Add files using upload-large-folder tool
Browse files- .gitattributes +5 -32
- LICENSE +202 -0
- README.md +125 -0
- added_tokens.json +28 -0
- captioncase_01.png +3 -0
- chat_template.jinja +120 -0
- config.json +66 -0
- generation_config.json +11 -0
- inference.py +166 -0
- inference_config.json +17 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +758 -0
- preprocessor_config.json +39 -0
- requirements.txt +5 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- video_preprocessor_config.json +41 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -1,35 +1,8 @@
|
|
| 1 |
-
*.
|
| 2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
-
*.
|
| 25 |
-
*.
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
-
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 1 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 2 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 4 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.gguf filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
captioncase_01.png filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
LICENSE
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
Apache License
|
| 3 |
+
Version 2.0, January 2004
|
| 4 |
+
http://www.apache.org/licenses/
|
| 5 |
+
|
| 6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 7 |
+
|
| 8 |
+
1. Definitions.
|
| 9 |
+
|
| 10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 12 |
+
|
| 13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 14 |
+
the copyright owner that is granting the License.
|
| 15 |
+
|
| 16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 17 |
+
other entities that control, are controlled by, or are under common
|
| 18 |
+
control with that entity. For the purposes of this definition,
|
| 19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 20 |
+
direction or management of such entity, whether by contract or
|
| 21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 23 |
+
|
| 24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 25 |
+
exercising permissions granted by this License.
|
| 26 |
+
|
| 27 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 28 |
+
including but not limited to software source code, documentation
|
| 29 |
+
source, and configuration files.
|
| 30 |
+
|
| 31 |
+
"Object" form shall mean any form resulting from mechanical
|
| 32 |
+
transformation or translation of a Source form, including but
|
| 33 |
+
not limited to compiled object code, generated documentation,
|
| 34 |
+
and conversions to other media types.
|
| 35 |
+
|
| 36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 37 |
+
Object form, made available under the License, as indicated by a
|
| 38 |
+
copyright notice that is included in or attached to the work
|
| 39 |
+
(an example is provided in the Appendix below).
|
| 40 |
+
|
| 41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 42 |
+
form, that is based on (or derived from) the Work and for which the
|
| 43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 45 |
+
of this License, Derivative Works shall not include works that remain
|
| 46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 47 |
+
the Work and Derivative Works thereof.
|
| 48 |
+
|
| 49 |
+
"Contribution" shall mean any work of authorship, including
|
| 50 |
+
the original version of the Work and any modifications or additions
|
| 51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 55 |
+
means any form of electronic, verbal, or written communication sent
|
| 56 |
+
to the Licensor or its representatives, including but not limited to
|
| 57 |
+
communication on electronic mailing lists, source code control systems,
|
| 58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 60 |
+
excluding communication that is conspicuously marked or otherwise
|
| 61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 62 |
+
|
| 63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 65 |
+
subsequently incorporated within the Work.
|
| 66 |
+
|
| 67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 72 |
+
Work and such Derivative Works in Source or Object form.
|
| 73 |
+
|
| 74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 77 |
+
(except as stated in this section) patent license to make, have made,
|
| 78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 79 |
+
where such license applies only to those patent claims licensable
|
| 80 |
+
by such Contributor that are necessarily infringed by their
|
| 81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 83 |
+
institute patent litigation against any entity (including a
|
| 84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 85 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 86 |
+
or contributory patent infringement, then any patent licenses
|
| 87 |
+
granted to You under this License for that Work shall terminate
|
| 88 |
+
as of the date such litigation is filed.
