Add clef-flash weights, joint schema head, code, and processor
Browse files- .gitattributes +1 -0
- LICENSE +202 -0
- chat_template.jinja +154 -0
- config.json +109 -0
- generation_config.json +6 -0
- joint_head.safetensors +3 -0
- joint_head_config.json +8 -0
- joint_schema_model.py +515 -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 +768 -0
- processor_config.json +60 -0
- tokenizer.json +3 -0
- tokenizer_config.json +30 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
Apache License
|
| 3 |
+
Version 2.0, January 2004
|
| 4 |
+
http://www.apache.org/licenses/
|
| 5 |
+
|
| 6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 7 |
+
|
| 8 |
+
1. Definitions.
|
| 9 |
+
|
| 10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 12 |
+
|
| 13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 14 |
+
the copyright owner that is granting the License.
|
| 15 |
+
|
| 16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 17 |
+
other entities that control, are controlled by, or are under common
|
| 18 |
+
control with that entity. For the purposes of this definition,
|
| 19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 20 |
+
direction or management of such entity, whether by contract or
|
| 21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 23 |
+
|
| 24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 25 |
+
exercising permissions granted by this License.
|
| 26 |
+
|
| 27 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 28 |
+
including but not limited to software source code, documentation
|
| 29 |
+
source, and configuration files.
|
| 30 |
+
|
| 31 |
+
"Object" form shall mean any form resulting from mechanical
|
| 32 |
+
transformation or translation of a Source form, including but
|
| 33 |
+
not limited to compiled object code, generated documentation,
|
| 34 |
+
and conversions to other media types.
|
| 35 |
+
|
| 36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 37 |
+
Object form, made available under the License, as indicated by a
|
| 38 |
+
copyright notice that is included in or attached to the work
|
| 39 |
+
(an example is provided in the Appendix below).
|
| 40 |
+
|
| 41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 42 |
+
form, that is based on (or derived from) the Work and for which the
|
| 43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 45 |
+
of this License, Derivative Works shall not include works that remain
|
| 46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 47 |
+
the Work and Derivative Works thereof.
|
| 48 |
+
|
| 49 |
+
"Contribution" shall mean any work of authorship, including
|
| 50 |
+
the original version of the Work and any modifications or additions
|
| 51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 55 |
+
means any form of electronic, verbal, or written communication sent
|
| 56 |
+
to the Licensor or its representatives, including but not limited to
|
| 57 |
+
communication on electronic mailing lists, source code control systems,
|
| 58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 60 |
+
excluding communication that is conspicuously marked or otherwise
|
| 61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 62 |
+
|
| 63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 65 |
+
subsequently incorporated within the Work.
|
| 66 |
+
|
| 67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 72 |
+
Work and such Derivative Works in Source or Object form.
|
| 73 |
+
|
| 74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 77 |
+
(except as stated in this section) patent license to make, have made,
|
| 78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 79 |
+
where such license applies only to those patent claims licensable
|
| 80 |
+
by such Contributor that are necessarily infringed by their
|
| 81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 83 |
+
institute patent litigation against any entity (including a
|
| 84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 85 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 86 |
+
or contributory patent infringement, then any patent licenses
|
| 87 |
+
granted to You under this License for that Work shall terminate
|
| 88 |
+
as of the date such litigation is filed.
|
| 89 |
+
|
| 90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 91 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 92 |
+
modifications, and in Source or Object form, provided that You
|
| 93 |
+
meet the following conditions:
|
| 94 |
+
|
| 95 |
+
(a) You must give any other recipients of the Work or
|
| 96 |
+
Derivative Works a copy of this License; and
|
| 97 |
+
|
| 98 |
+
(b) You must cause any modified files to carry prominent notices
|
| 99 |
+
stating that You changed the files; and
|
| 100 |
+
|
| 101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 102 |
+
that You distribute, all copyright, patent, trademark, and
|
| 103 |
+
attribution notices from the Source form of the Work,
|
| 104 |
+
excluding those notices that do not pertain to any part of
|
| 105 |
+
the Derivative Works; and
|
| 106 |
+
|
| 107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 108 |
+
distribution, then any Derivative Works that You distribute must
|
| 109 |
+
include a readable copy of the attribution notices contained
|
| 110 |
+
within such NOTICE file, excluding those notices that do not
|
| 111 |
+
pertain to any part of the Derivative Works, in at least one
|
| 112 |
+
of the following places: within a NOTICE text file distributed
|
| 113 |
+
as part of the Derivative Works; within the Source form or
|
| 114 |
+
documentation, if provided along with the Derivative Works; or,
|
| 115 |
+
within a display generated by the Derivative Works, if and
|
| 116 |
+
wherever such third-party notices normally appear. The contents
|
| 117 |
+
of the NOTICE file are for informational purposes only and
|
| 118 |
+
do not modify the License. You may add Your own attribution
|
| 119 |
+
notices within Derivative Works that You distribute, alongside
|
| 120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 121 |
+
that such additional attribution notices cannot be construed
|
| 122 |
+
as modifying the License.
|
| 123 |
+
|
| 124 |
+
You may add Your own copyright statement to Your modifications and
|
| 125 |
+
may provide additional or different license terms and conditions
|
| 126 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 127 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 128 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 129 |
+
the conditions stated in this License.
|
| 130 |
+
|
| 131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 133 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 134 |
+
this License, without any additional terms or conditions.
|
| 135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 136 |
+
the terms of any separate license agreement you may have executed
|
| 137 |
+
with Licensor regarding such Contributions.
