Add pplx-decider-4b (perplexity-ai/pplx-decider-flash-v1.2 @ 6d771ad, BF16, Apache-2.0)
Browse files- mlx/pplx-decider-4b/LICENSE +202 -0
- mlx/pplx-decider-4b/NOTICE +4 -0
- mlx/pplx-decider-4b/chat_template.jinja +154 -0
- mlx/pplx-decider-4b/config.json +113 -0
- mlx/pplx-decider-4b/decision_config.json +523 -0
- mlx/pplx-decider-4b/joint_config.json +9 -0
- mlx/pplx-decider-4b/model-00001-of-00002.safetensors +3 -0
- mlx/pplx-decider-4b/model-00002-of-00002.safetensors +3 -0
- mlx/pplx-decider-4b/model.safetensors.index.json +731 -0
- mlx/pplx-decider-4b/processor_config.json +61 -0
- mlx/pplx-decider-4b/readout.safetensors +3 -0
- mlx/pplx-decider-4b/tokenizer.json +3 -0
- mlx/pplx-decider-4b/tokenizer_config.json +37 -0
mlx/pplx-decider-4b/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.
|
mlx/pplx-decider-4b/NOTICE
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
pplx-decider-flash-v1.2
|
| 2 |
+
|
| 3 |
+
Derived from Qwen/Qwen3.5-4B, revision
|
| 4 |
+
851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a, under Apache License 2.0.
|
mlx/pplx-decider-4b/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 %}
|
mlx/pplx-decider-4b/config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5Model"
|
| 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": 2560,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 9216,
|
| 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": 1,
|
| 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": true,
|
| 84 |
+
"use_cache": true,
|
| 85 |
+
"vocab_size": 248320
|
| 86 |
+
},
|
| 87 |
+
"tie_word_embeddings": true,
|
| 88 |
+
"transformers_version": "5.17.0",
|
| 89 |
+
"video_token_id": 248057,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"deepstack_visual_indexes": [],
|
| 92 |
+
"depth": 24,
|
| 93 |
+
"dtype": "bfloat16",
|
| 94 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 95 |
+
"hidden_size": 1024,
|
| 96 |
+
"in_channels": 3,
|
| 97 |
+
"initializer_range": 0.02,
|
| 98 |
+
"intermediate_size": 4096,
|
| 99 |
+
"model_type": "qwen3_5_vision",
|
| 100 |
+
"num_heads": 16,
|
| 101 |
+
"num_position_embeddings": 2304,
|
| 102 |
+
"out_hidden_size": 2560,
|
| 103 |
+
"patch_size": 16,
|
| 104 |
+
"rope_parameters": {
|
| 105 |
+
"rope_theta": 10000.0,
|
| 106 |
+
"rope_type": "axial"
|
| 107 |
+
},
|
| 108 |
+
"spatial_merge_size": 2,
|
| 109 |
+
"temporal_patch_size": 2
|
| 110 |
+
},
|
| 111 |
+
"vision_end_token_id": 248054,
|
| 112 |
+
"vision_start_token_id": 248053
|
| 113 |
+
}
|
mlx/pplx-decider-4b/decision_config.json
ADDED
|
@@ -0,0 +1,523 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"format_version": 2,
|
| 3 |
+
"base_model": "Qwen/Qwen3.5-4B",
|
| 4 |
+
"revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
|
| 5 |
+
"attention_mode": "noncausal_full_attention",
|
| 6 |
+
"pooling": "last",
|
| 7 |
+
"temperature": 1.5539092221462472,
|
| 8 |
+
"max_pixels": 1638400,
|
| 9 |
+
"codes": [
|
| 10 |
+
"A",
|
| 11 |
+
"B",
|
| 12 |
+
"C",
|
| 13 |
+
"D",
|
| 14 |
+
"E",
|
| 15 |
+
"F",
|
| 16 |
+
"G",
|
| 17 |
+
"H",
|
| 18 |
+
"I",
|
| 19 |
+
"J",
|
| 20 |
+
"K",
|
| 21 |
+
"L",
|
| 22 |
+
"M",
|
| 23 |
+
"N",
|
| 24 |
+
"O",
|
| 25 |
+
"P",
|
| 26 |
+
"Q",
|
| 27 |
+
"R",
|
| 28 |
+
"S",
|
| 29 |
+
"T",
|
| 30 |
+
"U",
|
| 31 |
+
"V",
|
| 32 |
+
"W",
|
| 33 |
+
"X",
|
| 34 |
+
"Y",
|
| 35 |
+
"Z",
|
| 36 |
+
"AA",
|
| 37 |
+
"AB",
|
| 38 |
+
"AC",
|
| 39 |
+
"AD",
|
| 40 |
+
"AE",
|
| 41 |
+
"AF",
|
| 42 |
+
"AG",
|
| 43 |
+
"AH",
|
| 44 |
+
"AI",
|
| 45 |
+
"AJ",
|
| 46 |
+
"AK",
|
| 47 |
+
"AL",
|
| 48 |
+
"AM",
|
| 49 |
+
"AN",
|
| 50 |
+
"AO",
|
| 51 |
+
"AP",
|
| 52 |
+
"AQ",
|
| 53 |
+
"AR",
|
| 54 |
+
"AS",
|
| 55 |
+
"AT",
|
| 56 |
+
"AU",
|
| 57 |
+
"AV",
|
| 58 |
+
"AW",
|
| 59 |
+
"AX",
|
| 60 |
+
"AY",
|
| 61 |
+
"AZ",
|
| 62 |
+
"BA",
|
| 63 |
+
"BB",
|
| 64 |
+
"BC",
|
| 65 |
+
"BD",
|
| 66 |
+
"BE",
|
| 67 |
+
"BF",
|
| 68 |
+
"BG",
|
| 69 |
+
"BH",
|
| 70 |
+
"BI",
|
| 71 |
+
"BJ",
|
| 72 |
+
"BK",
|
| 73 |
+
"BL",
|
| 74 |
+
"BM",
|
| 75 |
+
"BN",
|
| 76 |
+
"BO",
|
| 77 |
+
"BP",
|
| 78 |
+
"BR",
|
| 79 |
+
"BS",
|
| 80 |
+
"BT",
|
| 81 |
+
"BU",
|
| 82 |
+
"BV",
|
| 83 |
+
"BW",
|
| 84 |
+
"BX",
|
| 85 |
+
"BY",
|
| 86 |
+
"CA",
|
| 87 |
+
"CB",
|
| 88 |
+
"CC",
|
| 89 |
+
"CD",
|
| 90 |
+
"CE",
|
| 91 |
+
"CF",
|
| 92 |
+
"CG",
|
| 93 |
+
"CH",
|
| 94 |
+
"CI",
|
| 95 |
+
"CK",
|
| 96 |
+
"CL",
|
| 97 |
+
"CM",
|
| 98 |
+
"CN",
|
| 99 |
+
"CO",
|
| 100 |
+
"CP",
|
| 101 |
+
"CR",
|
| 102 |
+
"CS",
|
| 103 |
+
"CT",
|
| 104 |
+
"CU",
|
| 105 |
+
"CV",
|
| 106 |
+
"CW",
|
| 107 |
+
"CX",
|
| 108 |
+
"CY",
|
| 109 |
+
"DA",
|
| 110 |
+
"DB",
|
| 111 |
+
"DC",
|
| 112 |
+
"DD",
|
| 113 |
+
"DE",
|
| 114 |
+
"DF",
|
| 115 |
+
"DG",
|
| 116 |
+
"DH",
|
| 117 |
+
"DI",
|
| 118 |
+
"DJ",
|
| 119 |
+
"DK",
|
| 120 |
+
"DL",
|
| 121 |
+
"DM",
|
| 122 |
+
"DN",
|
| 123 |
+
"DO",
|
| 124 |
+
"DP",
|
| 125 |
+
"DR",
|
| 126 |
+
"DS",
|
| 127 |
+
"DT",
|
| 128 |
+
"DU",
|
| 129 |
+
"DV",
|
| 130 |
+
"DW",
|
| 131 |
+
"DX",
|
| 132 |
+
"DY",
|
| 133 |
+
"EA",
|
| 134 |
+
"EB",
|
| 135 |
+
"EC",
|
| 136 |
+
"ED",
|
| 137 |
