Commit ·
b77518f
0
Parent(s):
init
Browse files- .gitattributes +38 -0
- LICENSE +177 -0
- NOTICE.txt +4 -0
- README.md +168 -0
- added_tokens.json +28 -0
- assets/bonsai-logo.svg +1 -0
- assets/frontier.png +3 -0
- assets/frontier.svg +191 -0
- chat_template.jinja +86 -0
- config.json +135 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- model.safetensors.index.json +911 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +14 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
frontier.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
assets/frontier.png filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Apache License
|
| 2 |
+
Version 2.0, January 2004
|
| 3 |
+
http://www.apache.org/licenses/
|
| 4 |
+
|
| 5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 6 |
+
|
| 7 |
+
1. Definitions.
|
| 8 |
+
|
| 9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 11 |
+
|
| 12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 13 |
+
the copyright owner that is granting the License.
|
| 14 |
+
|
| 15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 16 |
+
other entities that control, are controlled by, or are under common
|
| 17 |
+
control with that entity. For the purposes of this definition,
|
| 18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 19 |
+
direction or management of such entity, whether by contract or
|
| 20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 22 |
+
|
| 23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 24 |
+
exercising permissions granted by this License.
|
| 25 |
+
|
| 26 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 27 |
+
including but not limited to software source code, documentation
|
| 28 |
+
source, and configuration files.
|
| 29 |
+
|
| 30 |
+
"Object" form shall mean any form resulting from mechanical
|
| 31 |
+
transformation or translation of a Source form, including but
|
| 32 |
+
not limited to compiled object code, generated documentation,
|
| 33 |
+
and conversions to other media types.
|
| 34 |
+
|
| 35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 36 |
+
Object form, made available under the License, as indicated by a
|
| 37 |
+
copyright notice that is included in or attached to the work
|
| 38 |
+
(an example is provided in the Appendix below).
|
| 39 |
+
|
| 40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 41 |
+
form, that is based on (or derived from) the Work and for which the
|
| 42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 44 |
+
of this License, Derivative Works shall not include works that remain
|
| 45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 46 |
+
the Work and Derivative Works thereof.
|
| 47 |
+
|
| 48 |
+
"Contribution" shall mean any work of authorship, including
|
| 49 |
+
the original version of the Work and any modifications or additions
|
| 50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 54 |
+
means any form of electronic, verbal, or written communication sent
|
| 55 |
+
to the Licensor or its representatives, including but not limited to
|
| 56 |
+
communication on electronic mailing lists, source code control systems,
|
| 57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 59 |
+
excluding communication that is conspicuously marked or otherwise
|
| 60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 61 |
+
|
| 62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 64 |
+
subsequently incorporated within the Work.
|
| 65 |
+
|
| 66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 71 |
+
Work and such Derivative Works in Source or Object form.
|
| 72 |
+
|
| 73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 76 |
+
(except as stated in this section) patent license to make, have made,
|
| 77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 78 |
+
where such license applies only to those patent claims licensable
|
| 79 |
+
by such Contributor that are necessarily infringed by their
|
| 80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 82 |
+
institute patent litigation against any entity (including a
|
| 83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 84 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 85 |
+
or contributory patent infringement, then any patent licenses
|
| 86 |
+
granted to You under this License for that Work shall terminate
|
| 87 |
+
as of the date such litigation is filed.
|
| 88 |
+
|
| 89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 90 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 91 |
+
modifications, and in Source or Object form, provided that You
|
| 92 |
+
meet the following conditions:
|
| 93 |
+
|
| 94 |
+
(a) You must give any other recipients of the Work or
|
| 95 |
+
Derivative Works a copy of this License; and
|
| 96 |
+
|
| 97 |
+
(b) You must cause any modified files to carry prominent notices
|
| 98 |
+
stating that You changed the files; and
|
| 99 |
+
|
| 100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 101 |
+
that You distribute, all copyright, patent, trademark, and
|
| 102 |
+
attribution notices from the Source form of the Work,
|
| 103 |
+
excluding those notices that do not pertain to any part of
|
| 104 |
+
the Derivative Works; and
|
| 105 |
+
|
| 106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 107 |
+
distribution, then any Derivative Works that You distribute must
|
| 108 |
+
include a readable copy of the attribution notices contained
|
| 109 |
+
within such NOTICE file, excluding those notices that do not
|
| 110 |
+
pertain to any part of the Derivative Works, in at least one
|
| 111 |
+
of the following places: within a NOTICE text file distributed
|
| 112 |
+
as part of the Derivative Works; within the Source form or
|
| 113 |
+
documentation, if provided along with the Derivative Works; or,
|
| 114 |
+
within a display generated by the Derivative Works, if and
|
| 115 |
+
wherever such third-party notices normally appear. The contents
|
| 116 |
+
of the NOTICE file are for informational purposes only and
|
| 117 |
+
do not modify the License. You may add Your own attribution
|
| 118 |
+
notices within Derivative Works that You distribute, alongside
|
| 119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 120 |
+
that such additional attribution notices cannot be construed
|
| 121 |
+
as modifying the License.
|
| 122 |
+
|
| 123 |
+
You may add Your own copyright statement to Your modifications and
|
| 124 |
+
may provide additional or different license terms and conditions
|
| 125 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 126 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 127 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 128 |
+
the conditions stated in this License.