|
| 138 |
+
|
| 139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 141 |
+
except as required for reasonable and customary use in describing the
|
| 142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 143 |
+
|
| 144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 145 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 148 |
+
implied, including, without limitation, any warranties or conditions
|
| 149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 151 |
+
appropriateness of using or redistributing the Work and assume any
|
| 152 |
+
risks associated with Your exercise of permissions under this License.
|
| 153 |
+
|
| 154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 155 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 156 |
+
unless required by applicable law (such as deliberate and grossly
|
| 157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 158 |
+
liable to You for damages, including any direct, indirect, special,
|
| 159 |
+
incidental, or consequential damages of any character arising as a
|
| 160 |
+
result of this License or out of the use or inability to use the
|
| 161 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 162 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 163 |
+
other commercial damages or losses), even if such Contributor
|
| 164 |
+
has been advised of the possibility of such damages.
|
| 165 |
+
|
| 166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 169 |
+
or other liability obligations and/or rights consistent with this
|
| 170 |
+
License. However, in accepting such obligations, You may act only
|
| 171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 172 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 173 |
+
defend, and hold each Contributor harmless for any liability
|
| 174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 175 |
+
of your accepting any such warranty or additional liability.
|
| 176 |
+
|
| 177 |
+
END OF TERMS AND CONDITIONS
|
| 178 |
+
|
| 179 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 180 |
+
|
| 181 |
+
To apply the Apache License to your work, attach the following
|
| 182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 183 |
+
replaced with your own identifying information. (Don't include
|
| 184 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 185 |
+
comment syntax for the file format. We also recommend that a
|
| 186 |
+
file or class name and description of purpose be included on the
|
| 187 |
+
same "printed page" as the copyright notice for easier
|
| 188 |
+
identification within third-party archives.
|
| 189 |
+
|
| 190 |
+
Copyright 2026 Alibaba Cloud
|
| 191 |
+
|
| 192 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 193 |
+
you may not use this file except in compliance with the License.
|
| 194 |
+
You may obtain a copy of the License at
|
| 195 |
+
|
| 196 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 197 |
+
|
| 198 |
+
Unless required by applicable law or agreed to in writing, software
|
| 199 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 200 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 201 |
+
See the License for the specific language governing permissions and
|
| 202 |
+
limitations under the License.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 248056,
|
| 7 |
+
"model_type": "qwen3_5",
|
| 8 |
+
"text_config": {
|
| 9 |
+
"attention_bias": false,
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"attn_output_gate": true,
|
| 12 |
+
"bos_token_id": null,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"eos_token_id": 248044,
|
| 15 |
+
"full_attention_interval": 4,
|
| 16 |
+
"head_dim": 256,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 4096,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 12288,
|
| 21 |
+
"layer_types": [
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"full_attention"
|
| 54 |
+
],
|
| 55 |
+
"linear_conv_kernel_dim": 4,
|
| 56 |
+
"linear_key_head_dim": 128,
|
| 57 |
+
"linear_num_key_heads": 16,
|
| 58 |
+
"linear_num_value_heads": 32,
|
| 59 |
+
"linear_value_head_dim": 128,
|
| 60 |
+
"mamba_ssm_dtype": "float32",
|
| 61 |
+
"max_position_embeddings": 262144,
|
| 62 |
+
"mlp_only_layers": [],
|
| 63 |
+
"model_type": "qwen3_5_text",
|
| 64 |
+
"mtp_num_hidden_layers": 0,
|
| 65 |
+
"mtp_use_dedicated_embeddings": false,
|
| 66 |
+
"num_attention_heads": 16,
|
| 67 |
+
"num_hidden_layers": 32,
|
| 68 |
+
"num_key_value_heads": 4,
|
| 69 |
+
"pad_token_id": null,
|
| 70 |
+
"partial_rotary_factor": 0.25,
|
| 71 |
+
"rms_norm_eps": 1e-06,
|
| 72 |
+
"rope_parameters": {
|
| 73 |
+
"mrope_interleaved": true,
|
| 74 |
+
"mrope_section": [
|
| 75 |
+
11,
|
| 76 |
+
11,
|
| 77 |
+
10
|
| 78 |
+
],
|
| 79 |
+
"partial_rotary_factor": 0.25,
|
| 80 |
+
"rope_theta": 10000000,
|
| 81 |
+
"rope_type": "default"
|
| 82 |
+
},
|
| 83 |
+
"tie_word_embeddings": false,
|
| 84 |
+
"use_cache": true,
|
| 85 |
+
"vocab_size": 248320
|
| 86 |
+
},
|
| 87 |
+
"tie_word_embeddings": false,
|
| 88 |
+
"transformers_version": "5.10.2",
|
| 89 |
+
"video_token_id": 248057,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"deepstack_visual_indexes": [],
|
| 92 |
+
"depth": 27,
|
| 93 |
+
"dtype": "bfloat16",
|
| 94 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 95 |
+
"hidden_size": 1152,
|
| 96 |
+
"in_channels": 3,
|
| 97 |
+
"initializer_range": 0.02,
|
| 98 |
+
"intermediate_size": 4304,
|
| 99 |
+
"model_type": "qwen3_5_vision",
|
| 100 |
+
"num_heads": 16,
|
| 101 |
+
"num_position_embeddings": 2304,
|
| 102 |
+
"out_hidden_size": 4096,
|
| 103 |
+
"patch_size": 16,
|
| 104 |
+
"spatial_merge_size": 2,
|
| 105 |
+
"temporal_patch_size": 2
|
| 106 |
+
},
|
| 107 |
+
"vision_end_token_id": 248054,
|
| 108 |
+
"vision_start_token_id": 248053
|
| 109 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 248044,
|
| 4 |
+
"transformers_version": "5.10.2",
|
| 5 |
+
"use_cache": true
|
| 6 |
+
}
|
joint_head.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19cdcec8c81dc9212be320fff47462ab342fbc1278be4368fb3da71241cf5ba0
|
| 3 |
+
size 243538016
|
joint_head_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"hidden_size": 4096,
|
| 3 |
+
"width": 1024,
|
| 4 |
+
"routing_layers": 2,
|
| 5 |
+
"layers": 4,
|
| 6 |
+
"heads": 16,
|
| 7 |
+
"feedforward": 4096
|
| 8 |
+
}
|
joint_schema_model.py
ADDED
|
@@ -0,0 +1,515 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""CLEF: a multimodal Qwen backbone with a joint schema head for typed decisions.
