linear_fc1",
|
| 628 |
+
"model.visual.blocks.6.mlp.linear_fc2",
|
| 629 |
+
"model.visual.blocks.6.norm1",
|
| 630 |
+
"model.visual.blocks.6.norm2",
|
| 631 |
+
"model.visual.blocks.7.attn.proj",
|
| 632 |
+
"model.visual.blocks.7.attn.qkv",
|
| 633 |
+
"model.visual.blocks.7.mlp.linear_fc1",
|
| 634 |
+
"model.visual.blocks.7.mlp.linear_fc2",
|
| 635 |
+
"model.visual.blocks.7.norm1",
|
| 636 |
+
"model.visual.blocks.7.norm2",
|
| 637 |
+
"model.visual.blocks.8.attn.proj",
|
| 638 |
+
"model.visual.blocks.8.attn.qkv",
|
| 639 |
+
"model.visual.blocks.8.mlp.linear_fc1",
|
| 640 |
+
"model.visual.blocks.8.mlp.linear_fc2",
|
| 641 |
+
"model.visual.blocks.8.norm1",
|
| 642 |
+
"model.visual.blocks.8.norm2",
|
| 643 |
+
"model.visual.blocks.9.attn.proj",
|
| 644 |
+
"model.visual.blocks.9.attn.qkv",
|
| 645 |
+
"model.visual.blocks.9.mlp.linear_fc1",
|
| 646 |
+
"model.visual.blocks.9.mlp.linear_fc2",
|
| 647 |
+
"model.visual.blocks.9.norm1",
|
| 648 |
+
"model.visual.blocks.9.norm2",
|
| 649 |
+
"model.visual.merger.linear_fc1",
|
| 650 |
+
"model.visual.merger.linear_fc2",
|
| 651 |
+
"model.visual.merger.norm",
|
| 652 |
+
"model.visual.patch_embed.proj",
|
| 653 |
+
"model.visual.pos_embed",
|
| 654 |
+
"mtp.fc",
|
| 655 |
+
"mtp.layers.0.input_layernorm",
|
| 656 |
+
"mtp.layers.0.mlp.gate",
|
| 657 |
+
"mtp.layers.0.mlp.shared_expert_gate",
|
| 658 |
+
"mtp.layers.0.post_attention_layernorm",
|
| 659 |
+
"mtp.layers.0.self_attn.k_norm",
|
| 660 |
+
"mtp.layers.0.self_attn.q_norm",
|
| 661 |
+
"mtp.norm",
|
| 662 |
+
"mtp.pre_fc_norm_embedding",
|
| 663 |
+
"mtp.pre_fc_norm_hidden"
|
| 664 |
+
]
|
| 665 |
+
}
|
| 666 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 248044,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.57.0.dev0"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88cb8481c763e04a789b184908c4b811e5ff8f5462d7df2a600437622aafbd5d
|
| 3 |
+
size 2685011328
|
model-00002-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e665ea61c16830c788775768ab13bfcd2c1e085a1bce13c0b171ebe6ff0ee1e7
|
| 3 |
+
size 2685011320
|
model-00003-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:027b8676348cda8e359e00ac699ad4ebda6030629c362d7ebf888d582569d18c
|
| 3 |
+
size 2685011320
|
model-00004-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d7c0b92e8484cdb4bc1200d60bc9e7e0a76805191c7da1086050d7f779d194c
|
| 3 |
+
size 2685011328
|
model-00005-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:599fb808196e0fc32dd3144f3ba67d1c0105f3a5e9d3d6cf7153064306a3d316
|
| 3 |
+
size 2685011328
|
model-00006-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fa81d899dcaf6a7e6f79409f76c813e825ea8484b4e9a17bd0a3cba5e030547
|
| 3 |
+
size 2685011328
|
model-00007-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b590d706862b740886f25e555de88b60818452e2c7aa272242b9bd16173be56
|
| 3 |
+
size 2685011320
|
model-00008-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:488c7d68386a5c5df4e1f6e895b9620e6097d6cf4e756e2c5e0646ae6b1a86d5
|
| 3 |
+
size 2685011320
|
model-00009-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55ea5a09319507cff4a7d331d1a80d7136a345c2e2cbd229941bbbad29bb3466
|
| 3 |
+
size 3645245248
|
model-00010-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ed90ca3d76fd2d93003e94d6f762894db80692fb63fd4270447fbfba89ec244
|
| 3 |
+
size 2685012616
|
model-00011-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d17d0d2dfc9c36bfc569fa683918ef9a2635348370dacebdfc55f72e1e69292
|
| 3 |
+
size 2685012624
|
model-00012-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d103c30863b1e09e5d0da96b3498b6361a849c5aef5b828dc6ae26875724d4e5
|
| 3 |
+
size 2685012624
|
model-00013-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81e850b4ab29a4e53641c9280bbff8f65516affae0ada3437b4a8d08f4a6cea4
|
| 3 |
+
size 2332633512
|
model-00014-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60039bbdead35a4762a059467f5d7611a0b8483ecaa9f32b195328251a5ed4fa
|
| 3 |
+
size 199211096
|
model-00015-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b2e4bdac1a410f8251f7dca1f24bf7495a0d7c9d10f7fba46b3679a96157f41
|
| 3 |
+
size 1747138944
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 apodex_identity = '# Role Definition\\n- Name: Apodex\\n- Developer: Apodex AI\\n- Identity: An AI assistant developed by Apodex AI\\n- Core Principle: Always respond as Apodex and never pretend or claim to be any other AI model\\n- Please interact with the user strictly in the identity of Apodex.' %}\n{%- set identity_mode = identity_mode if identity_mode is defined else 'fallback' %}\n{%- set has_caller_system = (messages and messages[0].role == 'system') %}\n{%- set inject_identity = (identity_mode == 'force') or (identity_mode == 'fallback' and not has_caller_system) %}\n{%- 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 inject_identity %}\n {{- '\\n\\n' + apodex_identity }}\n {%- endif %}\n {%- if has_caller_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 inject_identity or has_caller_system %}\n {{- '<|im_start|>system\\n' }}\n {%- set parts = namespace(first=true) %}\n {%- if inject_identity %}\n {{- apodex_identity }}\n {%- set parts.first = false %}\n {%- endif %}\n {%- if has_caller_system %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {%- if not parts.first %}{{- '\\n\\n' }}{%- endif %}\n {{- content }}\n {%- endif %}\n {%- endif %}\n {{- '<|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 (preserve_thinking is not defined or preserve_thinking is true) or (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 | string if args_value is string else args_value | tojson | safe %}\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
|
|
|