|
| 129 |
+
|
| 130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 132 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 133 |
+
this License, without any additional terms or conditions.
|
| 134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 135 |
+
the terms of any separate license agreement you may have executed
|
| 136 |
+
with Licensor regarding such Contributions.
|
| 137 |
+
|
| 138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 140 |
+
except as required for reasonable and customary use in describing the
|
| 141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 142 |
+
|
| 143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 144 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 147 |
+
implied, including, without limitation, any warranties or conditions
|
| 148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 150 |
+
appropriateness of using or redistributing the Work and assume any
|
| 151 |
+
risks associated with Your exercise of permissions under this License.
|
| 152 |
+
|
| 153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 154 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 155 |
+
unless required by applicable law (such as deliberate and grossly
|
| 156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 157 |
+
liable to You for damages, including any direct, indirect, special,
|
| 158 |
+
incidental, or consequential damages of any character arising as a
|
| 159 |
+
result of this License or out of the use or inability to use the
|
| 160 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 161 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 162 |
+
other commercial damages or losses), even if such Contributor
|
| 163 |
+
has been advised of the possibility of such damages.
|
| 164 |
+
|
| 165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 168 |
+
or other liability obligations and/or rights consistent with this
|
| 169 |
+
License. However, in accepting such obligations, You may act only
|
| 170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 171 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 172 |
+
defend, and hold each Contributor harmless for any liability
|
| 173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 174 |
+
of your accepting any such warranty or additional liability.
|
| 175 |
+
|
| 176 |
+
END OF TERMS AND CONDITIONS
|
| 177 |
+
|
NOTICE.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This software is copyright 2026-present Prism ML, Inc. It is available under the Apache 2.0 license.
|
| 2 |
+
If you publicly deploy or redistribute this software, we would appreciate attribution such as: “Created using Bonsai by Prism ML."
|
| 3 |
+
|
| 4 |
+
This software is built from Qwen3-4B, Copyright 2024 Alibaba Cloud, which is available under the Apache 2.0 License: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE
|
README.md
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: mlx
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- 1-bit
|
| 7 |
+
- mlx
|
| 8 |
+
- apple-silicon
|
| 9 |
+
- on-device
|
| 10 |
+
- prismml
|
| 11 |
+
- bonsai
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<p align="center">
|
| 15 |
+
<img src="./assets/bonsai-logo.svg" width="280" alt="Bonsai">
|
| 16 |
+
</p>
|
| 17 |
+
|
| 18 |
+
<p align="center">
|
| 19 |
+
<a href="https://prismml.com"><b>Prism ML Website</b></a> |
|
| 20 |
+
<a href="https://github.com/PrismML-Eng/Bonsai-demo/blob/main/1-bit-bonsai-8b-whitepaper.pdf"><b>Whitepaper</b></a> |
|
| 21 |
+
<a href="https://github.com/PrismML-Eng/Bonsai-demo"><b>Demo & Examples</b></a> |
|
| 22 |
+
<a href="https://colab.research.google.com/drive/1EzyAaQ2nwDv_1X0jaC5XiVC3ZREg9bdG?usp=sharing"><b>Colab Notebook</b></a> |
|
| 23 |
+
<a href="https://discord.gg/prismml"><b>Discord</b></a>
|
| 24 |
+
</p>
|
| 25 |
+
|
| 26 |
+
# Bonsai-4B-mlx-1bit
|
| 27 |
+
|
| 28 |
+
End-to-end 1-bit language model for Apple Silicon
|
| 29 |
+
|
| 30 |
+
> **12.8x** smaller than FP16 | **4.8x** faster on M4 Pro | **60** tok/s on iPhone | runs on Mac, iPhone, iPad
|
| 31 |
+
|
| 32 |
+
## Highlights
|
| 33 |
+
|
| 34 |
+
- Deployed footprint — runs comfortably on any Mac or iPhone
|
| 35 |
+
- **End-to-end 1-bit weights** across embeddings, attention projections, MLP projections, and LM head
|
| 36 |
+
- **MLX-native format** (1-bit g128) with inline dequantization kernels — no FP16 materialization
|
| 37 |
+
- **Cross-platform companion**: also available as [GGUF Q1_0_g128](https://huggingface.co/prism-ml/Bonsai-4B-gguf) for llama.cpp
|
| 38 |
+
|
| 39 |
+
<p align="center">
|
| 40 |
+
<img src="./assets/frontier.svg" width="680" alt="Frontier Efficiency">
|
| 41 |
+
</p>
|
| 42 |
+
|
| 43 |
+
## Resources
|
| 44 |
+
|
| 45 |
+