|
| 2 |
+
|
| 3 |
+
A record provides a ``state`` (any JSON value), optional ``images`` and ``videos``,
|
| 4 |
+
and ``questions``. Each question has a ``type`` (``noul``, ``choice``, or ``score``),
|
| 5 |
+
``instructions``, and, for ``choice`` and ``score``, ``criteria`` describing the
|
| 6 |
+
allowed options. The model returns one logit per allowed option for every question.
|
| 7 |
+
"""
|
| 8 |
+
|
| 9 |
+
from __future__ import annotations
|
| 10 |
+
|
| 11 |
+
import json
|
| 12 |
+
import math
|
| 13 |
+
from dataclasses import dataclass
|
| 14 |
+
from dataclasses import field as dataclass_field
|
| 15 |
+
from pathlib import Path
|
| 16 |
+
from typing import Any
|
| 17 |
+
|
| 18 |
+
import torch
|
| 19 |
+
import torch.nn.functional as functional
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
SYSTEM_PROMPT = (
|
| 23 |
+
"Read the complete state and schema. Decide every field jointly. Each answer "
|
| 24 |
+
"must be exactly one of that field's allowed options."
|
| 25 |
+
)
|
| 26 |
+
IMAGE_PLACEHOLDER = "<|vision_start|><|image_pad|><|vision_end|>"
|
| 27 |
+
VIDEO_PLACEHOLDER = "<|vision_start|><|video_pad|><|vision_end|>"
|
| 28 |
+
MEDIA_BATCH_KEYS = ("pixel_values", "image_grid_thw", "pixel_values_videos", "video_grid_thw")
|
| 29 |
+
MEDIA_TOKEN_KEYS = ("mm_token_type_ids",)
|
| 30 |
+
QUESTION_TYPES = {"noul": 0, "choice": 1, "score": 2}
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
def render(value: Any) -> str:
|
| 34 |
+
if isinstance(value, str):
|
| 35 |
+
return value
|
| 36 |
+
return json.dumps(
|
| 37 |
+
value,
|
| 38 |
+
ensure_ascii=False,
|
| 39 |
+
separators=(",", ":"),
|
| 40 |
+
sort_keys=True,
|
| 41 |
+
)
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
def question_options(question: dict[str, Any]) -> list[tuple[str, Any]]:
|
| 45 |
+
question_type = str(question["type"])
|
| 46 |
+
if question_type == "noul":
|
| 47 |
+
criteria = {
|
| 48 |
+
"true": "The proposition is true or the answer is yes.",
|
| 49 |
+
"false": "The proposition is false or the answer is no.",
|
| 50 |
+
}
|
| 51 |
+
criteria.update(question.get("criteria") or {})
|
| 52 |
+
return [(key, criteria[key]) for key in ("true", "false")]
|
| 53 |
+
if question_type == "choice":
|
| 54 |
+
return sorted((str(key), value) for key, value in question["criteria"].items())
|
| 55 |
+
return [(str(index), value) for index, value in enumerate(question["criteria"])]
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
@dataclass(frozen=True)
|
| 59 |
+
class EncodedQuestion:
|
| 60 |
+
question_id: str
|
| 61 |
+
question_type: int
|
| 62 |
+
question_span: tuple[int, int]
|
| 63 |
+
option_spans: tuple[tuple[int, int], ...]
|
| 64 |
+
option_ids: tuple[str, ...]
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
@dataclass(frozen=True)
|
| 68 |
+
class EncodedRecord:
|
| 69 |
+
input_ids: tuple[int, ...]
|
| 70 |
+
questions: tuple[EncodedQuestion, ...]
