Add verified seed-42 full model and original adapter
Browse files- .gitattributes +2 -0
- LICENSE +49 -0
- LICENSE-OPENJEV +25 -0
- LICENSE-QWEN +202 -0
- README.md +41 -0
- THIRD_PARTY_NOTICES.md +7 -0
- adapter/adapter_config.json +52 -0
- adapter/adapter_model.safetensors +3 -0
- adapter/chat_template.jinja +154 -0
- adapter/tokenizer.json +3 -0
- adapter/tokenizer_config.json +36 -0
- chat_template.jinja +154 -0
- config.json +120 -0
- merge_verification.json +42 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +626 -0
- provenance.json +22 -0
- requirements.txt +3 -0
- score.py +59 -0
- scoring_config.json +9 -0
- tokenizer.json +3 -0
- tokenizer_config.json +36 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* 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
|
|
|
|
|
|
|
|
|
| 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 |
+
adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
SkillScreen — Proprietary / All Rights Reserved
|
| 2 |
+
|
| 3 |
+
Copyright (c) 2026 the respective SkillScreen contributors.
|
| 4 |
+
All rights reserved.
|
| 5 |
+
|
| 6 |
+
Scope
|
| 7 |
+
This notice applies to project-authored code, documentation, figures and
|
| 8 |
+
experiment artifacts only to the extent that they are copyright-protected and
|
| 9 |
+
owned by their respective SkillScreen contributors. Copyright ownership remains
|
| 10 |
+
with the respective rights holders.
|
| 11 |
+
|
| 12 |
+
No public reuse license
|
| 13 |
+
Except for the authorized collaboration below, a separate written permission,
|
| 14 |
+
or rights preserved below, no permission is granted to use, execute, copy,
|
| 15 |
+
modify, create derivative works from, distribute, sublicense or commercialize
|
| 16 |
+
the covered material. Research use and use for AI model training, fine-tuning
|
| 17 |
+
or distillation require prior written permission from the applicable rights
|
| 18 |
+
holders. Public availability does not grant a general reuse license.
|
| 19 |
+
|
| 20 |
+
Authorized project collaboration
|
| 21 |
+
Authorized SkillScreen team members and collaborators may access, execute, copy
|
| 22 |
+
and modify the covered material, including train and evaluate SkillScreen models,
|
| 23 |
+
solely for their work on the SkillScreen project. They may use coding agents acting
|
| 24 |
+
on their behalf for this work. This limited permission does not grant rights for
|
| 25 |
+
independent reuse, external redistribution, commercial licensing or AI model
|
| 26 |
+
training outside the authorized project work, including training an agent
|
| 27 |
+
provider's own models. Separate written permission is required for use beyond
|
| 28 |
+
that project work.
|
| 29 |
+
|
| 30 |
+
Third-party material and separate releases
|
| 31 |
+
Third-party content is excluded from this notice and retains its original
|
| 32 |
+
licenses and attribution requirements; see THIRD_PARTY_NOTICES.md. This notice
|
| 33 |
+
does not restrict rights granted by upstream rights holders. Separately released
|
| 34 |
+
artifacts, including Hugging Face releases, remain subject to the terms stated
|
| 35 |
+
for those releases. Existing separate licenses or permissions are not revoked
|
| 36 |
+
by this notice.
|
| 37 |
+
|
| 38 |
+
Rights preserved
|
| 39 |
+
This notice does not limit rights required by applicable law, including
|
| 40 |
+
statutory exceptions, or rights granted under GitHub's Terms of Service.
|
| 41 |
+
No patent or trademark rights are granted by this notice.
|
| 42 |
+
|
| 43 |
+
Disclaimer
|
| 44 |
+
To the extent permitted by applicable law, the covered material is provided
|
| 45 |
+
"AS IS", without warranties of any kind, and the rights holders disclaim
|
| 46 |
+
liability arising from its use.
|
| 47 |
+
|
| 48 |
+
For permissions beyond authorized project collaboration, contact the repository
|
| 49 |
+
owner to obtain permission from the applicable rights holders.
|
LICENSE-OPENJEV
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
OpenJev attribution
|
| 2 |
+
|
| 3 |
+
AlexWortega/openjev is designated MIT by the upstream model card.
|
| 4 |
+
Source revision a20448012c213128955ca0c693e7c943865cab77.
|
| 5 |
+
https://huggingface.co/AlexWortega/openjev
|
| 6 |
+
|
| 7 |
+
MIT License
|
| 8 |
+
|
| 9 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
| 10 |
+
of this software and associated documentation files (the "Software"), to deal
|
| 11 |
+
in the Software without restriction, including without limitation the rights
|
| 12 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
| 13 |
+
copies of the Software, and to permit persons to whom the Software is
|
| 14 |
+
furnished to do so, subject to the following conditions:
|
| 15 |
+
|
| 16 |
+
The above copyright notice and this permission notice shall be included in
|
| 17 |
+
all copies or substantial portions of the Software.