- **[Google Colab](https://colab.research.google.com/drive/1EzyAaQ2nwDv_1X0jaC5XiVC3ZREg9bdG?usp=sharing)** — try Bonsai in your browser, no setup required
|
| 46 |
+
- **[Whitepaper](https://github.com/PrismML-Eng/Bonsai-demo/blob/main/1-bit-bonsai-8b-whitepaper.pdf)** — for more details on Bonsai, check out our whitepaper
|
| 47 |
+
- **[Demo repo](https://github.com/PrismML-Eng/Bonsai-demo)** — comprehensive examples for serving, benchmarking, and integrating Bonsai
|
| 48 |
+
- **[Discord](https://discord.gg/prismml)** — join the community for support, discussion, and updates
|
| 49 |
+
- **1-bit kernels**: [MLX fork](https://github.com/PrismML-Eng/mlx) (Apple Silicon) · [mlx-swift fork](https://github.com/PrismML-Eng/mlx-swift) (iOS/macOS) · [llama.cpp fork](https://github.com/PrismML-Eng/llama.cpp) (CUDA + Metal)
|
| 50 |
+
- **[Locally AI](https://locallyai.app/)** — we have partnered with Locally AI for iPhone support
|
| 51 |
+
|
| 52 |
+
## Model Overview
|
| 53 |
+
|
| 54 |
+
| Item | Specification |
|
| 55 |
+
| :------------- | :--------------------------------------------------------------------- |
|
| 56 |
+
| Parameters | 4.0B (~3.6B non-embedding) |
|
| 57 |
+
| Architecture | Qwen3-4B dense: GQA (32 query / 8 KV heads), SwiGLU MLP, RoPE, RMSNorm |
|
| 58 |
+
| Layers | 36 Transformer decoder blocks |
|
| 59 |
+
| Context length | 32,768 tokens |
|
| 60 |
+
| Vocab size | 151,936 |
|
| 61 |
+
| Weight format | MLX 1-bit g128 |
|
| 62 |
+
| Deployed size | **0.63 GB** (12.8x smaller than FP16) |
|
| 63 |
+
| 1-bit coverage | Embeddings, attention projections, MLP projections, LM head |
|
| 64 |
+
| License | Apache 2.0 |
|
| 65 |
+
|
| 66 |
+
## Quantization Format: 1-bit g128
|
| 67 |
+
|
| 68 |
+
Each weight is a single bit: `0` maps to `−scale`, `1` maps to `+scale`. Every group of 128 weights shares one FP16 scale factor.
|
| 69 |
+
|
| 70 |
+
MLX's quantization formats generally store both a scale and a bias per group: `w = mlx_scale * bit + mlx_bias`. To pack our scale-only 1-bit weights into this format:
|
| 71 |
+
|
| 72 |
+
```
|
| 73 |
+
mlx_scale = 2 * original_scale
|
| 74 |
+
mlx_bias = −original_scale
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
This reconstructs `−scale` when `bit=0` and `+scale` when `bit=1`. Because MLX stores two FP16 values per group (scale + bias) instead of one, the effective bits per weight is slightly higher than the GGUF format:
|
| 78 |
+
|
| 79 |
+
- **MLX 1-bit g128**: **1.25 bpw** (1 sign bit + two 16-bit values amortized over 128 weights)
|
| 80 |
+
- **GGUF Q1_0_g128**: **1.125 bpw** (1 sign bit + one 16-bit scale amortized over 128 weights)
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Memory Requirement
|
| 84 |
+
|
| 85 |
+
Parameter memory only (weights and scales loaded into memory):
|
| 86 |
+
|
| 87 |
+
| Format | Size | Reduction | Ratio |
|
| 88 |
+
| :----------------- | ----------: | --------: | --------: |
|
| 89 |
+
| FP16 | 8.04 GB | — | 1.0x |
|
| 90 |
+
| **MLX 1-bit g128** | **0.63 GB** | **92.2%** | **12.8x** |
|
| 91 |
+
| GGUF Q1_0_g128 | 0.57 GB | 93.0% | 14.2x |
|
| 92 |
+
|
| 93 |
+
The model directory on disk is ~0.64 GB (~16 MB larger) because it also includes tokenizer, config, and other metadata files alongside the weights.
|
| 94 |
+
|
| 95 |
+
## Best Practices
|
| 96 |
+
|
| 97 |
+
### Generation Parameters
|
| 98 |
+
|
| 99 |
+
| Parameter | Default | Suggested range |
|
| 100 |
+
| :----------------- | :------ | :-------------- |
|
| 101 |
+
| Temperature | 0.5 | 0.5 -- 0.7 |
|
| 102 |
+
| Top-k | 20 | 20 -- 40 |
|
| 103 |
+
| Top-p | 0.9 | 0.85 -- 0.95 |
|
| 104 |
+
| Repetition penalty | 1.0 | |
|
| 105 |
+
| Presence penalty | 0.0 | |
|
| 106 |
+
|
| 107 |
+
### System Prompt
|
| 108 |
+
|
| 109 |
+
You can use a simple system prompt such as:
|
| 110 |
+
|
| 111 |
+
```
|
| 112 |
+
You are a helpful assistant
|
| 113 |
+
```
|
| 114 |
+
|
| 115 |
+
## Quickstart
|
| 116 |
+
|
| 117 |
+
### MLX (Python)
|
| 118 |
+
|
| 119 |
+
> **Requires PrismML fork of MLX** with 1-bit kernel support (upstream PR pending):
|
| 120 |
+
> ```bash
|
| 121 |
+
> pip install mlx-lm
|
| 122 |
+
> pip install mlx @ git+https://github.com/PrismML-Eng/mlx.git@prism
|
| 123 |
+
> ```
|
| 124 |
+
|
| 125 |
+
```python
|
| 126 |
+
from mlx_lm import load, generate
|
| 127 |
+
|
| 128 |
+
model, tokenizer = load("prism-ml/Bonsai-4B-mlx-1bit")
|
| 129 |
+
|
| 130 |
+
response = generate(
|
| 131 |
+
model,
|
| 132 |
+
tokenizer,
|
| 133 |
+
prompt="Explain quantum computing in simple terms.",
|
| 134 |
+
max_tokens=256,
|
| 135 |
+
)
|
| 136 |
+
print(response)
|
| 137 |
+
```
|
| 138 |
+
|
| 139 |
+
### MLX Swift (iOS / macOS)
|
| 140 |
+
|
| 141 |
+
1-bit Bonsai 4B runs natively on iPhone and iPad via MLX Swift. Requires our [mlx-swift fork with 1-bit kernels](https://github.com/PrismML-Eng/mlx-swift) (upstream PR pending).