|
| 71 |
+
record_id: str
|
| 72 |
+
media: dict[str, Any] | None = dataclass_field(default=None, compare=False, repr=False)
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
def _tokens(tokenizer: Any, text: str) -> list[int]:
|
| 76 |
+
return tokenizer(text, add_special_tokens=False).input_ids
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
def _encode_media(processor: Any, record: dict[str, Any]) -> tuple[list[int], dict[str, Any] | None]:
|
| 80 |
+
images = list(record.get("images") or [])
|
| 81 |
+
videos = list(record.get("videos") or [])
|
| 82 |
+
if not images and not videos:
|
| 83 |
+
return [], None
|
| 84 |
+
if processor is None:
|
| 85 |
+
raise ValueError("records with images or videos require a processor")
|
| 86 |
+
text = IMAGE_PLACEHOLDER * len(images) + VIDEO_PLACEHOLDER * len(videos) + "\n"
|
| 87 |
+
encoded = processor(
|
| 88 |
+
text=[text],
|
| 89 |
+
images=images or None,
|
| 90 |
+
videos=videos or None,
|
| 91 |
+
return_tensors="pt",
|
| 92 |
+
**(record.get("media_kwargs") or {}),
|
| 93 |
+
)
|
| 94 |
+
media = {key: encoded[key] for key in MEDIA_BATCH_KEYS if key in encoded}
|
| 95 |
+
for key in MEDIA_TOKEN_KEYS:
|
| 96 |
+
if key in encoded:
|
| 97 |
+
media[key] = encoded[key][0].tolist()
|
| 98 |
+
return encoded["input_ids"][0].tolist(), media
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
def encode_record(
|
| 102 |
+
tokenizer: Any,
|
| 103 |
+
record: dict[str, Any],
|
| 104 |
+
max_length: int = 16384,
|
| 105 |
+
max_state_tokens: int | None = None,
|
| 106 |
+
processor: Any | None = None,
|
| 107 |
+
) -> EncodedRecord:
|
| 108 |
+
schema_ids = _tokens(tokenizer, "\n\nSCHEMA FIELDS:\n")
|
| 109 |
+
questions: list[EncodedQuestion] = []
|
| 110 |
+
for question_index, (question_id, question) in enumerate(record["questions"].items()):
|
| 111 |
+
schema_ids.extend(
|
| 112 |
+
_tokens(
|
| 113 |
+
tokenizer,
|
| 114 |
+
f"\nFIELD {question_index + 1}\nID: {question_id}\nTYPE: {question['type']}\nINSTRUCTION: ",
|
| 115 |
+
)
|
| 116 |
+
)
|
| 117 |
+
question_start = len(schema_ids)
|
| 118 |
+
schema_ids.extend(_tokens(tokenizer, render(question["instructions"])))
|
| 119 |
+
question_end = len(schema_ids)
|
| 120 |
+
schema_ids.extend(_tokens(tokenizer, "\nALLOWED OPTIONS:\n"))
|
| 121 |
+
|
| 122 |
+
option_spans: list[tuple[int, int]] = []
|
| 123 |
+
option_ids: list[str] = []
|
| 124 |
+
for option_index, (option_id, description) in enumerate(question_options(question)):
|
| 125 |
+
schema_ids.extend(_tokens(tokenizer, f"OPTION {option_index + 1}: "))
|
| 126 |
+
option_start = len(schema_ids)
|
| 127 |
+
semantics = {"option_id": option_id}
|
| 128 |
+
if description is not None:
|
| 129 |
+
semantics["description"] = description
|
| 130 |
+
schema_ids.extend(_tokens(tokenizer, render(semantics)))
|
| 131 |
+
option_spans.append((option_start, len(schema_ids)))
|
| 132 |
+
option_ids.append(option_id)
|
| 133 |
+
schema_ids.extend(_tokens(tokenizer, "\n"))
|
| 134 |
+
schema_ids.extend(_tokens(tokenizer, "END FIELD\n"))
|
| 135 |
+
questions.append(
|
| 136 |
+
EncodedQuestion(
|
| 137 |
+
question_id=str(question_id),
|
| 138 |
+
question_type=QUESTION_TYPES[str(question["type"])],
|
| 139 |
+
question_span=(question_start, question_end),
|
| 140 |
+
option_spans=tuple(option_spans),
|
| 141 |
+
option_ids=tuple(option_ids),
|
| 142 |
+
)
|
| 143 |
+
)
|
| 144 |
+
|
| 145 |
+
prefix_ids = _tokens(
|
| 146 |
+
tokenizer,
|
| 147 |
+
f"<|im_start|>system\n{SYSTEM_PROMPT}<|im_end|>\n<|im_start|>user\nSTATE:\n",
|
| 148 |
+
)
|
| 149 |
+
suffix_ids = _tokens(
|
| 150 |
+
tokenizer,
|
| 151 |
+
"\n<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\nJOINT SCHEMA DECISIONS:",
|
| 152 |
+
)
|
| 153 |
+
media_ids, media = _encode_media(processor, record)
|
| 154 |
+
if media is not None:
|
| 155 |
+
media["token_offset"] = len(prefix_ids)
|
| 156 |
+
prefix_ids = prefix_ids + media_ids
|
| 157 |
+
state_ids = _tokens(tokenizer, render(record["state"]))
|
| 158 |
+
if max_state_tokens is not None:
|
| 159 |
+
state_ids = state_ids[:max_state_tokens]
|
| 160 |
+
fixed_length = len(prefix_ids) + len(schema_ids) + len(suffix_ids)
|
| 161 |
+
if fixed_length > max_length:
|
| 162 |
+
raise ValueError(
|
| 163 |
+
f"schema requires {fixed_length} tokens before state; maximum is {max_length}"
|
| 164 |
+
)
|
| 165 |
+
state_ids = state_ids[: max_length - fixed_length]
|
| 166 |
+
schema_offset = len(prefix_ids) + len(state_ids)
|
| 167 |