|
| 18 |
+
|
| 19 |
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
| 20 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
| 21 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
| 22 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
| 23 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
| 24 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
| 25 |
+
THE SOFTWARE.
|
LICENSE-QWEN
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 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
pipeline_tag: text-classification
|
| 4 |
+
license: other
|
| 5 |
+
license_name: skillscreen-proprietary
|
| 6 |
+
license_link: LICENSE
|
| 7 |
+
base_model: AlexWortega/openjev
|
| 8 |
+
datasets:
|
| 9 |
+
- ProtectSkills/MaliciousSkillBench
|
| 10 |
+
tags:
|
| 11 |
+
- skillscreen
|
| 12 |
+
- agent-security
|
| 13 |
+
- nli
|
| 14 |
+
- sd
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# SkillScreen-2B-SD
|
| 18 |
+
|
| 19 |
+
SkillScreen scores malicious agent skills directly from `SKILL.md` in one forward pass. This checkpoint uses the Source-Disjoint (SD) training split and an 8,192-token input budget.
|
| 20 |
+
|
| 21 |
+
Fine-tuned from [OpenJev 2B](https://huggingface.co/AlexWortega/openjev/tree/a20448012c213128955ca0c693e7c943865cab77/qwen3.5-2b-nli-v5) with LoRA and a trained classification head. Seed 42, one epoch, checkpoint 470. Full merged weights are at the root. The original adapter and trained head are in `adapter/`.
|
| 22 |
+
|
| 23 |
+
## Use
|
| 24 |
+
|
| 25 |
+
CUDA with BF16 support.
|
| 26 |
+
|
| 27 |
+
```bash
|
| 28 |
+
pip install torch==2.11.0 transformers==5.17.0 huggingface_hub==1.33.0
|
| 29 |
+
hf download SkillScreen/SkillScreen-2B-SD --local-dir skillscreen
|
| 30 |
+
python skillscreen/score.py path/to/SKILL.md
|
| 31 |
+
```
|
| 32 |
+
|
| 33 |
+
The score is the native entailment probability. A score **≥ 0.5** is flagged as suspicious. The fixed hypothesis is `This AI agent skill is malicious.` Inputs preserve the premise prefix and the complete hypothesis.
|
| 34 |
+
|
| 35 |
+
[Project page](https://jerroldh.github.io/SkillScreen-webpage/) · [Code](https://github.com/JerroldH/SkillScreen)
|
| 36 |
+
|
| 37 |
+
This release contains one checkpoint. Paper aggregate results cover five training seeds. Scores are uncalibrated, and a low score does not certify a package as safe. See `provenance.json` and `merge_verification.json` for the checkpoint and export checks.
|
| 38 |
+
|
| 39 |
+
Authors: Jerrold Huang, Junwei Quan, Saiyue Lyu, Zihan Guo, Yingqiang Ge.
|
| 40 |
+
|
| 41 |
+
SkillScreen-authored material is subject to `LICENSE`. Upstream rights and notices remain applicable.
|
THIRD_PARTY_NOTICES.md
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Third-party notices
|
| 2 |
+
|
| 3 |
+
SkillScreen-authored material is subject to LICENSE. Upstream rights remain applicable.
|
| 4 |
+
|
| 5 |
+
Base model [OpenJev](https://huggingface.co/AlexWortega/openjev/tree/a20448012c213128955ca0c693e7c943865cab77) is designated MIT by its model card. It derives from [Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B), licensed Apache-2.0. Upstream notices are included in LICENSE-OPENJEV and LICENSE-QWEN.
|
| 6 |
+
|
| 7 |
+
Training benchmark [MaliciousSkillBench](https://huggingface.co/datasets/ProtectSkills/MaliciousSkillBench/tree/d4b42ce5766a6e0359c987cf59c1007cb3795a90), Yue Wang et al. Benchmark metadata and splits are CC BY 4.0. Skill texts and packages retain upstream terms. No training texts or packages are distributed here.