|
| 89 |
+
|
| 90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 91 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 92 |
+
modifications, and in Source or Object form, provided that You
|
| 93 |
+
meet the following conditions:
|
| 94 |
+
|
| 95 |
+
(a) You must give any other recipients of the Work or
|
| 96 |
+
Derivative Works a copy of this License; and
|
| 97 |
+
|
| 98 |
+
(b) You must cause any modified files to carry prominent notices
|
| 99 |
+
stating that You changed the files; and
|
| 100 |
+
|
| 101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 102 |
+
that You distribute, all copyright, patent, trademark, and
|
| 103 |
+
attribution notices from the Source form of the Work,
|
| 104 |
+
excluding those notices that do not pertain to any part of
|
| 105 |
+
the Derivative Works; and
|
| 106 |
+
|
| 107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 108 |
+
distribution, then any Derivative Works that You distribute must
|
| 109 |
+
include a readable copy of the attribution notices contained
|
| 110 |
+
within such NOTICE file, excluding those notices that do not
|
| 111 |
+
pertain to any part of the Derivative Works, in at least one
|
| 112 |
+
of the following places: within a NOTICE text file distributed
|
| 113 |
+
as part of the Derivative Works; within the Source form or
|
| 114 |
+
documentation, if provided along with the Derivative Works; or,
|
| 115 |
+
within a display generated by the Derivative Works, if and
|
| 116 |
+
wherever such third-party notices normally appear. The contents
|
| 117 |
+
of the NOTICE file are for informational purposes only and
|
| 118 |
+
do not modify the License. You may add Your own attribution
|
| 119 |
+
notices within Derivative Works that You distribute, alongside
|
| 120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 121 |
+
that such additional attribution notices cannot be construed
|
| 122 |
+
as modifying the License.
|
| 123 |
+
|
| 124 |
+
You may add Your own copyright statement to Your modifications and
|
| 125 |
+
may provide additional or different license terms and conditions
|
| 126 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 127 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 128 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 129 |
+
the conditions stated in this License.
|
| 130 |
+
|
| 131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 133 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 134 |
+
this License, without any additional terms or conditions.
|
| 135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 136 |
+
the terms of any separate license agreement you may have executed
|
| 137 |
+
with Licensor regarding such Contributions.
|
| 138 |
+
|
| 139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 141 |
+
except as required for reasonable and customary use in describing the
|
| 142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 143 |
+
|
| 144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 145 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 148 |
+
implied, including, without limitation, any warranties or conditions
|
| 149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 151 |
+
appropriateness of using or redistributing the Work and assume any
|
| 152 |
+
risks associated with Your exercise of permissions under this License.
|
| 153 |
+
|
| 154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 155 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 156 |
+
unless required by applicable law (such as deliberate and grossly
|
| 157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 158 |
+
liable to You for damages, including any direct, indirect, special,
|
| 159 |
+
incidental, or consequential damages of any character arising as a
|
| 160 |
+
result of this License or out of the use or inability to use the
|
| 161 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 162 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 163 |
+
other commercial damages or losses), even if such Contributor
|
| 164 |
+
has been advised of the possibility of such damages.
|
| 165 |
+
|
| 166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 169 |
+
or other liability obligations and/or rights consistent with this
|
| 170 |
+
License. However, in accepting such obligations, You may act only
|
| 171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 172 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 173 |
+
defend, and hold each Contributor harmless for any liability
|
| 174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 175 |
+
of your accepting any such warranty or additional liability.
|
| 176 |
+
|
| 177 |
+
END OF TERMS AND CONDITIONS
|
| 178 |
+
|
| 179 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 180 |
+
|
| 181 |
+
To apply the Apache License to your work, attach the following
|
| 182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 183 |
+
replaced with your own identifying information. (Don't include
|
| 184 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 185 |
+
comment syntax for the file format. We also recommend that a
|
| 186 |
+
file or class name and description of purpose be included on the
|
| 187 |
+
same "printed page" as the copyright notice for easier
|
| 188 |
+
identification within third-party archives.
|
| 189 |
+
|
| 190 |
+
Copyright [yyyy] [name of copyright owner]
|
| 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
CHANGED
|
@@ -1,3 +1,128 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3-VL-8B-Instruct
|
| 4 |
+
library_name: transformers
|
| 5 |
+
pipeline_tag: image-text-to-text
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
tags:
|
| 9 |
+
- video
|
| 10 |
+
- multi-image
|
| 11 |
+
- video-captioning
|
| 12 |
+
- reference-grounding
|
| 13 |
+
- qwen3-vl
|
| 14 |
+
- grpo
|
| 15 |
---
|
| 16 |
+
|
| 17 |
+
# RefCaptioner
|
| 18 |
+
|
| 19 |
+
RefCaptioner is an 8B vision-language model for **multi-reference image-grounded video captioning**. Given a video and an ordered set of reference images, it writes a fluent English description and places tags such as `<Image_1>` directly after the visual phrases grounded by those references. Reference images may include distractors; the model is expected to omit tags that cannot be grounded in the video.
|
| 20 |
+
|
| 21 |
+
The released weights are a merged Hugging Face checkpoint based on [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct). No PEFT adapter is required at inference time.