+
shifted_questions = tuple(
|
| 168 |
+
EncodedQuestion(
|
| 169 |
+
question_id=question.question_id,
|
| 170 |
+
question_type=question.question_type,
|
| 171 |
+
question_span=(
|
| 172 |
+
question.question_span[0] + schema_offset,
|
| 173 |
+
question.question_span[1] + schema_offset,
|
| 174 |
+
),
|
| 175 |
+
option_spans=tuple(
|
| 176 |
+
(start + schema_offset, end + schema_offset)
|
| 177 |
+
for start, end in question.option_spans
|
| 178 |
+
),
|
| 179 |
+
option_ids=question.option_ids,
|
| 180 |
+
)
|
| 181 |
+
for question in questions
|
| 182 |
+
)
|
| 183 |
+
input_ids = tuple(prefix_ids + state_ids + schema_ids + suffix_ids)
|
| 184 |
+
if not input_ids or not shifted_questions:
|
| 185 |
+
raise ValueError("record produced no model input or questions")
|
| 186 |
+
return EncodedRecord(
|
| 187 |
+
input_ids=input_ids,
|
| 188 |
+
questions=shifted_questions,
|
| 189 |
+
record_id=str(record.get("id", "unknown")),
|
| 190 |
+
media=media,
|
| 191 |
+
)
|
| 192 |
+
|
| 193 |
+
|
| 194 |
+
def collate_records(
|
| 195 |
+
records: list[EncodedRecord],
|
| 196 |
+
pad_token_id: int,
|
| 197 |
+
device: torch.device,
|
| 198 |
+
) -> dict[str, Any]:
|
| 199 |
+
maximum_length = max(len(record.input_ids) for record in records)
|
| 200 |
+
input_ids = torch.full(
|
| 201 |
+
(len(records), maximum_length),
|
| 202 |
+
pad_token_id,
|
| 203 |
+
dtype=torch.long,
|
| 204 |
+
device=device,
|
| 205 |
+
)
|
| 206 |
+
attention_mask = torch.zeros(
|
| 207 |
+
(len(records), maximum_length),
|
| 208 |
+
dtype=torch.long,
|
| 209 |
+
device=device,
|
| 210 |
+
)
|
| 211 |
+
for index, record in enumerate(records):
|
| 212 |
+
length = len(record.input_ids)
|
| 213 |
+
input_ids[index, :length] = torch.tensor(record.input_ids, device=device)
|
| 214 |
+
attention_mask[index, :length] = 1
|
| 215 |
+
media: dict[str, torch.Tensor] = {}
|
| 216 |
+
for key in MEDIA_BATCH_KEYS:
|
| 217 |
+
values = [record.media[key] for record in records if record.media and key in record.media]
|
| 218 |
+
if values:
|
| 219 |
+
media[key] = torch.cat(values, dim=0).to(device)
|
| 220 |
+
for key in MEDIA_TOKEN_KEYS:
|
| 221 |
+
if any(record.media and key in record.media for record in records):
|
| 222 |
+
token_values = torch.zeros((len(records), maximum_length), dtype=torch.long, device=device)
|
| 223 |
+
for index, record in enumerate(records):
|
| 224 |
+
if record.media and key in record.media:
|
| 225 |
+
offset = record.media["token_offset"]
|
| 226 |
+
values = torch.tensor(record.media[key], dtype=torch.long, device=device)
|
| 227 |
+
token_values[index, offset : offset + len(values)] = values
|
| 228 |
+
media[key] = token_values
|
| 229 |
+
return {
|
| 230 |
+
"input_ids": input_ids,
|
| 231 |
+
"attention_mask": attention_mask,
|
| 232 |
+
"records": records,
|
| 233 |
+
"media": media,
|
| 234 |
+
}
|
| 235 |
+
|
| 236 |
+
|
| 237 |
+
class EvidenceRoutingLayer(torch.nn.Module):
|
| 238 |
+
def __init__(
|
| 239 |
+
self,
|
| 240 |
+
width: int,
|
| 241 |
+
heads: int,
|
| 242 |
+
feedforward: int,
|
| 243 |
+
dropout: float = 0.0,
|
| 244 |
+
) -> None:
|
| 245 |
+
super().__init__()
|
| 246 |
+
self.query_norm = torch.nn.LayerNorm(width)
|
| 247 |
+
self.memory_norm = torch.nn.LayerNorm(width)
|
| 248 |
+
self.attention = torch.nn.MultiheadAttention(
|
| 249 |
+
width,
|
| 250 |
+
heads,
|
| 251 |
+
dropout=dropout,
|
| 252 |
+
batch_first=True,
|
| 253 |
+
)
|
| 254 |
+
self.attention_dropout = torch.nn.Dropout(dropout)
|
| 255 |
+
self.feedforward_norm = torch.nn.LayerNorm(width)
|
| 256 |
+
self.feedforward = torch.nn.Sequential(
|
| 257 |
+
torch.nn.Linear(width, feedforward),
|
| 258 |
+
torch.nn.GELU(),
|
| 259 |
+
torch.nn.Dropout(dropout),
|
| 260 |
+
torch.nn.Linear(feedforward, width),
|
| 261 |
+
torch.nn.Dropout(dropout),
|
| 262 |
+
)
|
| 263 |
+
|
| 264 |
+
def forward(self, queries: torch.Tensor, memory: torch.Tensor) -> torch.Tensor:
|
| 265 |
+
normalized_queries = self.query_norm(queries)
|
| 266 |
+
routed, _ = self.attention(
|
| 267 |
+
normalized_queries,
|
| 268 |
+
self.memory_norm(memory),
|
| 269 |
+
self.memory_norm(memory),
|
| 270 |
+
need_weights=False,
|
| 271 |
+
)
|
| 272 |
+
queries = queries + self.attention_dropout(routed)
|
| 273 |
+
return queries + self.feedforward(self.feedforward_norm(queries))
|
| 274 |
+
|
| 275 |
+
|
| 276 |
+
class JointSchemaHead(torch.nn.Module):
|
| 277 |
+
def __init__(
|
| 278 |
+
self,
|
| 279 |
+
hidden_size: int,
|
| 280 |