|
adapter/adapter_config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "AlexWortega/openjev",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"kasa_config": null,
|
| 16 |
+
"layer_replication": null,
|
| 17 |
+
"layers_pattern": null,
|
| 18 |
+
"layers_to_transform": null,
|
| 19 |
+
"loftq_config": {},
|
| 20 |
+
"lora_alpha": 16,
|
| 21 |
+
"lora_bias": false,
|
| 22 |
+
"lora_dropout": 0.0,
|
| 23 |
+
"lora_ga_config": null,
|
| 24 |
+
"megatron_config": null,
|
| 25 |
+
"megatron_core": "megatron.core",
|
| 26 |
+
"modules_to_save": [
|
| 27 |
+
"score",
|
| 28 |
+
"classifier",
|
| 29 |
+
"score"
|
| 30 |
+
],
|
| 31 |
+
"monteclora_config": null,
|
| 32 |
+
"peft_type": "LORA",
|
| 33 |
+
"peft_version": "0.21.2",
|
| 34 |
+
"qalora_group_size": 16,
|
| 35 |
+
"r": 8,
|
| 36 |
+
"rank_pattern": {},
|
| 37 |
+
"revision": "a20448012c213128955ca0c693e7c943865cab77",
|
| 38 |
+
"target_modules": [
|
| 39 |
+
"v_proj",
|
| 40 |
+
"in_proj_qkv",
|
| 41 |
+
"q_proj",
|
| 42 |
+
"out_proj"
|
| 43 |
+
],
|
| 44 |
+
"target_parameters": null,
|
| 45 |
+
"task_type": "SEQ_CLS",
|
| 46 |
+
"trainable_token_indices": null,
|
| 47 |
+
"use_bdlora": null,
|
| 48 |
+
"use_dora": false,
|
| 49 |
+
"use_qalora": false,
|
| 50 |
+
"use_rslora": false,
|
| 51 |
+
"velora_config": null
|
| 52 |
+
}
|
adapter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:460ec55409b309babfc78323c4cc6852a57492260484dca58a2120934853da36
|
| 3 |
+
size 8775920
|
adapter/chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is true %}
|
| 150 |
+
{{- '<think>\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
adapter/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f399b3cd12fa270d51457bb749fb30863521e8359b8a27059c71b6c2f7d6dd6c
|
| 3 |
+
size 19989424
|
adapter/tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": true,
|
| 14 |
+
"max_length": 1024,
|
| 15 |
+
"model_max_length": 262144,
|
| 16 |
+
"model_specific_special_tokens": {
|
| 17 |
+
"audio_bos_token": "<|audio_start|>",
|
| 18 |
+
"audio_eos_token": "<|audio_end|>",
|
| 19 |
+
"audio_token": "<|audio_pad|>",
|
| 20 |
+
"image_token": "<|image_pad|>",
|
| 21 |
+
"video_token": "<|video_pad|>",
|
| 22 |
+
"vision_bos_token": "<|vision_start|>",
|
| 23 |
+
"vision_eos_token": "<|vision_end|>"
|
| 24 |
+
},
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"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+",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"stride": 0,
|
| 29 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 30 |
+
"truncation_side": "right",
|
| 31 |
+
"truncation_strategy": "longest_first",
|
| 32 |
+
"unk_token": null,
|
| 33 |
+
"video_token": "<|video_pad|>",
|
| 34 |
+
"vision_bos_token": "<|vision_start|>",
|
| 35 |
+
"vision_eos_token": "<|vision_end|>"
|
| 36 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is true %}
|
| 150 |
+
{{- '<think>\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"id2label": {
|
| 7 |
+
"0": "contradiction",
|
| 8 |
+
"1": "entailment",
|
| 9 |
+
"2": "neutral"
|
| 10 |
+
},
|
| 11 |
+
"image_token_id": 248056,
|
| 12 |
+
"label2id": {
|
| 13 |
+
"contradiction": 0,
|
| 14 |
+
"entailment": 1,
|
| 15 |
+
"neutral": 2
|
| 16 |
+
},
|
| 17 |
+
"model_type": "qwen3_5",
|
| 18 |
+
"nli_template": "Premise: {premise}\nHypothesis: {hypothesis}",
|
| 19 |
+
"pad_token_id": 248044,
|
| 20 |
+
"problem_type": "single_label_classification",
|
| 21 |
+
"text_config": {
|
| 22 |
+
"_name_or_path": "SkillScreen/SkillScreen-2B-SD",
|
| 23 |
+
"attention_bias": false,
|
| 24 |
+
"attention_dropout": 0.0,
|
| 25 |
+
"attn_output_gate": true,
|
| 26 |
+
"bos_token_id": null,
|
| 27 |
+
"dtype": "bfloat16",
|
| 28 |
+
"eos_token_id": 248044,
|
| 29 |
+
"full_attention_interval": 4,
|
| 30 |
+
"head_dim": 256,
|
| 31 |
+
"hidden_act": "silu",
|
| 32 |
+
"hidden_size": 2048,
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 6144,
|
| 35 |
+
"layer_types": [
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"full_attention"
|
| 60 |
+
],
|
| 61 |
+
"linear_conv_kernel_dim": 4,
|
| 62 |
+
"linear_key_head_dim": 128,
|
| 63 |
+
"linear_num_key_heads": 16,
|
| 64 |
+
"linear_num_value_heads": 16,
|
| 65 |
+
"linear_value_head_dim": 128,
|
| 66 |
+
"mamba_ssm_dtype": "float32",
|
| 67 |
+
"max_position_embeddings": 262144,
|
| 68 |
+
"mlp_only_layers": [],
|
| 69 |
+
"model_type": "qwen3_5_text",
|
| 70 |
+
"mtp_num_hidden_layers": 1,
|
| 71 |
+
"mtp_use_dedicated_embeddings": false,
|
| 72 |
+
"num_attention_heads": 8,
|
| 73 |
+
"num_hidden_layers": 24,
|
| 74 |
+
"num_key_value_heads": 2,
|
| 75 |
+
"pad_token_id": 248044,
|
| 76 |
+
"partial_rotary_factor": 0.25,
|
| 77 |
+
"rms_norm_eps": 1e-06,
|
| 78 |
+
"rope_parameters": {
|
| 79 |
+
"mrope_interleaved": true,
|
| 80 |
+
"mrope_section": [
|
| 81 |
+
11,
|
| 82 |
+
11,
|
| 83 |
+
10
|
| 84 |
+
],
|
| 85 |
+
"partial_rotary_factor": 0.25,
|
| 86 |
+
"rope_theta": 10000000,
|
| 87 |
+
"rope_type": "default"
|
| 88 |
+
},
|
| 89 |
+
"tie_word_embeddings": true,
|
| 90 |
+
"use_cache": false,
|
| 91 |
+
"vocab_size": 248320
|
| 92 |
+
},
|
| 93 |
+
"tie_word_embeddings": true,
|
| 94 |
+
"transformers_version": "5.17.0",
|
| 95 |
+
"use_cache": false,
|
| 96 |
+
"video_token_id": 248057,
|
| 97 |
+
"vision_config": {
|
| 98 |
+
"deepstack_visual_indexes": [],
|
| 99 |
+
"depth": 24,
|
| 100 |
+
"dtype": "bfloat16",
|
| 101 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 102 |
+
"hidden_size": 1024,
|
| 103 |
+
"in_channels": 3,
|
| 104 |
+
"initializer_range": 0.02,
|
| 105 |
+
"intermediate_size": 4096,
|
| 106 |
+
"model_type": "qwen3_5_vision",
|
| 107 |
+
"num_heads": 16,
|
| 108 |
+
"num_position_embeddings": 2304,
|
| 109 |
+
"out_hidden_size": 2048,
|
| 110 |
+
"patch_size": 16,
|
| 111 |
+
"rope_parameters": {
|
| 112 |
+
"rope_theta": 10000.0,
|
| 113 |
+
"rope_type": "axial"
|
| 114 |
+
},
|
| 115 |
+
"spatial_merge_size": 2,
|
| 116 |
+
"temporal_patch_size": 2
|
| 117 |
+
},
|
| 118 |
+
"vision_end_token_id": 248054,
|
| 119 |
+
"vision_start_token_id": 248053
|
| 120 |
+
}
|