|
| 22 |
+
|
| 23 |
+
## Model details
|
| 24 |
+
|
| 25 |
+
| Item | Value |
|
| 26 |
+
|---|---|
|
| 27 |
+
| Base model | `Qwen/Qwen3-VL-8B-Instruct` |
|
| 28 |
+
| Release checkpoint | `RefCaptioner1.0` |
|
| 29 |
+
| Input | Ordered reference images plus one video |
|
| 30 |
+
| Output | English caption with local `<Image_n>` bindings |
|
| 31 |
+
| Thinking mode | Disabled |
|
| 32 |
+
| Weight format | Merged `safetensors` |
|
| 33 |
+
|
| 34 |
+
## Installation
|
| 35 |
+
|
| 36 |
+
```bash
|
| 37 |
+
pip install -r requirements.txt
|
| 38 |
+
```
|
| 39 |
+
|
| 40 |
+
RefCaptioner uses the standard Qwen3-VL inference stack and does not require a task-specific runtime. Any environment that can run Qwen3-VL with a compatible Transformers release can be used directly.
|
| 41 |
+
|
| 42 |
+
The benchmark environment used `torch==2.9.0`, `transformers==4.57.6`, `accelerate==1.14.0`, `qwen-vl-utils==0.0.14`, and `av==17.1.0`.
|
| 43 |
+
|
| 44 |
+
## Quick start
|
| 45 |
+
|
| 46 |
+
```bash
|
| 47 |
+
python inference.py \
|
| 48 |
+
--model NOVAglow646/RefCaptioner \
|
| 49 |
+
--video /path/to/video.mp4 \
|
| 50 |
+
--images /path/to/ref_1.jpg /path/to/ref_2.jpg /path/to/ref_3.png
|
| 51 |
+
```
|
| 52 |
+
|
| 53 |
+
The image order defines the tag mapping: the first image is `<Image_1>`, the second is `<Image_2>`, and so on. The script uses the exact prompt structure and deterministic decoding configuration used for the reported test-set inference.
|
| 54 |
+
|
| 55 |
+
## Reproduction configuration
|
| 56 |
+
|
| 57 |
+
The released benchmark captions were generated with the following settings:
|
| 58 |
+
|
| 59 |
+
| Parameter | Value |
|
| 60 |
+
|---|---:|
|
| 61 |
+
| Prompt protocol | `Prompt_1.0` |
|
| 62 |
+
| Maximum input length | 18,000 tokens |
|
| 63 |
+
| Maximum new tokens | 512 |
|
| 64 |
+
| Video sampling rate | 2 FPS |
|
| 65 |
+
| Minimum video frames | 4 |
|
| 66 |
+
| Reference-image maximum pixels | 602,112 |
|
| 67 |
+
| Video-frame maximum pixels | 602,112 |
|
| 68 |
+
| Decoding | Greedy (`do_sample=False`) |
|
| 69 |
+
| Temperature | 0.0 |
|
| 70 |
+
| Top-p / top-k | 1.0 / 0 |
|
| 71 |
+
| Inference dtype | `bfloat16` |
|
| 72 |
+
| Thinking | Disabled |
|
| 73 |
+
|
| 74 |
+
The same values are machine-readable in `inference_config.json`. The eight GPUs used for the full benchmark only provided sample-level parallelism; eight GPUs are not a model requirement. A single device can run the model when it has enough memory, while `device_map="auto"` can distribute the model across available devices.
|
| 75 |
+
|
| 76 |
+
## Input and output contract
|
| 77 |
+
|
| 78 |
+
The prompt labels each ordered reference before presenting the associated image, then presents the video. The model must:
|
| 79 |
+
|
| 80 |
+
1. describe visible video content in one English paragraph;
|
| 81 |
+
2. place every used `<Image_n>` immediately after a concrete grounded phrase;
|
| 82 |
+
3. group tags only when they ground the same visual unit; and
|
| 83 |
+
4. omit distractor or uncertain references rather than forcing all tags into the caption.
|
| 84 |
+
|
| 85 |
+
Example output:
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
## MRVBench Results
|
| 90 |
+
|
| 91 |
+
The following scores report RefCaptioner on MRVBench. `Eff-Bind = Ref-Tag-R × Ref-Bind`.