|
| 142 |
+
|
| 143 |
+
## Throughput (MLX / Apple Silicon)
|
| 144 |
+
|
| 145 |
+
| Platform | Backend | TG128 (tok/s) | FP16 TG (tok/s) | TG vs FP16 | PP512 (tok/s) | FP16 PP512 (tok/s) |
|
| 146 |
+
| :---------------- | :-------------- | ------------: | --------------: | ---------: | ------------: | -----------------: |
|
| 147 |
+
| M4 Pro 48 GB | MLX (Python) | 132 | 28 | **4.8x** | 806 | 728 |
|
| 148 |
+
| M4 Pro 48 GB | llama.cpp Metal | 136 | 29 | **4.7x** | 915 | 915 |
|
| 149 |
+
| iPhone 17 Pro Max | MLX Swift | 60 | — | — | 651 | — |
|
| 150 |
+
|
| 151 |
+
## Citation
|
| 152 |
+
|
| 153 |
+
If you use 1-bit Bonsai 4B, please cite:
|
| 154 |
+
|
| 155 |
+
```bibtex
|
| 156 |
+
@techreport{bonsai,
|
| 157 |
+
title = {Bonsai: End-to-End 1-bit Language Model Deployment
|
| 158 |
+
Across Apple, GPU, and Mobile Runtimes},
|
| 159 |
+
author = {Prism ML},
|
| 160 |
+
year = {2026},
|
| 161 |
+
month = {March},
|
| 162 |
+
url = {https://prismml.com}
|
| 163 |
+
}
|
| 164 |
+
```
|
| 165 |
+
|
| 166 |
+
## Contact
|
| 167 |
+
|
| 168 |
+
For questions, feedback, or collaboration inquiries: **contact@prismml.com**
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
assets/bonsai-logo.svg
ADDED
|
assets/frontier.png
ADDED
|
Git LFS Details
|
assets/frontier.svg
ADDED
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n<think>\n\n</think>\n\n' }}
|
| 86 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 151669,
|
| 3 |
+
"max_position_embeddings": 32768,
|
| 4 |
+
"hidden_size": 2560,
|
| 5 |
+
"intermediate_size": 9728,
|
| 6 |
+
"num_hidden_layers": 36,
|
| 7 |
+
"num_attention_heads": 32,
|
| 8 |
+
"use_sliding_window": false,
|
| 9 |
+
"sliding_window": null,
|
| 10 |
+
"max_window_layers": 28,
|
| 11 |
+
"num_key_value_heads": 8,
|
| 12 |
+
"head_dim": 128,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"rms_norm_eps": 1e-06,
|
| 16 |
+
"use_cache": true,
|
| 17 |
+
"rope_theta": 5000000.0,
|
| 18 |
+
"rope_scaling": {
|
| 19 |
+
"rope_type": "yarn",
|
| 20 |
+
"factor": 4.0,
|
| 21 |
+
"original_max_position_embeddings": 8192
|
| 22 |
+
},
|
| 23 |
+
"attention_bias": false,
|
| 24 |
+
"attention_dropout": 0.0,
|
| 25 |
+
"layer_types": [
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention"
|
| 62 |
+
],
|
| 63 |
+
"return_dict": true,
|
| 64 |
+
"output_hidden_states": false,
|
| 65 |
+
"torchscript": false,
|
| 66 |
+
"dtype": null,
|
| 67 |
+
"pruned_heads": {},
|
| 68 |
+
"tie_word_embeddings": true,
|
| 69 |
+
"chunk_size_feed_forward": 0,
|
| 70 |
+
"is_encoder_decoder": false,
|
| 71 |
+
"is_decoder": false,
|
| 72 |
+
"cross_attention_hidden_size": null,
|
| 73 |
+
"add_cross_attention": false,
|
| 74 |
+
"tie_encoder_decoder": false,
|
| 75 |
+
"architectures": [
|
| 76 |
+
"Qwen3ForCausalLM"
|
| 77 |
+
],
|
| 78 |
+
"finetuning_task": null,
|
| 79 |
+
"id2label": {
|
| 80 |
+
"0": "LABEL_0",
|
| 81 |
+
"1": "LABEL_1"
|
| 82 |
+
},
|
| 83 |
+
"label2id": {
|
| 84 |
+
"LABEL_0": 0,
|
| 85 |
+
"LABEL_1": 1
|
| 86 |
+
},
|
| 87 |
+
"task_specific_params": null,
|
| 88 |
+
"problem_type": null,
|
| 89 |
+
"tokenizer_class": null,
|
| 90 |
+
"prefix": null,
|
| 91 |
+
"bos_token_id": null,
|
| 92 |
+
"pad_token_id": 151643,
|
| 93 |
+
"eos_token_id": 151645,
|
| 94 |
+
"sep_token_id": null,
|
| 95 |
+
"decoder_start_token_id": null,
|
| 96 |
+
"max_length": 20,
|
| 97 |
+
"min_length": 0,
|
| 98 |
+
"do_sample": false,
|
| 99 |
+
"early_stopping": false,
|
| 100 |
+
"num_beams": 1,
|
| 101 |
+
"temperature": 1.0,
|
| 102 |
+
"top_k": 50,
|
| 103 |
+
"top_p": 1.0,
|
| 104 |
+
"typical_p": 1.0,
|
| 105 |
+
"repetition_penalty": 1.0,
|
| 106 |
+
"length_penalty": 1.0,
|
| 107 |
+
"no_repeat_ngram_size": 0,
|
| 108 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 109 |
+
"bad_words_ids": null,
|
| 110 |
+
"num_return_sequences": 1,
|
| 111 |
+
"output_scores": false,
|
| 112 |
+
"return_dict_in_generate": false,
|
| 113 |
+
"forced_bos_token_id": null,
|
| 114 |
+
"forced_eos_token_id": null,
|
| 115 |
+
"remove_invalid_values": false,
|
| 116 |
+
"exponential_decay_length_penalty": null,
|
| 117 |
+
"suppress_tokens": null,
|
| 118 |
+
"begin_suppress_tokens": [
|
| 119 |
+
151643,
|
| 120 |
+
151645
|
| 121 |
+
],
|
| 122 |
+
"num_beam_groups": 1,
|
| 123 |
+
"diversity_penalty": 0.0,
|
| 124 |
+
"_name_or_path": "",
|
| 125 |
+
"transformers_version": "4.57.6",
|
| 126 |
+
"no_bias": true,
|
| 127 |
+
"tf_legacy_loss": false,
|
| 128 |
+
"use_bfloat16": false,
|
| 129 |
+
"model_type": "qwen3",
|
| 130 |
+
"output_attentions": false,
|
| 131 |
+
"quantization": {
|
| 132 |
+
"group_size": 128,
|
| 133 |
+
"bits": 1
|
| 134 |
+
}
|
| 135 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 151645,
|
| 4 |
+
"pad_token_id": 151643,
|
| 5 |
+
"transformers_version": "4.57.0",
|
| 6 |
+
"begin_suppress_tokens": [
|
| 7 |
+
151645
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.5,
|
| 10 |
+
"top_p": 0.85,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"min_p": 0.0,
|
| 13 |
+
"presence_penalty": 0.0,
|
| 14 |
+
"repetition_penalty": 1.0,
|
| 15 |
+
"do_sample": true
|
| 16 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95b90b3e65efd3a4b0cc49c82d685a8430db10f2a42257ae57c1d982a6a1e5f5
|
| 3 |
+
size 628865840
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,911 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 628765392
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 7 |
+
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
| 8 |
+
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
| 9 |
+
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.k_norm.weight": "model.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.q_norm.weight": "model.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
| 26 |
+
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 27 |
+
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
| 28 |
+
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
| 29 |
+
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 30 |
+
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
| 31 |
+
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.k_norm.weight": "model.safetensors",
|
| 33 |
+
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 34 |
+
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 35 |
+
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
| 36 |
+
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
| 37 |
+
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
| 38 |
+
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
| 39 |
+
"model.layers.1.self_attn.q_norm.weight": "model.safetensors",
|
| 40 |
+
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 41 |
+
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 42 |
+
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
| 43 |
+
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 44 |
+
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 45 |
+
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
| 46 |
+
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 47 |
+
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
| 48 |
+
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
| 49 |
+
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 50 |
+
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
| 51 |
+
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
| 52 |
+