merge_verification.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"passed": true,
|
| 3 |
+
"run_id": "direct-sd-s42",
|
| 4 |
+
"seed": 42,
|
| 5 |
+
"selected_update": 470,
|
| 6 |
+
"precision": "bfloat16",
|
| 7 |
+
"threshold": 0.5,
|
| 8 |
+
"validation_records": 833,
|
| 9 |
+
"longest_validation_tokens": 8192,
|
| 10 |
+
"original_adapter_replay_max_logit_difference": 0.0625,
|
| 11 |
+
"original_adapter_replay_max_probability_difference": 0.007315270195471513,
|
| 12 |
+
"original_adapter_replay_decision_differences_at_0_5": 0,
|
| 13 |
+
"fresh_native_reload_max_logit_difference": 0.0,
|
| 14 |
+
"trained_classification_head_preserved": true,
|
| 15 |
+
"merge_max_logit_difference": 0.1875,
|
| 16 |
+
"merge_max_probability_difference": 0.05210707294269523,
|
| 17 |
+
"decision_differences_at_0_5": 0,
|
| 18 |
+
"adapter_validation_at_0_5": {
|
| 19 |
+
"tp": 649,
|
| 20 |
+
"fn": 15,
|
| 21 |
+
"fp": 6,
|
| 22 |
+
"tn": 163,
|
| 23 |
+
"recall": 0.9774096385542169,
|
| 24 |
+
"fpr": 0.03550295857988166
|
| 25 |
+
},
|
| 26 |
+
"merged_validation_at_0_5": {
|
| 27 |
+
"tp": 649,
|
| 28 |
+
"fn": 15,
|
| 29 |
+
"fp": 6,
|
| 30 |
+
"tn": 163,
|
| 31 |
+
"recall": 0.9774096385542169,
|
| 32 |
+
"fpr": 0.03550295857988166
|
| 33 |
+
},
|
| 34 |
+
"peak_gpu_allocated_gib": 5.09755802154541,
|
| 35 |
+
"peak_gpu_reserved_gib": 5.21875,
|
| 36 |
+
"seconds": 126.86285077797947,
|
| 37 |
+
"public_scoring_helper": {
|
| 38 |
+
"passed": true,
|
| 39 |
+
"probability_difference": 0.0,
|
| 40 |
+
"used_tokens": 514
|
| 41 |
+
}
|
| 42 |
+
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce15bffa1f0ca0d507bd44a06160d7dc89f298a9c01943650c8be5c18ecc6230
|
| 3 |
+
size 1999936744
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac5ebb2ff22e583b0cc6dfe9b37dd1d93d6df7305e72d6a8df936ba4bfff30cf
|
| 3 |
+
size 1998904824
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:477fa2471f7532c87f7c60886b4fa6102978c0732375de9a718334e177c0353c
|
| 3 |
+
size 427728976
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,626 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 2213247808,
|
| 4 |
+
"total_size": 4426495616
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 157 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 168 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 177 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 180 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 181 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 219 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 222 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 223 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 224 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 235 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 236 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 237 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 238 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 239 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 240 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 241 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 242 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 243 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 244 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 245 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 246 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 247 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 248 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 249 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 250 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 251 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 252 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 253 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 254 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 255 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 256 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 257 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 258 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 259 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 260 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 261 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 262 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 263 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 273 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 274 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 275 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 276 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 277 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 278 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 279 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 280 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 281 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 282 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 283 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 284 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 285 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 297 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 298 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 299 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 300 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 301 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 302 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 303 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 304 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 305 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 306 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 307 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 308 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 309 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 310 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 311 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 312 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 313 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 314 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 315 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 316 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 317 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 318 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 319 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 320 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.language_model.norm.weight": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 332 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 333 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 334 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 335 |