+
width: int,
|
| 281 |
+
routing_layers: int,
|
| 282 |
+
layers: int,
|
| 283 |
+
heads: int,
|
| 284 |
+
feedforward: int,
|
| 285 |
+
dropout: float = 0.0,
|
| 286 |
+
) -> None:
|
| 287 |
+
super().__init__()
|
| 288 |
+
self.hidden_norm = torch.nn.LayerNorm(hidden_size)
|
| 289 |
+
self.memory_projection = torch.nn.Linear(hidden_size, width, bias=False)
|
| 290 |
+
self.question_projection = torch.nn.Linear(hidden_size, width, bias=False)
|
| 291 |
+
self.option_question_projection = torch.nn.Linear(hidden_size, width, bias=False)
|
| 292 |
+
self.global_projection = torch.nn.Linear(hidden_size, width, bias=False)
|
| 293 |
+
self.option_context_projection = torch.nn.Linear(hidden_size, width, bias=False)
|
| 294 |
+
self.option_lexical_projection = torch.nn.Linear(hidden_size, width, bias=False)
|
| 295 |
+
self.type_embedding = torch.nn.Embedding(3, width)
|
| 296 |
+
self.evidence_layers = torch.nn.ModuleList(
|
| 297 |
+
[
|
| 298 |
+
EvidenceRoutingLayer(
|
| 299 |
+
width=width,
|
| 300 |
+
heads=heads,
|
| 301 |
+
feedforward=feedforward,
|
| 302 |
+
dropout=dropout,
|
| 303 |
+
)
|
| 304 |
+
for _ in range(routing_layers)
|
| 305 |
+
]
|
| 306 |
+
)
|
| 307 |
+
self.option_summary_norm = torch.nn.LayerNorm(width)
|
| 308 |
+
self.layers = torch.nn.ModuleList(
|
| 309 |
+
[
|
| 310 |
+
torch.nn.TransformerDecoderLayer(
|
| 311 |
+
d_model=width,
|
| 312 |
+
nhead=heads,
|
| 313 |
+
dim_feedforward=feedforward,
|
| 314 |
+
dropout=dropout,
|
| 315 |
+
activation="gelu",
|
| 316 |
+
batch_first=True,
|
| 317 |
+
norm_first=True,
|
| 318 |
+
)
|
| 319 |
+
for _ in range(layers)
|
| 320 |
+
]
|
| 321 |
+
)
|
| 322 |
+
self.field_norm = torch.nn.LayerNorm(width)
|
| 323 |
+
self.option_norm = torch.nn.LayerNorm(width)
|
| 324 |
+
self.residual_scorer = torch.nn.Sequential(
|
| 325 |
+
torch.nn.Linear(width * 4, width),
|
| 326 |
+
torch.nn.GELU(),
|
| 327 |
+
torch.nn.Dropout(dropout),
|
| 328 |
+
torch.nn.Linear(width, 1),
|
| 329 |
+
)
|
| 330 |
+
self.prior_logit_scale = torch.nn.Parameter(torch.zeros(()))
|
| 331 |
+
self.joint_logit_scale = torch.nn.Parameter(torch.zeros(()))
|
| 332 |
+
self.residual_gate = torch.nn.Parameter(torch.zeros(()))
|
| 333 |
+
|
| 334 |
+
@staticmethod
|
| 335 |
+
def _mean_span(values: torch.Tensor, span: tuple[int, int]) -> torch.Tensor:
|
| 336 |
+
start, end = span
|
| 337 |
+
return values[start:end].mean(dim=0)
|
| 338 |
+
|
| 339 |
+
def forward(
|
| 340 |
+
self,
|
| 341 |
+
hidden_states: torch.Tensor,
|
| 342 |
+
input_ids: torch.Tensor,
|
| 343 |
+
attention_mask: torch.Tensor,
|
| 344 |
+
records: list[EncodedRecord],
|
| 345 |
+
output_embedding_weight: torch.Tensor,
|
| 346 |
+
) -> list[list[torch.Tensor]]:
|
| 347 |
+
results: list[list[torch.Tensor]] = []
|
| 348 |
+
normalized_hidden = self.hidden_norm(hidden_states)
|
| 349 |
+
for batch_index, record in enumerate(records):
|
| 350 |
+
sequence_length = int(attention_mask[batch_index].sum().item())
|
| 351 |
+
sequence_hidden = normalized_hidden[batch_index, :sequence_length]
|
| 352 |
+
memory = self.memory_projection(sequence_hidden).unsqueeze(0)
|
| 353 |
+
global_vector = sequence_hidden[-1]
|
| 354 |
+
question_vectors = torch.stack(
|
| 355 |
+
[
|
| 356 |
+
self._mean_span(sequence_hidden, question.question_span)
|
| 357 |
+
for question in record.questions
|
| 358 |
+
]
|
| 359 |
+
)
|
| 360 |
+
type_ids = torch.tensor(
|
| 361 |
+
[question.question_type for question in record.questions],
|
| 362 |
+
device=hidden_states.device,
|
| 363 |
+
)
|
| 364 |
+
option_contexts: list[torch.Tensor] = []
|
| 365 |
+
lexical_options: list[torch.Tensor] = []
|
| 366 |
+
option_counts = []
|
| 367 |
+
for question in record.questions:
|
| 368 |
+
context_vectors = torch.stack(
|
| 369 |
+
[
|
| 370 |
+
self._mean_span(sequence_hidden, span)
|
| 371 |
+
for span in question.option_spans
|
| 372 |
+
]
|
| 373 |
+
)
|
| 374 |
+
lexical_vectors = []
|
| 375 |
+
for start, end in question.option_spans:
|
| 376 |
+
token_ids = input_ids[batch_index, start:end]
|
| 377 |
+
lexical_vectors.append(output_embedding_weight[token_ids].mean(dim=0))
|
| 378 |
+
lexical = torch.stack(lexical_vectors)
|
| 379 |
+
option_contexts.append(context_vectors)
|
| 380 |
+
lexical_options.append(lexical)
|
| 381 |
+
option_counts.append(len(question.option_spans))
|
| 382 |
+
|
| 383 |
+
option_queries = []
|
| 384 |
+
for question_index, (context_vectors, lexical) in enumerate(
|
| 385 |
+
zip(option_contexts, lexical_options)