"model.layers.10.self_attn.k_norm.weight": "model.safetensors",
|
| 53 |
+
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 54 |
+
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 55 |
+
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 56 |
+
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
| 57 |
+
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
| 58 |
+
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
| 59 |
+
"model.layers.10.self_attn.q_norm.weight": "model.safetensors",
|
| 60 |
+
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 61 |
+
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 62 |
+
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 63 |
+
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 64 |
+
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 65 |
+
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 66 |
+
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 67 |
+
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
| 68 |
+
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
| 69 |
+
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 70 |
+
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
| 71 |
+
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
| 72 |
+
"model.layers.11.self_attn.k_norm.weight": "model.safetensors",
|
| 73 |
+
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 74 |
+
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 75 |
+
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
| 76 |
+
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 77 |
+
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
| 78 |
+
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
| 79 |
+
"model.layers.11.self_attn.q_norm.weight": "model.safetensors",
|
| 80 |
+
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 81 |
+
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 82 |
+
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
| 83 |
+
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 84 |
+
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 85 |
+
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
| 86 |
+
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 87 |
+
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
| 88 |
+
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
| 89 |
+
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 90 |
+
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
| 91 |
+
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
| 92 |
+
"model.layers.12.self_attn.k_norm.weight": "model.safetensors",
|
| 93 |
+
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 94 |
+
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 95 |
+
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 96 |
+
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
| 97 |
+
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
| 98 |
+
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
| 99 |
+
"model.layers.12.self_attn.q_norm.weight": "model.safetensors",
|
| 100 |
+
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 101 |
+
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 102 |
+
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 103 |
+
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 104 |
+
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 105 |
+
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 106 |
+
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 107 |
+
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
| 108 |
+
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
| 109 |
+
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 110 |
+
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
| 111 |
+
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
| 112 |
+
"model.layers.13.self_attn.k_norm.weight": "model.safetensors",
|
| 113 |
+
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 114 |
+
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 115 |
+
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
| 116 |
+
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
| 117 |
+
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
| 118 |
+
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
| 119 |
+
"model.layers.13.self_attn.q_norm.weight": "model.safetensors",
|
| 120 |
+
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 121 |
+
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 122 |
+
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
| 123 |
+
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 124 |
+
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 125 |
+
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
| 126 |
+
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 127 |
+
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
| 128 |
+
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
| 129 |
+
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 130 |
+
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
| 131 |
+
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
| 132 |
+
"model.layers.14.self_attn.k_norm.weight": "model.safetensors",
|
| 133 |
+
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 134 |
+
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 135 |
+
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 136 |
+
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
| 137 |
+
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
| 138 |
+
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
| 139 |
+
"model.layers.14.self_attn.q_norm.weight": "model.safetensors",
|
| 140 |
+
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 141 |
+
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 142 |
+
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 143 |
+
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 144 |
+
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 145 |
+
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 146 |
+
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 147 |
+
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
| 148 |
+
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
| 149 |
+
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 150 |
+
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
| 151 |
+
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
| 152 |
+
"model.layers.15.self_attn.k_norm.weight": "model.safetensors",
|
| 153 |
+
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 154 |
+
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 155 |
+
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
| 156 |
+
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 157 |
+
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
| 158 |
+
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
| 159 |
+
"model.layers.15.self_attn.q_norm.weight": "model.safetensors",
|
| 160 |
+
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 161 |
+
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 162 |
+
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
| 163 |
+
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 164 |
+
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 165 |
+
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
| 166 |
+
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 167 |
+
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
| 168 |
+