|
| 92 |
+
|
| 93 |
+
| Model | KP-Cov ↑ | VQA ↑ | VQA-Cov ↑ | Ref-Tag-P ↑ | Ref-Tag-R ↑ | Ref-Bind ↑ | Eff-Bind ↑ | Dist-Rej ↑ | FalseRef-Any ↓ | Subj-R ↑ | Subj-F1 ↑ | MRVScore ↑ |
|
| 94 |
+
|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
|
| 95 |
+
| **RefCaptioner** | 0.882 | 0.686 | 0.837 | 0.994 | 0.943 | 0.967 | 0.912 | 0.985 | 0.100 | 0.817 | 0.869 | 0.888 |
|
| 96 |
+
|
| 97 |
+
These values are tied to the prompt and preprocessing configuration above; changing frame sampling, pixel limits, prompt wording, or decoding can change the results.
|
| 98 |
+
|
| 99 |
+
## Intended use
|
| 100 |
+
|
| 101 |
+
The model is intended for research on multi-reference video understanding, grounded caption generation, reference selection, and local phrase-to-image binding. It is not designed to identify people, infer sensitive attributes, or establish the provenance or ownership of visual content.
|
| 102 |
+
|
| 103 |
+
## Limitations
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
- Results depend on frame sampling and may miss short events between sampled frames.
|
| 107 |
+
- The output is English and follows a task-specific caption style.
|
| 108 |
+
- Reference tags express visual grounding, not identity verification.
|
| 109 |
+
|
| 110 |
+
Users should verify generated descriptions before applying them in consequential settings.
|
| 111 |
+
|
| 112 |
+
## License
|
| 113 |
+
|
| 114 |
+
The model weights are released under the Apache 2.0 license, following the base model. The companion benchmark contains separate media and annotation considerations; consult its dataset card before use or redistribution.
|
| 115 |
+
|
| 116 |
+
## Citation
|
| 117 |
+
|
| 118 |
+
```bibtex
|
| 119 |
+
@misc{liu2026refcaptionermultireferenceimagegroundedvideo,
|
| 120 |
+
title={RefCaptioner: Multi-Reference Image-Grounded Video Captioning},
|
| 121 |
+
author={Tengfei Liu and Yang Shi and Yuran Wang and Xiaohan Zhang and Yuqing Wen and Yuqi Tang and Qixun Wang and Zhuoran Zhang and Xuanyu Zhu and Weihong Lin and Xinlei Yu and Yujie Wei and Xinwei Long and Fengxiang Wang and Xinlong Chen and Yue Ding and Jialu Chen and Haotian Wang and Yuanxing Zhang},
|
| 122 |
+
year={2026},
|
| 123 |
+
eprint={2607.28509},
|
| 124 |
+
archivePrefix={arXiv},
|
| 125 |
+
primaryClass={cs.CV},
|
| 126 |
+
url={https://arxiv.org/abs/2607.28509}
|
| 127 |
+
}
|
| 128 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
captioncase_01.png
ADDED
|
Git LFS Details
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"image_token_id": 151655,
|
| 8 |
+
"model_type": "qwen3_vl",
|
| 9 |
+
"pad_token_id": 151643,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"attention_bias": false,
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"bos_token_id": 151643,
|
| 14 |
+
"dtype": "bfloat16",
|
| 15 |
+
"eos_token_id": 151645,
|
| 16 |
+
"head_dim": 128,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 4096,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 12288,
|
| 21 |
+
"max_position_embeddings": 262144,
|
| 22 |
+
"model_type": "qwen3_vl_text",
|
| 23 |
+
"num_attention_heads": 32,
|
| 24 |
+
"num_hidden_layers": 36,
|
| 25 |
+
"num_key_value_heads": 8,
|
| 26 |
+
"rms_norm_eps": 1e-06,
|
| 27 |
+
"rope_scaling": {
|
| 28 |
+
"mrope_interleaved": true,
|
| 29 |
+
"mrope_section": [
|
| 30 |
+
24,
|
| 31 |
+
20,
|
| 32 |
+
20
|
| 33 |
+
],
|
| 34 |
+
"rope_type": "default"
|
| 35 |
+
},
|
| 36 |
+
"rope_theta": 5000000,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 151936
|
| 39 |
+
},
|
| 40 |
+
"tie_word_embeddings": false,
|
| 41 |
+
"transformers_version": "4.57.6",
|
| 42 |
+
"video_token_id": 151656,
|
| 43 |
+
"vision_config": {
|
| 44 |
+
"deepstack_visual_indexes": [
|
| 45 |
+
8,
|
| 46 |
+
16,
|
| 47 |
+
24