|
| 386 |
+
):
|
| 387 |
+
option_queries.append(
|
| 388 |
+
self.option_context_projection(context_vectors)
|
| 389 |
+
+ self.option_lexical_projection(lexical)
|
| 390 |
+
+ self.option_question_projection(
|
| 391 |
+
question_vectors[question_index]
|
| 392 |
+
).unsqueeze(0)
|
| 393 |
+
)
|
| 394 |
+
routed_options = torch.cat(option_queries, dim=0).unsqueeze(0)
|
| 395 |
+
for layer in self.evidence_layers:
|
| 396 |
+
routed_options = layer(routed_options, memory)
|
| 397 |
+
routed_options = routed_options[0]
|
| 398 |
+
split_options = list(torch.split(routed_options, option_counts, dim=0))
|
| 399 |
+
|
| 400 |
+
base_fields = self.question_projection(question_vectors)
|
| 401 |
+
option_summaries = []
|
| 402 |
+
for field, options in zip(base_fields, split_options):
|
| 403 |
+
routing_weights = torch.softmax(
|
| 404 |
+
torch.matmul(options, field) / math.sqrt(options.shape[-1]),
|
| 405 |
+
dim=0,
|
| 406 |
+
)
|
| 407 |
+
option_summaries.append(
|
| 408 |
+
torch.sum(routing_weights.unsqueeze(-1) * options, dim=0)
|
| 409 |
+
)
|
| 410 |
+
fields = (
|
| 411 |
+
base_fields
|
| 412 |
+
+ self.option_summary_norm(torch.stack(option_summaries))
|
| 413 |
+
+ self.global_projection(global_vector).unsqueeze(0)
|
| 414 |
+
+ self.type_embedding(type_ids)
|
| 415 |
+
)
|
| 416 |
+
fields = fields.unsqueeze(0)
|
| 417 |
+
for layer in self.layers:
|
| 418 |
+
fields = layer(fields, memory)
|
| 419 |
+
fields = self.field_norm(fields[0])
|
| 420 |
+
|
| 421 |
+
record_logits: list[torch.Tensor] = []
|
| 422 |
+
for field, question, lexical, routed in zip(
|
| 423 |
+
fields,
|
| 424 |
+
record.questions,
|
| 425 |
+
lexical_options,
|
| 426 |
+
split_options,
|
| 427 |
+
):
|
| 428 |
+
anchor = functional.normalize(
|
| 429 |
+
question_vectors[len(record_logits)] + global_vector,
|
| 430 |
+
dim=-1,
|
| 431 |
+
)
|
| 432 |
+
lexical_anchor = functional.normalize(lexical, dim=-1)
|
| 433 |
+
prior_scale = self.prior_logit_scale.clamp(max=math.log(100.0)).exp()
|
| 434 |
+
prior = prior_scale * torch.matmul(lexical_anchor, anchor)
|
| 435 |
+
options = self.option_norm(routed)
|
| 436 |
+
repeated_field = field.unsqueeze(0).expand_as(options)
|
| 437 |
+
cosine = functional.cosine_similarity(repeated_field, options, dim=-1)
|
| 438 |
+
features = torch.cat(
|
| 439 |
+
[
|
| 440 |
+
repeated_field,
|
| 441 |
+
options,
|
| 442 |
+
repeated_field * options,
|
| 443 |
+
torch.abs(repeated_field - options),
|
| 444 |
+
],
|
| 445 |
+
dim=-1,
|
| 446 |
+
)
|
| 447 |
+
residual = self.residual_scorer(features).squeeze(-1)
|
| 448 |
+
joint_scale = self.joint_logit_scale.clamp(max=math.log(100.0)).exp()
|
| 449 |
+
joint = joint_scale * cosine + residual
|
| 450 |
+
record_logits.append(
|
| 451 |
+
prior + torch.sigmoid(self.residual_gate) * joint
|
| 452 |
+
)
|
| 453 |
+
results.append(record_logits)
|
| 454 |
+
return results
|
| 455 |
+
|
| 456 |
+
|
| 457 |
+
class ClefModel(torch.nn.Module):
|
| 458 |
+
def __init__(self, language_model: Any, head: JointSchemaHead) -> None:
|
| 459 |
+
super().__init__()
|
| 460 |
+
self.language_model = language_model
|
| 461 |
+
self.head = head
|
| 462 |
+
|
| 463 |
+
def forward(self, batch: dict[str, Any]) -> list[list[torch.Tensor]]:
|
| 464 |
+
base_model = (
|
| 465 |
+
self.language_model.get_base_model()
|
| 466 |
+
if hasattr(self.language_model, "get_base_model")
|
| 467 |
+
else self.language_model
|
| 468 |
+
)
|
| 469 |
+
media = batch.get("media") or {}
|
| 470 |
+
text_model = base_model.model
|
| 471 |
+
if not media and hasattr(text_model, "language_model"):
|
| 472 |
+
text_model = text_model.language_model
|
| 473 |
+
outputs = text_model(
|
| 474 |
+
input_ids=batch["input_ids"],
|
| 475 |
+
attention_mask=batch["attention_mask"],
|
| 476 |
+
use_cache=False,
|
| 477 |
+
return_dict=True,
|
| 478 |
+
**media,
|
| 479 |
+
)
|
| 480 |
+
return self.head(
|
| 481 |
+
outputs.last_hidden_state,
|
| 482 |
+
batch["input_ids"],
|
| 483 |
+
batch["attention_mask"],
|
| 484 |
+
batch["records"],
|
| 485 |
+
base_model.get_output_embeddings().weight,
|
| 486 |
+
)
|
| 487 |
+
|
| 488 |
+
|
| 489 |
+
def load_release_model(
|
| 490 |
+
model_path: str | Path,
|
| 491 |
+
device: str | torch.device = "cuda",
|
| 492 |
+
dtype: torch.dtype = torch.bfloat16,
|
| 493 |
+
**from_pretrained_kwargs: Any,
|
| 494 |
+
) -> tuple[ClefModel, Any]:
|
| 495 |
+
"""Load a CLEF release (merged backbone, joint schema head, and processor)."""