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
| 169 |
+
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 170 |
+
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
| 171 |
+
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
| 172 |
+
"model.layers.16.self_attn.k_norm.weight": "model.safetensors",
|
| 173 |
+
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 174 |
+
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 175 |
+
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
| 176 |
+
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
| 177 |
+
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
| 178 |
+
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
| 179 |
+
"model.layers.16.self_attn.q_norm.weight": "model.safetensors",
|
| 180 |
+
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 181 |
+
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 182 |
+
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
| 183 |
+
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 184 |
+
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 185 |
+
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
| 186 |
+
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 187 |
+
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
| 188 |
+
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
| 189 |
+
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 190 |
+
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
| 191 |
+
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
| 192 |
+
"model.layers.17.self_attn.k_norm.weight": "model.safetensors",
|
| 193 |
+
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 194 |
+
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 195 |
+
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
| 196 |
+
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
| 197 |
+
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
| 198 |
+
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
| 199 |
+
"model.layers.17.self_attn.q_norm.weight": "model.safetensors",
|
| 200 |
+
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 201 |
+
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 202 |
+
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
| 203 |
+
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 204 |
+
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 205 |
+
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
| 206 |
+
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 207 |
+
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
| 208 |
+
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
| 209 |
+
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 210 |
+
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
| 211 |
+
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
| 212 |
+
"model.layers.18.self_attn.k_norm.weight": "model.safetensors",
|
| 213 |
+
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 214 |
+
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 215 |
+
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
| 216 |
+
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
| 217 |
+
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
| 218 |
+
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
| 219 |
+
"model.layers.18.self_attn.q_norm.weight": "model.safetensors",
|
| 220 |
+
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 221 |
+
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 222 |
+
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
| 223 |
+
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 224 |
+
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 225 |
+
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
| 226 |
+
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 227 |
+
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
| 228 |
+
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
| 229 |
+
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 230 |
+
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
| 231 |
+
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
| 232 |
+
"model.layers.19.self_attn.k_norm.weight": "model.safetensors",
|
| 233 |
+
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 234 |
+
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 235 |
+
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
| 236 |
+
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 237 |
+
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
| 238 |
+
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
| 239 |
+
"model.layers.19.self_attn.q_norm.weight": "model.safetensors",
|
| 240 |
+
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 241 |
+
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 242 |
+
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
| 243 |
+
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 244 |
+
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 245 |
+
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
| 246 |
+
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 247 |
+
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
| 248 |
+
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
| 249 |
+
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 250 |
+
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
| 251 |
+
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
| 252 |
+
"model.layers.2.self_attn.k_norm.weight": "model.safetensors",
|
| 253 |
+
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 254 |
+
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 255 |
+
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 256 |
+
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 257 |
+
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 258 |
+
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
| 259 |
+
"model.layers.2.self_attn.q_norm.weight": "model.safetensors",
|
| 260 |
+
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 261 |
+
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 262 |
+
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 263 |
+
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 264 |
+
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 265 |
+
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 266 |
+
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 267 |
+
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 268 |
+
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
| 269 |
+
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 270 |
+
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 271 |
+
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
| 272 |
+
"model.layers.20.self_attn.k_norm.weight": "model.safetensors",
|
| 273 |
+
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 274 |
+
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 275 |
+
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 276 |
+
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 277 |
+
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 278 |
+
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
| 279 |
+
"model.layers.20.self_attn.q_norm.weight": "model.safetensors",
|
| 280 |
+
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 281 |
+
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 282 |
+
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 283 |
+