+
"model.visual.blocks.0.norm1.bias": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.visual.blocks.0.norm1.weight": "model-00002-of-00003.safetensors",
|
| 337 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00003.safetensors",
|
| 339 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 340 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 341 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 342 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 343 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 344 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 347 |
+
"model.visual.blocks.1.norm1.bias": "model-00002-of-00003.safetensors",
|
| 348 |
+
"model.visual.blocks.1.norm1.weight": "model-00002-of-00003.safetensors",
|
| 349 |
+
"model.visual.blocks.1.norm2.bias": "model-00002-of-00003.safetensors",
|
| 350 |
+
"model.visual.blocks.1.norm2.weight": "model-00002-of-00003.safetensors",
|
| 351 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.visual.blocks.10.norm1.bias": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.visual.blocks.10.norm1.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.visual.blocks.10.norm2.bias": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.visual.blocks.10.norm2.weight": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.visual.blocks.11.norm1.bias": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.visual.blocks.11.norm1.weight": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.visual.blocks.11.norm2.bias": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.visual.blocks.11.norm2.weight": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.visual.blocks.12.norm1.bias": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.visual.blocks.12.norm1.weight": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.visual.blocks.12.norm2.bias": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.visual.blocks.12.norm2.weight": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.visual.blocks.13.norm1.bias": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.visual.blocks.13.norm1.weight": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.visual.blocks.13.norm2.bias": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.visual.blocks.13.norm2.weight": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 406 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 407 |
+
"model.visual.blocks.14.norm1.bias": "model-00003-of-00003.safetensors",
|
| 408 |
+
"model.visual.blocks.14.norm1.weight": "model-00003-of-00003.safetensors",
|
| 409 |
+
"model.visual.blocks.14.norm2.bias": "model-00003-of-00003.safetensors",
|
| 410 |
+
"model.visual.blocks.14.norm2.weight": "model-00003-of-00003.safetensors",
|
| 411 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 412 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 413 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 414 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 415 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 416 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 417 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 418 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 419 |
+
"model.visual.blocks.15.norm1.bias": "model-00003-of-00003.safetensors",
|
| 420 |
+
"model.visual.blocks.15.norm1.weight": "model-00003-of-00003.safetensors",
|
| 421 |
+
"model.visual.blocks.15.norm2.bias": "model-00003-of-00003.safetensors",
|
| 422 |
+
"model.visual.blocks.15.norm2.weight": "model-00003-of-00003.safetensors",
|
| 423 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.visual.blocks.16.norm1.bias": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.visual.blocks.16.norm1.weight": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.visual.blocks.16.norm2.bias": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.visual.blocks.16.norm2.weight": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.visual.blocks.17.norm1.bias": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.visual.blocks.17.norm1.weight": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.visual.blocks.17.norm2.bias": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.visual.blocks.17.norm2.weight": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 451 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 452 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 453 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 454 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 455 |
+
"model.visual.blocks.18.norm1.bias": "model-00003-of-00003.safetensors",
|
| 456 |
+
"model.visual.blocks.18.norm1.weight": "model-00003-of-00003.safetensors",
|
| 457 |
+
"model.visual.blocks.18.norm2.bias": "model-00003-of-00003.safetensors",
|
| 458 |
+
"model.visual.blocks.18.norm2.weight": "model-00003-of-00003.safetensors",
|
| 459 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 460 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 461 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 462 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 463 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 464 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 465 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 466 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 467 |
+
"model.visual.blocks.19.norm1.bias": "model-00003-of-00003.safetensors",
|
| 468 |
+