+
"EE",
|
| 138 |
+
"EF",
|
| 139 |
+
"EG",
|
| 140 |
+
"EH",
|
| 141 |
+
"EI",
|
| 142 |
+
"EK",
|
| 143 |
+
"EL",
|
| 144 |
+
"EM",
|
| 145 |
+
"EN",
|
| 146 |
+
"EO",
|
| 147 |
+
"EP",
|
| 148 |
+
"EQ",
|
| 149 |
+
"ER",
|
| 150 |
+
"ES",
|
| 151 |
+
"ET",
|
| 152 |
+
"EU",
|
| 153 |
+
"EV",
|
| 154 |
+
"EW",
|
| 155 |
+
"EX",
|
| 156 |
+
"EZ",
|
| 157 |
+
"FA",
|
| 158 |
+
"FB",
|
| 159 |
+
"FC",
|
| 160 |
+
"FD",
|
| 161 |
+
"FE",
|
| 162 |
+
"FF",
|
| 163 |
+
"FG",
|
| 164 |
+
"FH",
|
| 165 |
+
"FI",
|
| 166 |
+
"FK",
|
| 167 |
+
"FL",
|
| 168 |
+
"FM",
|
| 169 |
+
"FN",
|
| 170 |
+
"FO",
|
| 171 |
+
"FP",
|
| 172 |
+
"FR",
|
| 173 |
+
"FS",
|
| 174 |
+
"FT",
|
| 175 |
+
"FU",
|
| 176 |
+
"FW",
|
| 177 |
+
"FX",
|
| 178 |
+
"FY",
|
| 179 |
+
"GA",
|
| 180 |
+
"GB",
|
| 181 |
+
"GC",
|
| 182 |
+
"GD",
|
| 183 |
+
"GE",
|
| 184 |
+
"GF",
|
| 185 |
+
"GG",
|
| 186 |
+
"GH",
|
| 187 |
+
"GI",
|
| 188 |
+
"GL",
|
| 189 |
+
"GM",
|
| 190 |
+
"GN",
|
| 191 |
+
"GO",
|
| 192 |
+
"GP",
|
| 193 |
+
"GR",
|
| 194 |
+
"GS",
|
| 195 |
+
"GT",
|
| 196 |
+
"GU",
|
| 197 |
+
"GV",
|
| 198 |
+
"GW",
|
| 199 |
+
"GX",
|
| 200 |
+
"GY",
|
| 201 |
+
"HA",
|
| 202 |
+
"HB",
|
| 203 |
+
"HC",
|
| 204 |
+
"HD",
|
| 205 |
+
"HE",
|
| 206 |
+
"HF",
|
| 207 |
+
"HG",
|
| 208 |
+
"HH",
|
| 209 |
+
"HI",
|
| 210 |
+
"HK",
|
| 211 |
+
"HL",
|
| 212 |
+
"HM",
|
| 213 |
+
"HN",
|
| 214 |
+
"HO",
|
| 215 |
+
"HP",
|
| 216 |
+
"HQ",
|
| 217 |
+
"HR",
|
| 218 |
+
"HS",
|
| 219 |
+
"HT",
|
| 220 |
+
"HU",
|
| 221 |
+
"HV",
|
| 222 |
+
"HW",
|
| 223 |
+
"HX",
|
| 224 |
+
"HY",
|
| 225 |
+
"HZ",
|
| 226 |
+
"IA",
|
| 227 |
+
"IB",
|
| 228 |
+
"IC",
|
| 229 |
+
"ID",
|
| 230 |
+
"IE",
|
| 231 |
+
"IF",
|
| 232 |
+
"IG",
|
| 233 |
+
"IH",
|
| 234 |
+
"II",
|
| 235 |
+
"IJ",
|
| 236 |
+
"IK",
|
| 237 |
+
"IL",
|
| 238 |
+
"IM",
|
| 239 |
+
"IN",
|
| 240 |
+
"IO",
|
| 241 |
+
"IP",
|
| 242 |
+
"IQ",
|
| 243 |
+
"IR",
|
| 244 |
+
"IS",
|
| 245 |
+
"IT",
|
| 246 |
+
"IU",
|
| 247 |
+
"IV",
|
| 248 |
+
"IW",
|
| 249 |
+
"IX",
|
| 250 |
+
"IZ",
|
| 251 |
+
"JA",
|
| 252 |
+
"JB",
|
| 253 |
+
"JC",
|
| 254 |
+
"JD",
|
| 255 |
+
"JE",
|
| 256 |
+
"JI",
|
| 257 |
+
"JJ",
|
| 258 |
+
"JK",
|
| 259 |
+
"JM",
|
| 260 |
+
"JO",
|
| 261 |
+
"JP",
|
| 262 |
+
"JR",
|
| 263 |
+
"JS",
|
| 264 |
+
"JT"
|
| 265 |
+
],
|
| 266 |
+
"token_ids": [
|
| 267 |
+
32,
|
| 268 |
+
33,
|
| 269 |
+
34,
|
| 270 |
+
35,
|
| 271 |
+
36,
|
| 272 |
+
37,
|
| 273 |
+
38,
|
| 274 |
+
39,
|
| 275 |
+
40,
|
| 276 |
+
41,
|
| 277 |
+
42,
|
| 278 |
+
43,
|
| 279 |
+
44,
|
| 280 |
+
45,
|
| 281 |
+
46,
|
| 282 |
+
47,
|
| 283 |
+
48,
|
| 284 |
+
49,
|
| 285 |
+
50,
|
| 286 |
+
51,
|
| 287 |
+
52,
|
| 288 |
+
53,
|
| 289 |
+
54,
|
| 290 |
+
55,
|
| 291 |
+
56,
|
| 292 |
+
57,
|
| 293 |
+
5840,
|
| 294 |
+
1803,
|
| 295 |
+
1646,
|
| 296 |
+
1745,
|
| 297 |
+
13276,
|
| 298 |
+
8018,
|
| 299 |
+
1825,
|
| 300 |
+
28946,
|
| 301 |
+
15015,
|
| 302 |
+
29595,
|
| 303 |
+
11568,
|
| 304 |
+
939,
|
| 305 |
+
1354,
|
| 306 |
+
1058,
|
| 307 |
+
18183,
|
| 308 |
+
2456,
|
| 309 |
+
88898,
|
| 310 |
+
905,
|
| 311 |
+
1846,
|
| 312 |
+
802,
|
| 313 |
+
33869,
|
| 314 |
+
7839,
|
| 315 |
+
14006,
|
| 316 |
+
2860,
|
| 317 |
+
2926,
|
| 318 |
+
22828,
|
| 319 |
+
6844,
|
| 320 |
+
9798,
|
| 321 |
+
4738,
|
| 322 |
+
9265,
|
| 323 |
+
11261,
|
| 324 |
+
19278,
|
| 325 |
+
36513,
|
| 326 |
+
93801,
|
| 327 |
+
8335,
|
| 328 |
+
14544,
|
| 329 |
+
85266,
|
| 330 |
+
9110,
|
| 331 |
+
28000,
|
| 332 |
+
15137,
|
| 333 |
+
4525,
|
| 334 |
+
25261,
|
| 335 |
+
12717,
|
| 336 |
+
7116,
|
| 337 |
+
17078,
|
| 338 |
+
14497,
|
| 339 |
+
57339,
|
| 340 |
+
74909,
|
| 341 |
+
52072,
|
| 342 |
+
19305,
|
| 343 |
+
4887,
|
| 344 |
+
12607,
|
| 345 |
+
3580,
|
| 346 |
+
6281,
|
| 347 |
+
2036,
|
| 348 |
+
9362,
|
| 349 |
+
8533,
|
| 350 |
+
2080,
|
| 351 |
+
10911,
|
| 352 |
+
2925,
|
| 353 |
+
3040,
|
| 354 |
+
9690,
|
| 355 |
+
27731,
|
| 356 |
+
8023,
|
| 357 |
+
6901,
|
| 358 |
+
8702,
|
| 359 |
+
6211,
|
| 360 |
+
1123,
|
| 361 |
+
16307,
|
| 362 |
+
18990,
|
| 363 |
+
64045,
|
| 364 |
+
63037,
|
| 365 |
+
33380,
|
| 366 |
+
6151,
|
| 367 |
+
3392,
|
| 368 |
+
5449,
|
| 369 |
+
3967,
|
| 370 |
+
1113,
|
| 371 |
+
5095,
|
| 372 |
+
51923,
|
| 373 |
+
49600,
|
| 374 |
+
17099,
|
| 375 |
+
51483,
|
| 376 |
+
17756,
|
| 377 |
+
16037,
|
| 378 |
+
8135,
|
| 379 |
+
30237,
|
| 380 |
+
5683,
|
| 381 |
+
9992,
|
| 382 |
+
7444,
|
| 383 |
+
5751,
|
| 384 |
+
10284,
|
| 385 |
+
20887,
|
| 386 |
+
59884,
|
| 387 |
+
52396,
|
| 388 |
+
16103,
|
| 389 |
+
67547,
|
| 390 |
+
18535,
|
| 391 |
+
8006,
|
| 392 |
+
7263,
|
| 393 |
+
1425,
|
| 394 |
+
6878,
|
| 395 |
+
14453,
|
| 396 |
+
9097,
|
| 397 |
+
44072,
|
| 398 |
+
76089,
|
| 399 |
+
68720,
|
| 400 |
+
2662,
|
| 401 |
+
2629,
|
| 402 |
+
923,
|
| 403 |
+
6548,
|
| 404 |
+
8924,
|
| 405 |
+
52194,
|
| 406 |
+
622,
|
| 407 |
+
1515,
|
| 408 |
+
1300,
|
| 409 |
+
37523,
|
| 410 |
+
44473,
|
| 411 |
+
36530,
|
| 412 |
+
3152,
|
| 413 |
+
93924,
|
| 414 |
+
3505,
|
| 415 |
+
15731,
|
| 416 |
+
6542,
|
| 417 |
+
14176,
|
| 418 |
+
11091,
|
| 419 |
+
1686,
|
| 420 |
+
11660,
|
| 421 |
+