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 284 |
+
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 285 |
+
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 286 |
+
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 287 |
+
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 288 |
+
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
| 289 |
+
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 290 |
+
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 291 |
+
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
| 292 |
+
"model.layers.21.self_attn.k_norm.weight": "model.safetensors",
|
| 293 |
+
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 294 |
+
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 295 |
+
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 296 |
+
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 297 |
+
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 298 |
+
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
| 299 |
+
"model.layers.21.self_attn.q_norm.weight": "model.safetensors",
|
| 300 |
+
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 301 |
+
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 302 |
+
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 303 |
+
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 304 |
+
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 305 |
+
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 306 |
+
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 307 |
+
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 308 |
+
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
| 309 |
+
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 310 |
+
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 311 |
+
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
| 312 |
+
"model.layers.22.self_attn.k_norm.weight": "model.safetensors",
|
| 313 |
+
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 314 |
+
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 315 |
+
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 316 |
+
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 317 |
+
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 318 |
+
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
| 319 |
+
"model.layers.22.self_attn.q_norm.weight": "model.safetensors",
|
| 320 |
+
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 321 |
+
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 322 |
+
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 323 |
+
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 324 |
+
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 325 |
+
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 326 |
+
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 327 |
+
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 328 |
+
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
| 329 |
+
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 330 |
+
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 331 |
+
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
| 332 |
+
"model.layers.23.self_attn.k_norm.weight": "model.safetensors",
|
| 333 |
+
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 334 |
+
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 335 |
+
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 336 |
+
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 337 |
+
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 338 |
+
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
| 339 |
+
"model.layers.23.self_attn.q_norm.weight": "model.safetensors",
|
| 340 |
+
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 341 |
+
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 342 |
+
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 343 |
+
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 344 |
+
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 345 |
+
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 346 |
+
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 347 |
+
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 348 |
+
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
| 349 |
+
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 350 |
+
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 351 |
+
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
| 352 |
+
"model.layers.24.self_attn.k_norm.weight": "model.safetensors",
|
| 353 |
+
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 354 |
+
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 355 |
+
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 356 |
+
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 357 |
+
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 358 |
+
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
| 359 |
+
"model.layers.24.self_attn.q_norm.weight": "model.safetensors",
|
| 360 |
+
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 361 |
+
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 362 |
+
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 363 |
+
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 364 |
+
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 365 |
+
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 366 |
+
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 367 |
+
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 368 |
+
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
| 369 |
+
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 370 |
+
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 371 |
+
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
| 372 |
+
"model.layers.25.self_attn.k_norm.weight": "model.safetensors",
|
| 373 |
+
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 374 |
+
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 375 |
+
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 376 |
+
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 377 |
+
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 378 |
+
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
| 379 |
+
"model.layers.25.self_attn.q_norm.weight": "model.safetensors",
|
| 380 |
+
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 381 |
+
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 382 |
+
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 383 |
+
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 384 |
+
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 385 |
+
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 386 |
+
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 387 |
+
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
| 388 |
+
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
| 389 |
+
"model.layers.26.self_attn.k_norm.weight": "model.safetensors",
|
| 390 |
+
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
| 391 |
+
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
| 392 |
+
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
| 393 |
+
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
| 394 |
+
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
| 395 |
+
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
| 396 |
+
"model.layers.26.self_attn.q_norm.weight": "model.safetensors",
|
| 397 |
+
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
| 398 |
+
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
| 399 |