"model.visual.blocks.19.norm1.weight": "model-00003-of-00003.safetensors",
|
| 469 |
+
"model.visual.blocks.19.norm2.bias": "model-00003-of-00003.safetensors",
|
| 470 |
+
"model.visual.blocks.19.norm2.weight": "model-00003-of-00003.safetensors",
|
| 471 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 472 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 473 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 474 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 475 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 476 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 477 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 478 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 479 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00003.safetensors",
|
| 480 |
+
"model.visual.blocks.2.norm1.weight": "model-00002-of-00003.safetensors",
|
| 481 |
+
"model.visual.blocks.2.norm2.bias": "model-00002-of-00003.safetensors",
|
| 482 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00003.safetensors",
|
| 483 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 484 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 485 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 486 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 487 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 488 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 489 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 490 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 491 |
+
"model.visual.blocks.20.norm1.bias": "model-00003-of-00003.safetensors",
|
| 492 |
+
"model.visual.blocks.20.norm1.weight": "model-00003-of-00003.safetensors",
|
| 493 |
+
"model.visual.blocks.20.norm2.bias": "model-00003-of-00003.safetensors",
|
| 494 |
+
"model.visual.blocks.20.norm2.weight": "model-00003-of-00003.safetensors",
|
| 495 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 496 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 497 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 498 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 499 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 500 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 501 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 502 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 503 |
+
"model.visual.blocks.21.norm1.bias": "model-00003-of-00003.safetensors",
|
| 504 |
+
"model.visual.blocks.21.norm1.weight": "model-00003-of-00003.safetensors",
|
| 505 |
+
"model.visual.blocks.21.norm2.bias": "model-00003-of-00003.safetensors",
|
| 506 |
+
"model.visual.blocks.21.norm2.weight": "model-00003-of-00003.safetensors",
|
| 507 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 508 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 509 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 510 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 511 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 512 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 513 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 514 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 515 |
+
"model.visual.blocks.22.norm1.bias": "model-00003-of-00003.safetensors",
|
| 516 |
+
"model.visual.blocks.22.norm1.weight": "model-00003-of-00003.safetensors",
|
| 517 |
+
"model.visual.blocks.22.norm2.bias": "model-00003-of-00003.safetensors",
|
| 518 |
+
"model.visual.blocks.22.norm2.weight": "model-00003-of-00003.safetensors",
|
| 519 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00003-of-00003.safetensors",
|
| 520 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00003-of-00003.safetensors",
|
| 521 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00003-of-00003.safetensors",
|
| 522 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00003-of-00003.safetensors",
|
| 523 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 524 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 525 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 526 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 527 |
+
"model.visual.blocks.23.norm1.bias": "model-00003-of-00003.safetensors",
|
| 528 |
+
"model.visual.blocks.23.norm1.weight": "model-00003-of-00003.safetensors",
|
| 529 |
+
"model.visual.blocks.23.norm2.bias": "model-00003-of-00003.safetensors",
|
| 530 |
+
"model.visual.blocks.23.norm2.weight": "model-00003-of-00003.safetensors",
|
| 531 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 532 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 533 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 534 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 535 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 536 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 537 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 538 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 539 |
+
"model.visual.blocks.3.norm1.bias": "model-00002-of-00003.safetensors",
|
| 540 |
+
"model.visual.blocks.3.norm1.weight": "model-00002-of-00003.safetensors",
|
| 541 |
+
"model.visual.blocks.3.norm2.bias": "model-00002-of-00003.safetensors",
|
| 542 |
+
"model.visual.blocks.3.norm2.weight": "model-00002-of-00003.safetensors",
|
| 543 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 544 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 545 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 546 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 547 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 548 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 549 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 550 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 551 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00003.safetensors",
|
| 552 |
+
"model.visual.blocks.4.norm1.weight": "model-00002-of-00003.safetensors",
|
| 553 |
+
"model.visual.blocks.4.norm2.bias": "model-00002-of-00003.safetensors",
|
| 554 |
+
"model.visual.blocks.4.norm2.weight": "model-00002-of-00003.safetensors",
|