|
| 48 |
+
],
|
| 49 |
+
"depth": 27,
|
| 50 |
+
"dtype": "bfloat16",
|
| 51 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 52 |
+
"hidden_size": 1152,
|
| 53 |
+
"in_channels": 3,
|
| 54 |
+
"initializer_range": 0.02,
|
| 55 |
+
"intermediate_size": 4304,
|
| 56 |
+
"model_type": "qwen3_vl",
|
| 57 |
+
"num_heads": 16,
|
| 58 |
+
"num_position_embeddings": 2304,
|
| 59 |
+
"out_hidden_size": 4096,
|
| 60 |
+
"patch_size": 16,
|
| 61 |
+
"spatial_merge_size": 2,
|
| 62 |
+
"temporal_patch_size": 2
|
| 63 |
+
},
|
| 64 |
+
"vision_end_token_id": 151653,
|
| 65 |
+
"vision_start_token_id": 151652
|
| 66 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": false,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"max_new_tokens": 512,
|
| 9 |
+
"pad_token_id": 151643,
|
| 10 |
+
"transformers_version": "4.57.6"
|
| 11 |
+
}
|
inference.py
ADDED
|
@@ -0,0 +1,166 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""Run RefCaptioner with the MRVBench inference configuration."""
|
| 3 |
+
|
| 4 |
+
from __future__ import annotations
|
| 5 |
+
|
| 6 |
+
import argparse
|
| 7 |
+
import json
|
| 8 |
+
from pathlib import Path
|
| 9 |
+
|
| 10 |
+
import torch
|
| 11 |
+
from qwen_vl_utils import process_vision_info
|
| 12 |
+
from transformers import AutoProcessor, Qwen3VLForConditionalGeneration
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
INSTRUCTION = """You are a multi-reference video captioning model.
|
| 16 |
+
|
| 17 |
+
Input:
|
| 18 |
+
- Several reference images, each labeled as <Image_1>, <Image_2>, etc.
|
| 19 |
+
- Some reference images may be distractors that are not visible in the video.
|
| 20 |
+
- One reference video.
|
| 21 |
+
|
| 22 |
+
Task:
|
| 23 |
+
Write one fluent English video caption that describes the visible video content and locally binds each usable reference image tag to the visual phrase it grounds.
|
| 24 |
+
|
| 25 |
+
Output rules:
|
| 26 |
+
- Return only the caption: no markdown, bullets, JSON, explanations, or title.
|
| 27 |
+
- Write one natural English paragraph, usually 4 to 7 complete sentences and about 120 to 250 words.
|
| 28 |
+
- Cover the main video style or format, main subject, setting, referenced appearances or objects, action progression, and useful camera, lighting, color, or mood details.
|
| 29 |
+
- Keep the caption grounded in visible video evidence. Do not invent unseen names, relationships, causes, dialogue, or story details.
|
| 30 |
+
- Do not mention audio, music, speech, dialogue, transcript, voiceover, or sound. Mention visible subtitles, logos, or text only when visually important.
|
| 31 |
+
|
| 32 |
+
Reference binding rules:
|
| 33 |
+
- Use only the provided tags. Do not invent tags.
|
| 34 |
+
- Use a tag only when its reference image can be grounded to visible video content.
|
| 35 |
+
- Do not force every provided tag. Omit tags whose image is not visible in the video or cannot be confidently grounded.
|
| 36 |
+
- Place each used tag immediately after a concrete grounded phrase, such as "the woman <Image_1>" or "the red dress <Image_2>".
|
| 37 |
+
- Multiple tags may be stacked as one contiguous tag group only when they refer to the same concrete visual unit, such as the same person, animal, character, vehicle, room, landscape, outfit item, prop, action pose, lighting, mood, or visual style.
|
| 38 |
+
- Do not stack tags merely because the images are related. A person and their clothing, accessory, carried object, background, or action are usually different visual units and should be tagged on separate phrases.
|
| 39 |
+
- If several tags belong to the same visual unit, keep them together as a complete tag group whenever that unit is explicitly mentioned.
|
| 40 |
+
- If two tags need different phrases, do not stack them.