80440,
|
| 422 |
+
18836,
|
| 423 |
+
26132,
|
| 424 |
+
5934,
|
| 425 |
+
24794,
|
| 426 |
+
40229,
|
| 427 |
+
3660,
|
| 428 |
+
11361,
|
| 429 |
+
10191,
|
| 430 |
+
8225,
|
| 431 |
+
3860,
|
| 432 |
+
78413,
|
| 433 |
+
17680,
|
| 434 |
+
15900,
|
| 435 |
+
78138,
|
| 436 |
+
15653,
|
| 437 |
+
5213,
|
| 438 |
+
22150,
|
| 439 |
+
39500,
|
| 440 |
+
10460,
|
| 441 |
+
35131,
|
| 442 |
+
21563,
|
| 443 |
+
43194,
|
| 444 |
+
27127,
|
| 445 |
+
3697,
|
| 446 |
+
20011,
|
| 447 |
+
24368,
|
| 448 |
+
15058,
|
| 449 |
+
23658,
|
| 450 |
+
8362,
|
| 451 |
+
16035,
|
| 452 |
+
24583,
|
| 453 |
+
52857,
|
| 454 |
+
38403,
|
| 455 |
+
60456,
|
| 456 |
+
81519,
|
| 457 |
+
40097,
|
| 458 |
+
16522,
|
| 459 |
+
29722,
|
| 460 |
+
21756,
|
| 461 |
+
18567,
|
| 462 |
+
1736,
|
| 463 |
+
48043,
|
| 464 |
+
87013,
|
| 465 |
+
22456,
|
| 466 |
+
23165,
|
| 467 |
+
55523,
|
| 468 |
+
13097,
|
| 469 |
+
50397,
|
| 470 |
+
41741,
|
| 471 |
+
23073,
|
| 472 |
+
6401,
|
| 473 |
+
86538,
|
| 474 |
+
16585,
|
| 475 |
+
11622,
|
| 476 |
+
2464,
|
| 477 |
+
84982,
|
| 478 |
+
75516,
|
| 479 |
+
36984,
|
| 480 |
+
58795,
|
| 481 |
+
47217,
|
| 482 |
+
59675,
|
| 483 |
+
5681,
|
| 484 |
+
3151,
|
| 485 |
+
1271,
|
| 486 |
+
887,
|
| 487 |
+
5203,
|
| 488 |
+
2685,
|
| 489 |
+
1849,
|
| 490 |
+
72470,
|
| 491 |
+
5370,
|
| 492 |
+
74063,
|
| 493 |
+
27629,
|
| 494 |
+
1655,
|
| 495 |
+
1728,
|
| 496 |
+
669,
|
| 497 |
+
3682,
|
| 498 |
+
3191,
|
| 499 |
+
59865,
|
| 500 |
+
2712,
|
| 501 |
+
1580,
|
| 502 |
+
922,
|
| 503 |
+
77243,
|
| 504 |
+
2990,
|
| 505 |
+
78493,
|
| 506 |
+
5228,
|
| 507 |
+
2750,
|
| 508 |
+
42711,
|
| 509 |
+
44568,
|
| 510 |
+
56402,
|
| 511 |
+
48236,
|
| 512 |
+
38993,
|
| 513 |
+
43559,
|
| 514 |
+
61250,
|
| 515 |
+
32942,
|
| 516 |
+
86302,
|
| 517 |
+
25310,
|
| 518 |
+
26313,
|
| 519 |
+
81770,
|
| 520 |
+
12185,
|
| 521 |
+
78382
|
| 522 |
+
]
|
| 523 |
+
}
|
mlx/pplx-decider-4b/joint_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": 3,
|
| 3 |
+
"template": "joint-question-inline-readout-v1",
|
| 4 |
+
"marker": "<|fim_suffix|>",
|
| 5 |
+
"readout_offset": 0,
|
| 6 |
+
"max_questions": null,
|
| 7 |
+
"max_length": null,
|
| 8 |
+
"usage": "nonpadding_joint_sequence_including_template_and_image_positions"
|
| 9 |
+
}
|
mlx/pplx-decider-4b/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c1a0c1ab331c7aec1b4b7932eabf80593b56c694fe2b779209c0e0413df1cef
|
| 3 |
+
size 4972946624
|
mlx/pplx-decider-4b/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ba8301660e066f5849b60b1a36a242fc54ca18dd9bd526fdcbc50889171b70
|
| 3 |
+
size 4105669472
|
mlx/pplx-decider-4b/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,731 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4539265536,
|
| 4 |
+
"total_size": 9078531072
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 10 |
+
"language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 12 |
+
"language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 24 |
+
"language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 38 |
+
"language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 63 |
+
"language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 77 |
+
"language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 91 |
+
"language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 93 |
+
"language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 116 |
+
"language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"language_model.layers.17.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 130 |
+
"language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 132 |
+
"language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"language_model.layers.18.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 144 |
+
"language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 146 |
+
"language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 169 |
+
"language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"language_model.layers.20.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 183 |
+
"language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 185 |
+
"language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"language_model.layers.21.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 197 |
+
"language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 199 |
+
"language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"language_model.layers.22.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 211 |
+
"language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 213 |
+
"language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"language_model.layers.24.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 236 |
+
"language_model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"language_model.layers.24.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 238 |
+
"language_model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"language_model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"language_model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"language_model.layers.24.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"language_model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"language_model.layers.25.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 250 |