| 555 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 556 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 557 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 558 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 559 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 560 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 561 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 562 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 563 |
+
"model.visual.blocks.5.norm1.bias": "model-00002-of-00003.safetensors",
|
| 564 |
+
"model.visual.blocks.5.norm1.weight": "model-00002-of-00003.safetensors",
|
| 565 |
+
"model.visual.blocks.5.norm2.bias": "model-00002-of-00003.safetensors",
|
| 566 |
+
"model.visual.blocks.5.norm2.weight": "model-00002-of-00003.safetensors",
|
| 567 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 568 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 569 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 570 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 571 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 572 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 573 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 574 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 575 |
+
"model.visual.blocks.6.norm1.bias": "model-00002-of-00003.safetensors",
|
| 576 |
+
"model.visual.blocks.6.norm1.weight": "model-00002-of-00003.safetensors",
|
| 577 |
+
"model.visual.blocks.6.norm2.bias": "model-00002-of-00003.safetensors",
|
| 578 |
+
"model.visual.blocks.6.norm2.weight": "model-00002-of-00003.safetensors",
|
| 579 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 580 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 581 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 582 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 583 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 584 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 585 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 586 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 587 |
+
"model.visual.blocks.7.norm1.bias": "model-00002-of-00003.safetensors",
|
| 588 |
+
"model.visual.blocks.7.norm1.weight": "model-00002-of-00003.safetensors",
|
| 589 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00003.safetensors",
|
| 590 |
+
"model.visual.blocks.7.norm2.weight": "model-00002-of-00003.safetensors",
|
| 591 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 592 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 593 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 594 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 595 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 596 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00003.safetensors",
|
| 597 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00003.safetensors",
|
| 598 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00003.safetensors",
|
| 599 |
+
"model.visual.blocks.8.norm1.bias": "model-00002-of-00003.safetensors",
|
| 600 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00003.safetensors",
|
| 601 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00003.safetensors",
|
| 602 |
+
"model.visual.blocks.8.norm2.weight": "model-00002-of-00003.safetensors",
|
| 603 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00002-of-00003.safetensors",
|
| 604 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00003.safetensors",
|
| 605 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00003.safetensors",
|
| 606 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00003.safetensors",
|
| 607 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00003.safetensors",
|
| 608 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 609 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 610 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 611 |
+
"model.visual.blocks.9.norm1.bias": "model-00003-of-00003.safetensors",
|
| 612 |
+
"model.visual.blocks.9.norm1.weight": "model-00003-of-00003.safetensors",
|
| 613 |
+
"model.visual.blocks.9.norm2.bias": "model-00003-of-00003.safetensors",
|
| 614 |
+
"model.visual.blocks.9.norm2.weight": "model-00003-of-00003.safetensors",
|
| 615 |
+
"model.visual.merger.linear_fc1.bias": "model-00003-of-00003.safetensors",
|
| 616 |
+
"model.visual.merger.linear_fc1.weight": "model-00003-of-00003.safetensors",
|
| 617 |
+
"model.visual.merger.linear_fc2.bias": "model-00003-of-00003.safetensors",
|
| 618 |
+
"model.visual.merger.linear_fc2.weight": "model-00003-of-00003.safetensors",
|
| 619 |
+
"model.visual.merger.norm.bias": "model-00003-of-00003.safetensors",
|
| 620 |
+
"model.visual.merger.norm.weight": "model-00003-of-00003.safetensors",
|
| 621 |
+
"model.visual.patch_embed.proj.bias": "model-00003-of-00003.safetensors",
|
| 622 |
+
"model.visual.patch_embed.proj.weight": "model-00003-of-00003.safetensors",
|
| 623 |
+
"model.visual.pos_embed.weight": "model-00003-of-00003.safetensors",
|
| 624 |
+
"score.weight": "model-00003-of-00003.safetensors"
|
| 625 |
+
}
|
| 626 |
+
}
|
provenance.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"run_id": "direct-sd-s42",
|
| 3 |
+
"seed": 42,
|
| 4 |
+
"selected_update": 470,
|
| 5 |
+
"base_model": {
|
| 6 |
+
"repo_id": "AlexWortega/openjev",
|
| 7 |
+
"subfolder": "qwen3.5-2b-nli-v5",
|
| 8 |
+
"revision": "a20448012c213128955ca0c693e7c943865cab77"
|
| 9 |
+
},
|
| 10 |
+
"dataset": {
|
| 11 |
+
"repo_id": "ProtectSkills/MaliciousSkillBench",
|
| 12 |
+
"revision": "d4b42ce5766a6e0359c987cf59c1007cb3795a90",
|
| 13 |
+
"config": "primary",
|
| 14 |
+
"protocol": "source_disjoint"
|
| 15 |
+
},
|
| 16 |
+
"input": {
|
| 17 |
+
"scope": "SKILL.md only",
|
| 18 |
+
"hypothesis": "This AI agent skill is malicious.",
|
| 19 |
+
"max_length": 8192
|
| 20 |
+
},
|
| 21 |
+
"original_adapter_sha256": "460ec55409b309babfc78323c4cc6852a57492260484dca58a2120934853da36"
|
| 22 |
+
}
|
requirements.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch==2.11.0
|
| 2 |
+
transformers==5.17.0
|
| 3 |
+
huggingface_hub==1.33.0
|
score.py
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Score inert skill text with SkillScreen. Default decision threshold is 0.5."""