|
| 41 |
+
- Attach tags to explicit noun phrases, not pronouns such as "he", "she", "it", "they", or "them".
|
| 42 |
+
- Do not put all tags at the end of the caption.
|
| 43 |
+
- Do not write phrases like "from <Image_N>", "shown in <Image_N>", "as shown in <Image_N>", "same as <Image_N>", or "similar to <Image_N>"."""
|
| 44 |
+
|
| 45 |
+
FINAL_REQUEST = (
|
| 46 |
+
"Now write the final caption. Use only visibly grounded provided tags exactly "
|
| 47 |
+
"as tag tokens, attach them to concrete visual phrases, omit ungrounded "
|
| 48 |
+
"distractor tags, and stack tags only when they refer to the same visual unit."
|
| 49 |
+
)
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def parse_args() -> argparse.Namespace:
|
| 53 |
+
parser = argparse.ArgumentParser()
|
| 54 |
+
parser.add_argument("--model", default="NOVAglow646/RefCaptioner")
|
| 55 |
+
parser.add_argument("--video", type=Path, required=True)
|
| 56 |
+
parser.add_argument("--images", type=Path, nargs="+", required=True)
|
| 57 |
+
parser.add_argument("--config", type=Path, default=Path(__file__).with_name("inference_config.json"))
|
| 58 |
+
return parser.parse_args()
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def build_messages(video: Path, images: list[Path], cfg: dict) -> list[dict]:
|
| 62 |
+
tags = [f"<Image_{index}>" for index in range(1, len(images) + 1)]
|
| 63 |
+
content: list[dict] = [
|
| 64 |
+
{"type": "text", "text": INSTRUCTION},
|
| 65 |
+
{
|
| 66 |
+
"type": "text",
|
| 67 |
+
"text": (
|
| 68 |
+
"\n\nCurrent sample starts here.\nReference image tags, in order: "
|
| 69 |
+
+ ", ".join(tags)
|
| 70 |
+
+ "\nEach following image is the visual reference for the tag immediately before it.\n\n"
|
| 71 |
+
),
|
| 72 |
+
},
|
| 73 |
+
]
|
| 74 |
+
for tag, image in zip(tags, images):
|
| 75 |
+
content.extend(
|
| 76 |
+
[
|
| 77 |
+
{"type": "text", "text": f"{tag} reference image:\n"},
|
| 78 |
+
{
|
| 79 |
+
"type": "image",
|
| 80 |
+
"image": str(image.resolve()),
|
| 81 |
+
"max_pixels": cfg["image_max_pixels"],
|
| 82 |
+
},
|
| 83 |
+
{"type": "text", "text": "\n\n"},
|
| 84 |
+
]
|
| 85 |
+
)
|
| 86 |
+
content.extend(
|
| 87 |
+
[
|
| 88 |
+
{"type": "text", "text": "Reference video:\n"},
|
| 89 |
+
{
|
| 90 |
+
"type": "video",
|
| 91 |
+
"video": str(video.resolve()),
|
| 92 |
+
"fps": cfg["video_fps"],
|
| 93 |
+
"min_frames": cfg["video_min_frames"],
|
| 94 |
+
"max_frames": cfg["video_max_frames"],
|
| 95 |
+
"max_pixels": cfg["video_max_pixels"],
|
| 96 |
+
},
|
| 97 |
+
{"type": "text", "text": "\n\n" + FINAL_REQUEST},
|
| 98 |
+
]
|
| 99 |
+
)
|
| 100 |
+
return [{"role": "user", "content": content}]
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
def main() -> None:
|
| 104 |
+
args = parse_args()
|
| 105 |
+
if not args.video.is_file():
|
| 106 |
+
raise FileNotFoundError(args.video)
|
| 107 |
+
missing = [path for path in args.images if not path.is_file()]
|
| 108 |
+
if missing:
|
| 109 |
+
raise FileNotFoundError(f"Missing reference images: {missing}")
|
| 110 |
+
|
| 111 |
+
cfg = json.loads(args.config.read_text(encoding="utf-8"))
|
| 112 |
+
model = Qwen3VLForConditionalGeneration.from_pretrained(
|
| 113 |
+
args.model,
|
| 114 |
+
dtype=torch.bfloat16,
|
| 115 |
+
device_map=cfg["device_map"],
|
| 116 |
+
).eval()
|
| 117 |
+
processor = AutoProcessor.from_pretrained(args.model)
|
| 118 |
+
messages = build_messages(args.video, args.images, cfg)
|
| 119 |
+
text = processor.apply_chat_template(
|
| 120 |
+
messages,
|
| 121 |
+
tokenize=False,
|
| 122 |
+
add_generation_prompt=True,
|
| 123 |
+
enable_thinking=False,
|
| 124 |
+
)
|
| 125 |
+
image_inputs, video_inputs, video_kwargs = process_vision_info(
|
| 126 |
+
messages, return_video_kwargs=True
|
| 127 |
+
)
|
| 128 |
+
if isinstance(video_kwargs, dict):
|
| 129 |
+
video_kwargs = {
|
| 130 |
+
key: value
|
| 131 |
+
for key, value in video_kwargs.items()
|
| 132 |
+
if not (isinstance(value, list) and not value)
|
| 133 |
+
}
|
| 134 |
+
if isinstance(video_kwargs.get("fps"), list) and video_kwargs["fps"]:
|
| 135 |
+
video_kwargs["fps"] = video_kwargs["fps"][0]
|
| 136 |
+
inputs = processor(
|
| 137 |
+
text=[text],
|
| 138 |
+
images=image_inputs,
|
| 139 |
+
videos=video_inputs,
|
| 140 |
+
padding=True,
|
| 141 |
+
return_tensors="pt",
|
| 142 |
+
**video_kwargs,
|
| 143 |
+
)
|
| 144 |
+
if inputs["input_ids"].shape[-1] > cfg["max_length"]:
|
| 145 |
+
raise ValueError(
|
| 146 |
+
f"Input has {inputs['input_ids'].shape[-1]} tokens; "
|
| 147 |
+
f"limit is {cfg['max_length']}."
|
| 148 |
+
)
|
| 149 |
+
inputs = inputs.to(model.device)
|
| 150 |
+
with torch.inference_mode():
|
| 151 |
+
generated = model.generate(
|
| 152 |
+
**inputs,
|
| 153 |
+
max_new_tokens=cfg["max_new_tokens"],
|
| 154 |
+
do_sample=False,
|
| 155 |
+
)
|
| 156 |
+
trimmed = [output[len(source) :] for source, output in zip(inputs.input_ids, generated)]
|
| 157 |
+
caption = processor.batch_decode(
|
| 158 |
+
trimmed,
|
| 159 |
+
skip_special_tokens=True,
|
| 160 |
+
clean_up_tokenization_spaces=False,
|
| 161 |
+
)[0].strip()
|
| 162 |
+
print(caption)
|
| 163 |
+
|
| 164 |
+
|
| 165 |
+
if __name__ == "__main__":
|
| 166 |
+
main()
|
inference_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"prompt_version": "Prompt_1.0",
|
| 3 |
+