|
| 496 |
+
from huggingface_hub import snapshot_download
|
| 497 |
+
from safetensors.torch import load_file
|
| 498 |
+
from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
|
| 499 |
+
|
| 500 |
+
path = Path(model_path)
|
| 501 |
+
if not path.is_dir():
|
| 502 |
+
path = Path(snapshot_download(str(model_path)))
|
| 503 |
+
backbone = Qwen3_5ForConditionalGeneration.from_pretrained(
|
| 504 |
+
path,
|
| 505 |
+
dtype=dtype,
|
| 506 |
+
device_map={"": str(device)},
|
| 507 |
+
**from_pretrained_kwargs,
|
| 508 |
+
)
|
| 509 |
+
backbone.config.use_cache = False
|
| 510 |
+
head_config = json.loads((path / "joint_head_config.json").read_text())
|
| 511 |
+
head = JointSchemaHead(**head_config)
|
| 512 |
+
head.load_state_dict(load_file(path / "joint_head.safetensors"), strict=True)
|
| 513 |
+
head = head.to(device=device, dtype=dtype)
|
| 514 |
+
processor = AutoProcessor.from_pretrained(path)
|
| 515 |
+
return ClefModel(backbone, head).eval(), processor
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b45a8e968141cdcc58fb71c9adfc258e2c77b5f062bc636c1fd5bc5d916b565
|
| 3 |
+
size 4942706120
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7590856c713eed844a2dcf48e6c43c4de165b788bc3f80e328311183cdbc7db8
|
| 3 |
+
size 4987757928
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6eac2467952c33361ed7dcb3c7959d1086bbe57201cd3749c3d769fdc17fe63
|
| 3 |
+
size 4954810240
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fcecc6556b39171238373a465f409794b7f821fb4cd1e6459e3a9c0fe317af7
|
| 3 |
+
size 3934446832
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,768 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 9409813744,
|
| 4 |
+
"total_size": 18819627488
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 406 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 407 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 408 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 409 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 410 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 411 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 412 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 413 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 414 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 415 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 416 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 417 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 418 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 419 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 420 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
|
| 421 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
|
| 422 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
|
| 423 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
|
| 424 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
|
| 425 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
|
| 426 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
|
| 427 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
|
| 428 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
|
| 429 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 430 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 431 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 432 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 433 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 730 |
+
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
| 731 |
+
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
| 732 |
+
"model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
|
| 733 |
+
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 734 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 735 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 736 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 737 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 738 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 739 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 740 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 741 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 742 |
+
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
| 743 |
+
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
| 744 |
+
"model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
|
| 745 |
+
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
| 746 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 747 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 748 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 749 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 750 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 751 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 752 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 753 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 754 |
+
"model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
|
| 755 |
+
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
| 756 |
+
"model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
|
| 757 |
+
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
| 758 |
+
"model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 759 |
+
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 760 |
+
"model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 761 |
+
"model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 762 |
+
"model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
|
| 763 |
+
"model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
|
| 764 |
+
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
| 765 |
+
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
| 766 |
+
"model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
|
| 767 |
+
}
|
| 768 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"model_max_length": 262144,
|
| 13 |
+
"model_specific_special_tokens": {
|
| 14 |
+
"audio_bos_token": "<|audio_start|>",
|
| 15 |
+
"audio_eos_token": "<|audio_end|>",
|
| 16 |
+
"audio_token": "<|audio_pad|>",
|
| 17 |
+
"image_token": "<|image_pad|>",
|
| 18 |
+
"video_token": "<|video_pad|>",
|
| 19 |
+
"vision_bos_token": "<|vision_start|>",
|
| 20 |
+
"vision_eos_token": "<|vision_end|>"
|
| 21 |
+
},
|
| 22 |
+
"pad_token": "<|endoftext|>",
|
| 23 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 24 |
+
"split_special_tokens": false,
|
| 25 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 26 |
+
"unk_token": null,
|
| 27 |
+
"video_token": "<|video_pad|>",
|
| 28 |
+
"vision_bos_token": "<|vision_start|>",
|
| 29 |
+
"vision_eos_token": "<|vision_end|>"
|
| 30 |
+
}
|