+
"language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"language_model.layers.25.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 252 |
+
"language_model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"language_model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"language_model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"language_model.layers.25.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 263 |
+
"language_model.layers.26.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 264 |
+
"language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 265 |
+
"language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 266 |
+
"language_model.layers.26.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 267 |
+
"language_model.layers.26.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 268 |
+
"language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 269 |
+
"language_model.layers.26.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 270 |
+
"language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 271 |
+
"language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 272 |
+
"language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"language_model.layers.28.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 289 |
+
"language_model.layers.28.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"language_model.layers.28.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 291 |
+
"language_model.layers.28.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"language_model.layers.28.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"language_model.layers.28.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"language_model.layers.28.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"language_model.layers.28.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"language_model.layers.29.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 303 |
+
"language_model.layers.29.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"language_model.layers.29.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 305 |
+
"language_model.layers.29.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"language_model.layers.29.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"language_model.layers.29.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"language_model.layers.29.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"language_model.layers.29.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"language_model.layers.30.linear_attn.A_log": "model-00002-of-00002.safetensors",
|
| 328 |
+
"language_model.layers.30.linear_attn.conv1d.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"language_model.layers.30.linear_attn.dt_bias": "model-00002-of-00002.safetensors",
|
| 330 |
+
"language_model.layers.30.linear_attn.in_proj_a.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"language_model.layers.30.linear_attn.in_proj_b.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"language_model.layers.30.linear_attn.in_proj_z.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"language_model.layers.30.linear_attn.norm.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"language_model.layers.30.linear_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 340 |
+
"language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 341 |
+
"language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 342 |
+
"language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 343 |
+
"language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 344 |
+
"language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 345 |
+
"language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 346 |
+
"language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 347 |
+
"language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 348 |
+
"language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 350 |
+
"language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 353 |
+
"language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 367 |
+
"language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 369 |
+
"language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 381 |
+
"language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 406 |
+
"language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
|
| 420 |
+
"language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 433 |
+
"visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 434 |
+
"visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 435 |
+
"visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 436 |
+
"visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 437 |
+
"visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 438 |
+
"visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 439 |
+
"visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 440 |
+
"visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 441 |
+
"visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
|
| 442 |
+
"visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
|
| 443 |
+
"visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors",
|
| 444 |
+
"visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors",
|
| 445 |
+
"visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 446 |
+
"visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 447 |
+
"visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 448 |
+
"visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 449 |
+
"visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 450 |
+
"visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 451 |
+
"visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 452 |
+
"visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 453 |
+
"visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
|
| 454 |
+
"visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
|
| 455 |
+
"visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors",
|
| 456 |
+
"visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors",
|
| 457 |
+
"visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 458 |
+
"visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 459 |
+
"visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 460 |
+
"visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 461 |
+
"visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 462 |
+
"visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 463 |
+
"visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 464 |
+
"visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 465 |
+
"visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
|
| 466 |
+
"visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
|
| 467 |
+
"visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
|
| 468 |
+
"visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
|
| 469 |
+
"visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 470 |
+
"visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 471 |
+
"visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 472 |
+
"visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 473 |
+
"visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 474 |
+
"visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 475 |
+
"visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 476 |
+
"visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 477 |
+
"visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
|
| 478 |
+
"visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
|
| 479 |
+
"visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
|
| 480 |
+
"visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
|
| 481 |
+
"visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 482 |
+
"visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 483 |
+
"visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 484 |
+
"visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 485 |
+
"visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 486 |
+
"visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 487 |
+
"visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 488 |
+
"visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 489 |
+
"visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
|
| 490 |
+
"visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
|
| 491 |
+
"visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
|
| 492 |
+
"visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
|
| 493 |
+
"visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 494 |
+
"visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 495 |
+
"visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 496 |
+
"visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 497 |
+
"visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 498 |
+
"visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 499 |
+
"visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 500 |
+
"visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 501 |
+
"visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
|
| 502 |
+
"visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
|
| 503 |
+
"visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
|
| 504 |
+
"visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
|
| 505 |
+
"visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 506 |
+
"visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 507 |
+
"visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 508 |
+
"visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 509 |
+
"visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 510 |
+
"visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 511 |
+
"visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 512 |
+
"visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 513 |
+
"visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
|
| 514 |
+
"visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
|
| 515 |
+
"visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
|
| 516 |
+
"visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
|
| 517 |
+
"visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 518 |
+
"visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 519 |
+
"visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 520 |
+
"visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 521 |
+
"visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 522 |
+
"visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 523 |
+
"visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 524 |
+
"visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 525 |
+
"visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
|
| 526 |
+
"visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
|
| 527 |
+
"visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
|
| 528 |
+
"visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
|
| 529 |
+
"visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 530 |
+
"visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 531 |
+
"visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 532 |
+
"visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 533 |
+
"visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 534 |
+
"visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 535 |
+
"visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 536 |
+
"visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 537 |
+
"visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
|
| 538 |
+
"visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
|
| 539 |
+
"visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
|
| 540 |
+
"visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
|
| 541 |
+
"visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 542 |
+
"visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 543 |
+
"visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 544 |
+
"visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 545 |
+
"visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 546 |
+
"visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 547 |
+
"visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 548 |
+
"visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 549 |
+
"visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
|
| 550 |
+
"visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
|
| 551 |
+
"visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
|
| 552 |
+
"visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
|
| 553 |
+
"visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 554 |
+
"visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 555 |
+
"visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 556 |
+
"visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 557 |
+
"visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 558 |
+
"visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 559 |
+
"visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 560 |
+
"visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 561 |
+
"visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
|
| 562 |
+
"visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
|
| 563 |
+
"visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
|
| 564 |
+
"visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
|
| 565 |
+
"visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 566 |
+
"visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 567 |
+
"visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 568 |
+
"visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 569 |
+
"visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 570 |
+
"visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 571 |
+
"visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 572 |
+
"visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 573 |
+
"visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
|
| 574 |
+
"visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
|
| 575 |
+
"visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
|
| 576 |
+
"visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
|
| 577 |
+
"visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 578 |
+
"visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 579 |
+
"visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 580 |
+
"visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 581 |
+
"visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 582 |
+
"visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 583 |
+
"visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 584 |
+
"visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 585 |
+
"visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
|
| 586 |
+
"visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
|
| 587 |
+
"visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors",
|
| 588 |
+
"visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors",
|
| 589 |
+
"visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 590 |
+
"visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 591 |
+
"visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 592 |
+
"visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 593 |
+
"visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 594 |
+
"visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 595 |
+
"visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 596 |
+
"visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 597 |
+
"visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
|
| 598 |
+
"visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
|
| 599 |
+
"visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
|
| 600 |
+
"visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
|
| 601 |
+
"visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 602 |
+
"visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 603 |
+
"visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 604 |
+
"visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 605 |
+
"visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 606 |
+
"visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 607 |
+
"visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 608 |
+
"visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 609 |
+
"visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
|
| 610 |
+
"visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
|
| 611 |
+
"visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
|
| 612 |
+
"visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
|
| 613 |
+
"visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 614 |
+
"visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 615 |
+
"visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 616 |
+
"visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 617 |
+
"visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 618 |
+
"visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 619 |
+
"visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 620 |
+
"visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 621 |
+
"visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
|
| 622 |
+
"visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
|
| 623 |
+
"visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
|
| 624 |
+
"visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
|
| 625 |
+
"visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 626 |
+
"visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 627 |
+
"visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 628 |
+
"visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 629 |
+
"visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 630 |
+
"visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 631 |
+
"visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 632 |
+
"visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 633 |
+
"visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
|
| 634 |
+
"visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
|
| 635 |
+
"visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
|
| 636 |
+
"visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
|
| 637 |
+
"visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 638 |
+
"visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 639 |
+
"visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 640 |
+
"visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 641 |
+
"visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 642 |
+
"visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 643 |
+
"visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 644 |
+
"visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 645 |
+
"visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
|
| 646 |
+
"visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
|
| 647 |
+
"visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors",
|
| 648 |
+
"visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors",
|
| 649 |
+
"visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 650 |
+
"visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 651 |
+
"visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 652 |
+
"visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 653 |
+
"visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 654 |
+
"visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 655 |
+
"visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 656 |
+
"visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 657 |
+
"visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors",
|
| 658 |
+
"visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors",
|
| 659 |
+
"visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors",
|
| 660 |
+
"visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 662 |
+
"visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 664 |
+
"visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 666 |
+
"visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 668 |
+
"visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
|
| 670 |
+
"visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
|
| 672 |
+
"visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
|
| 673 |
+
"visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 674 |