"max_length": 18000,
|
| 4 |
+
"max_new_tokens": 512,
|
| 5 |
+
"video_fps": 2.0,
|
| 6 |
+
"video_min_frames": 4,
|
| 7 |
+
"video_max_frames": 20,
|
| 8 |
+
"image_max_pixels": 602112,
|
| 9 |
+
"video_max_pixels": 602112,
|
| 10 |
+
"do_sample": false,
|
| 11 |
+
"temperature": 0.0,
|
| 12 |
+
"top_p": 1.0,
|
| 13 |
+
"top_k": 0,
|
| 14 |
+
"disable_thinking": true,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"device_map": "auto"
|
| 17 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef0877b9809a0fd6c490a4c1732050c8ff9f868465e481b46545a4fe1892d38e
|
| 3 |
+
size 4999798040
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6388a789f71c1057c216372e1c110d4e723256ff406f3c48d1304d4aea54b9e1
|
| 3 |
+
size 4996637696
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab6bd4c5a9aa0ade02a3b2ffca0c6c04f36c05ce58f6a2b4dc65f2bd0c7331b1
|
| 3 |
+
size 4920415120
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25e039773d95d5ce39bb911d7360d18f7d106bf8e3a367de3ac030fd80b08bc5
|
| 3 |
+
size 2617488656
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,758 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8767123696,
|
| 4 |
+
"total_size": 17534247392
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00003-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 405 |
+
"model.language_model.norm.weight": "model-00003-of-00004.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 409 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00004.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 413 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00003-of-00004.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.bias": "model-00002-of-00004.safetensors",
|
| 417 |
+
"model.visual.blocks.0.norm2.weight": "model-00002-of-00004.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 421 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00003-of-00004.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 425 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.bias": "model-00003-of-00004.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm1.weight": "model-00003-of-00004.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.bias": "model-00003-of-00004.safetensors",
|
| 429 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.10.norm2.weight": "model-00002-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00003-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.bias": "model-00002-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.bias": "model-00002-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.bias": "model-00003-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm1.weight": "model-00003-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.bias": "model-00003-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.12.norm2.weight": "model-00003-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.bias": "model-00002-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm1.weight": "model-00003-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.bias": "model-00003-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.13.norm2.weight": "model-00002-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00003-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.bias": "model-00003-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.bias": "model-00002-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm1.weight": "model-00003-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.bias": "model-00003-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.bias": "model-00002-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00003-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00003-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.bias": "model-00003-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm1.weight": "model-00003-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.bias": "model-00003-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.17.norm2.weight": "model-00003-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm1.weight": "model-00002-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.bias": "model-00002-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.18.norm2.weight": "model-00003-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.bias": "model-00003-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm1.weight": "model-00002-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.bias": "model-00002-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.bias": "model-00002-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.bias": "model-00003-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.2.norm2.weight": "model-00002-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.bias": "model-00002-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.bias": "model-00002-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.20.norm2.weight": "model-00002-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00003-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.bias": "model-00002-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm1.weight": "model-00002-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.bias": "model-00003-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.bias": "model-00002-