|
| 2 |
+
import argparse
|
| 3 |
+
import json
|
| 4 |
+
from pathlib import Path
|
| 5 |
+
|
| 6 |
+
import torch
|
| 7 |
+
from huggingface_hub import hf_hub_download
|
| 8 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
def main():
|
| 12 |
+
parser = argparse.ArgumentParser(description=__doc__)
|
| 13 |
+
parser.add_argument('skill', type=Path, help='SKILL.md, or package JSON for the Package model')
|
| 14 |
+
parser.add_argument('--model', default=str(Path(__file__).resolve().parent))
|
| 15 |
+
parser.add_argument('--revision', default='main')
|
| 16 |
+
args = parser.parse_args()
|
| 17 |
+
if not torch.cuda.is_available():
|
| 18 |
+
raise RuntimeError('This verified recipe requires CUDA with BF16 support')
|
| 19 |
+
local = Path(args.model).is_dir()
|
| 20 |
+
path = Path(args.model) / 'scoring_config.json' if local else Path(
|
| 21 |
+
hf_hub_download(args.model, 'scoring_config.json', revision=args.revision))
|
| 22 |
+
settings = json.loads(path.read_text())
|
| 23 |
+
options = {'local_files_only': True} if local else {'revision':args.revision}
|
| 24 |
+
tokenizer = AutoTokenizer.from_pretrained(args.model, trust_remote_code=False, **options)
|
| 25 |
+
assert tokenizer.num_special_tokens_to_add(False) == 0
|
| 26 |
+
if settings['input']['scope'] == 'SKILL.md + related file contents':
|
| 27 |
+
from package_inputs import encode_package
|
| 28 |
+
row = json.loads(args.skill.read_text(encoding='utf-8'))
|
| 29 |
+
ids, original, _ = encode_package(tokenizer, row,
|
| 30 |
+
settings['input']['hypothesis'], settings['input']['max_length'])
|
| 31 |
+
else:
|
| 32 |
+
text = args.skill.read_text(encoding='utf-8')
|
| 33 |
+
if len(text) > 262144:
|
| 34 |
+
raise ValueError('For inputs above 262,144 characters, use the research pipeline bounded encoder')
|
| 35 |
+
suffix = '\nHypothesis: ' + settings['input']['hypothesis']
|
| 36 |
+
suffix_ids = tokenizer.encode(suffix, add_special_tokens=False)
|
| 37 |
+
ids = tokenizer.encode('Premise: ' + text + suffix, add_special_tokens=False)
|
| 38 |
+
original = len(ids)
|
| 39 |
+
limit = settings['input']['max_length']
|
| 40 |
+
if original > limit:
|
| 41 |
+
ids = ids[:limit - len(suffix_ids)] + suffix_ids
|
| 42 |
+
model = AutoModelForSequenceClassification.from_pretrained(args.model,
|
| 43 |
+
dtype=torch.bfloat16, attn_implementation='sdpa', trust_remote_code=False, **options)
|
| 44 |
+
assert model.config.label2id == {'contradiction':0,'entailment':1,'neutral':2}
|
| 45 |
+
tokenizer.pad_token_id = model.config.pad_token_id
|
| 46 |
+
model.config.use_cache = model.config.text_config.use_cache = False
|
| 47 |
+
model = model.cuda().eval()
|
| 48 |
+
inputs = torch.tensor([ids], dtype=torch.long, device='cuda')
|
| 49 |
+
with torch.inference_mode(), torch.autocast('cuda', dtype=torch.bfloat16):
|
| 50 |
+
logits = model(input_ids=inputs, attention_mask=torch.ones_like(inputs)).logits[0].float().double()
|
| 51 |
+
if not torch.isfinite(logits).all():
|
| 52 |
+
raise ValueError('Nonfinite model score')
|
| 53 |
+
probability = logits.softmax(-1)[1].item()
|
| 54 |
+
print(json.dumps({'malicious_probability':probability,'suspicious':probability >= 0.5,
|
| 55 |
+
'truncated':original > settings['input']['max_length']}, indent=2))
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
if __name__ == '__main__':
|
| 59 |
+
main()
|
scoring_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"input": {
|
| 3 |
+
"scope": "SKILL.md only",
|
| 4 |
+
"hypothesis": "This AI agent skill is malicious.",
|
| 5 |
+
"max_length": 8192
|
| 6 |
+
},
|
| 7 |
+
"score": "native entailment softmax",
|
| 8 |
+
"decision_threshold": 0.5
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f399b3cd12fa270d51457bb749fb30863521e8359b8a27059c71b6c2f7d6dd6c
|
| 3 |
+
size 19989424
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": true,
|
| 14 |
+
"max_length": 1024,
|
| 15 |
+
"model_max_length": 262144,
|
| 16 |
+
"model_specific_special_tokens": {
|
| 17 |
+
"audio_bos_token": "<|audio_start|>",
|
| 18 |
+
"audio_eos_token": "<|audio_end|>",
|
| 19 |
+
"audio_token": "<|audio_pad|>",
|
| 20 |
+
"image_token": "<|image_pad|>",
|
| 21 |
+
"video_token": "<|video_pad|>",
|
| 22 |
+
"vision_bos_token": "<|vision_start|>",
|
| 23 |
+
"vision_eos_token": "<|vision_end|>"
|
| 24 |
+
},
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"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+",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"stride": 0,
|
| 29 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 30 |
+
"truncation_side": "right",
|
| 31 |
+
"truncation_strategy": "longest_first",
|
| 32 |
+
"unk_token": null,
|
| 33 |
+
"video_token": "<|video_pad|>",
|
| 34 |
+
"vision_bos_token": "<|vision_start|>",
|
| 35 |
+
"vision_eos_token": "<|vision_end|>"
|
| 36 |
+
}
|