+
"visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 676 |
+
"visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 677 |
+
"visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 678 |
+
"visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 680 |
+
"visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
|
| 682 |
+
"visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
|
| 684 |
+
"visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 686 |
+
"visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 687 |
+
"visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 688 |
+
"visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 689 |
+
"visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 690 |
+
"visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 692 |
+
"visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 693 |
+
"visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
|
| 694 |
+
"visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
|
| 696 |
+
"visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 698 |
+
"visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 699 |
+
"visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 700 |
+
"visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 702 |
+
"visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 703 |
+
"visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 704 |
+
"visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 705 |
+
"visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
|
| 706 |
+
"visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
|
| 708 |
+
"visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
|
| 710 |
+
"visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
|
| 711 |
+
"visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
|
| 712 |
+
"visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
|
| 713 |
+
"visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 714 |
+
"visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 715 |
+
"visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 716 |
+
"visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 717 |
+
"visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
|
| 718 |
+
"visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
|
| 719 |
+
"visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
|
| 720 |
+
"visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
|
| 721 |
+
"visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
|
| 722 |
+
"visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
|
| 723 |
+
"visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
|
| 724 |
+
"visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
|
| 725 |
+
"visual.merger.norm.bias": "model-00002-of-00002.safetensors",
|
| 726 |
+
"visual.merger.norm.weight": "model-00002-of-00002.safetensors",
|
| 727 |
+
"visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
|
| 728 |
+
"visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
|
| 729 |
+
"visual.pos_embed.weight": "model-00002-of-00002.safetensors"
|
| 730 |
+
}
|
| 731 |
+
}
|
mlx/pplx-decider-4b/processor_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1638400,
|
| 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 |
+
"max_video_tokens": 768,
|
| 48 |
+
"merge_size": 2,
|
| 49 |
+
"min_frames": 4,
|
| 50 |
+
"patch_size": 16,
|
| 51 |
+
"resample": 3,
|
| 52 |
+
"rescale_factor": 0.00392156862745098,
|
| 53 |
+
"return_metadata": false,
|
| 54 |
+
"size": {
|
| 55 |
+
"longest_edge": 25165824,
|
| 56 |
+
"shortest_edge": 4096
|
| 57 |
+
},
|
| 58 |
+
"temporal_patch_size": 2,
|
| 59 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 60 |
+
}
|
| 61 |
+
}
|
mlx/pplx-decider-4b/readout.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6751578171026190d4db8078e97162b404fd984646e0e9aec13844e4dd5b1711
|
| 3 |
+
size 1305712
|
mlx/pplx-decider-4b/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f32ce20dc35f57a7f9ad1eac03525bd7d30f9df8cea6507e958279cc3657706
|
| 3 |
+
size 19989492
|
mlx/pplx-decider-4b/tokenizer_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": true,
|
| 14 |
+
"max_length": null,
|
| 15 |
+
"model_max_length": 262144,
|
| 16 |
+
"model_specific_special_tokens": {
|
| 17 |
+
"audio_bos_token": "<|audio_start|>",
|
| 18 |
+
"audio_eos_token": "<|audio_end|>",
|
| 19 |
+
"audio_token": "<|audio_pad|>",
|
| 20 |
+
"image_token": "<|image_pad|>",
|
| 21 |
+
"video_token": "<|video_pad|>",
|
| 22 |
+
"vision_bos_token": "<|vision_start|>",
|
| 23 |
+
"vision_eos_token": "<|vision_end|>"
|
| 24 |
+
},
|
| 25 |
+
"pad_to_multiple_of": null,
|
| 26 |
+
"pad_token": "<|endoftext|>",
|
| 27 |
+
"pad_token_type_id": 0,
|
| 28 |
+
"padding_side": "left",
|
| 29 |
+
"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+",
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"split_special_tokens": false,
|
| 32 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 33 |
+
"unk_token": null,
|
| 34 |
+
"video_token": "<|video_pad|>",
|
| 35 |
+
"vision_bos_token": "<|vision_start|>",
|
| 36 |
+
"vision_eos_token": "<|vision_end|>"
|
| 37 |
+
}
|