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm1.weight": "model-00002-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.bias": "model-00003-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.22.norm2.weight": "model-00003-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00003-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.bias": "model-00002-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm1.weight": "model-00002-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.23.norm2.weight": "model-00003-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00002-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.24.norm1.bias": "model-00003-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.24.norm1.weight": "model-00003-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.24.norm2.bias": "model-00002-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.24.norm2.weight": "model-00002-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.25.norm1.weight": "model-00002-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.25.norm2.bias": "model-00003-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.25.norm2.weight": "model-00003-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00003-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.26.norm1.bias": "model-00002-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.26.norm1.weight": "model-00003-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.26.norm2.weight": "model-00002-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00003-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.4.norm1.bias": "model-00002-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.4.norm1.weight": "model-00003-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00003-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00003-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.5.norm2.bias": "model-00003-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.5.norm2.weight": "model-00003-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00003-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.6.norm1.bias": "model-00003-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.6.norm1.weight": "model-00003-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.7.norm2.bias": "model-00002-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00002-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.8.norm1.weight": "model-00002-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.8.norm2.bias": "model-00002-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00002-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.9.norm2.bias": "model-00003-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.9.norm2.weight": "model-00003-of-00004.safetensors",
|
| 730 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00003-of-00004.safetensors",
|
| 731 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 732 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00003-of-00004.safetensors",
|
| 733 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 734 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00004.safetensors",
|
| 735 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00004-of-00004.safetensors",
|
| 736 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 737 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 738 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 739 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 740 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
|
| 741 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00003-of-00004.safetensors",
|
| 742 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00003-of-00004.safetensors",
|
| 743 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00003-of-00004.safetensors",
|
| 744 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 745 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00004.safetensors",
|
| 746 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00004-of-00004.safetensors",
|
| 747 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
|
| 748 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 749 |
+
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 750 |
+
"model.visual.merger.linear_fc2.bias": "model-00002-of-00004.safetensors",
|
| 751 |
+
"model.visual.merger.linear_fc2.weight": "model-00003-of-00004.safetensors",
|
| 752 |
+
"model.visual.merger.norm.bias": "model-00002-of-00004.safetensors",
|
| 753 |
+
"model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
|
| 754 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
|
| 755 |
+
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
| 756 |
+
"model.visual.pos_embed.weight": "model-00003-of-00004.safetensors"
|
| 757 |
+
}
|
| 758 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": null,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 16777216,
|
| 36 |
+
"shortest_edge": 65536
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
requirements.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch>=2.4
|
| 2 |
+
transformers>=4.57.0,<5
|
| 3 |
+
accelerate>=1.0
|
| 4 |
+
qwen-vl-utils>=0.0.14
|
| 5 |
+
av>=14
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"processor_class": "Qwen3VLProcessor",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|