+
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
| 400 |
+
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
| 401 |
+
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
| 402 |
+
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
| 403 |
+
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 404 |
+
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
| 405 |
+
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
| 406 |
+
"model.layers.27.self_attn.k_norm.weight": "model.safetensors",
|
| 407 |
+
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 408 |
+
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
| 409 |
+
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
| 410 |
+
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 411 |
+
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
| 412 |
+
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
| 413 |
+
"model.layers.27.self_attn.q_norm.weight": "model.safetensors",
|
| 414 |
+
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 415 |
+
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
| 416 |
+
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
| 417 |
+
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 418 |
+
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
| 419 |
+
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
| 420 |
+
"model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
| 421 |
+
"model.layers.28.mlp.gate_proj.scales": "model.safetensors",
|
| 422 |
+
"model.layers.28.mlp.gate_proj.biases": "model.safetensors",
|
| 423 |
+
"model.layers.28.self_attn.k_norm.weight": "model.safetensors",
|
| 424 |
+
"model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
| 425 |
+
"model.layers.28.self_attn.k_proj.scales": "model.safetensors",
|
| 426 |
+
"model.layers.28.self_attn.k_proj.biases": "model.safetensors",
|
| 427 |
+
"model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
| 428 |
+
"model.layers.28.self_attn.o_proj.scales": "model.safetensors",
|
| 429 |
+
"model.layers.28.self_attn.o_proj.biases": "model.safetensors",
|
| 430 |
+
"model.layers.28.self_attn.q_norm.weight": "model.safetensors",
|
| 431 |
+
"model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
| 432 |
+
"model.layers.28.self_attn.q_proj.scales": "model.safetensors",
|
| 433 |
+
"model.layers.28.self_attn.q_proj.biases": "model.safetensors",
|
| 434 |
+
"model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
| 435 |
+
"model.layers.28.self_attn.v_proj.scales": "model.safetensors",
|
| 436 |
+
"model.layers.28.self_attn.v_proj.biases": "model.safetensors",
|
| 437 |
+
"model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
| 438 |
+
"model.layers.29.mlp.gate_proj.scales": "model.safetensors",
|
| 439 |
+
"model.layers.29.mlp.gate_proj.biases": "model.safetensors",
|
| 440 |
+
"model.layers.29.self_attn.k_norm.weight": "model.safetensors",
|
| 441 |
+
"model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
| 442 |
+
"model.layers.29.self_attn.k_proj.scales": "model.safetensors",
|
| 443 |
+
"model.layers.29.self_attn.k_proj.biases": "model.safetensors",
|
| 444 |
+
"model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
| 445 |
+
"model.layers.29.self_attn.o_proj.scales": "model.safetensors",
|
| 446 |
+
"model.layers.29.self_attn.o_proj.biases": "model.safetensors",
|
| 447 |
+
"model.layers.29.self_attn.q_norm.weight": "model.safetensors",
|
| 448 |
+
"model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
| 449 |
+
"model.layers.29.self_attn.q_proj.scales": "model.safetensors",
|
| 450 |
+
"model.layers.29.self_attn.q_proj.biases": "model.safetensors",
|
| 451 |
+
"model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
| 452 |
+
"model.layers.29.self_attn.v_proj.scales": "model.safetensors",
|
| 453 |
+
"model.layers.29.self_attn.v_proj.biases": "model.safetensors",
|
| 454 |
+
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 455 |
+
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 456 |
+
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
| 457 |
+
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 458 |
+
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 459 |
+
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
| 460 |
+
"model.layers.3.self_attn.k_norm.weight": "model.safetensors",
|
| 461 |
+
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 462 |
+
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 463 |
+
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 464 |
+
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 465 |
+
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 466 |
+
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
| 467 |
+
"model.layers.3.self_attn.q_norm.weight": "model.safetensors",
|
| 468 |
+
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 469 |
+
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 470 |
+
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 471 |
+
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 472 |
+
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 473 |
+
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 474 |
+
"model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
| 475 |
+
"model.layers.30.mlp.gate_proj.scales": "model.safetensors",
|
| 476 |
+
"model.layers.30.mlp.gate_proj.biases": "model.safetensors",
|
| 477 |
+
"model.layers.30.self_attn.k_norm.weight": "model.safetensors",
|
| 478 |
+
"model.layers.30.self_attn.k_proj.weight": "model.safetensors",
|
| 479 |
+
"model.layers.30.self_attn.k_proj.scales": "model.safetensors",
|
| 480 |
+
"model.layers.30.self_attn.k_proj.biases": "model.safetensors",
|
| 481 |
+
"model.layers.30.self_attn.o_proj.weight": "model.safetensors",
|
| 482 |
+
"model.layers.30.self_attn.o_proj.scales": "model.safetensors",
|
| 483 |
+
"model.layers.30.self_attn.o_proj.biases": "model.safetensors",
|
| 484 |
+
"model.layers.30.self_attn.q_norm.weight": "model.safetensors",
|
| 485 |
+
"model.layers.30.self_attn.q_proj.weight": "model.safetensors",
|
| 486 |
+
"model.layers.30.self_attn.q_proj.scales": "model.safetensors",
|
| 487 |
+
"model.layers.30.self_attn.q_proj.biases": "model.safetensors",
|
| 488 |
+
"model.layers.30.self_attn.v_proj.weight": "model.safetensors",
|
| 489 |
+
"model.layers.30.self_attn.v_proj.scales": "model.safetensors",
|
| 490 |
+
"model.layers.30.self_attn.v_proj.biases": "model.safetensors",
|
| 491 |
+
"model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
| 492 |
+
"model.layers.31.mlp.gate_proj.scales": "model.safetensors",
|
| 493 |
+
"model.layers.31.mlp.gate_proj.biases": "model.safetensors",
|
| 494 |
+
"model.layers.31.self_attn.k_norm.weight": "model.safetensors",
|
| 495 |
+
"model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
| 496 |
+
"model.layers.31.self_attn.k_proj.scales": "model.safetensors",
|
| 497 |
+
"model.layers.31.self_attn.k_proj.biases": "model.safetensors",
|
| 498 |
+
"model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
| 499 |
+
"model.layers.31.self_attn.o_proj.scales": "model.safetensors",
|
| 500 |
+
"model.layers.31.self_attn.o_proj.biases": "model.safetensors",
|
| 501 |
+
"model.layers.31.self_attn.q_norm.weight": "model.safetensors",
|
| 502 |
+
"model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
| 503 |
+
"model.layers.31.self_attn.q_proj.scales": "model.safetensors",
|
| 504 |
+
"model.layers.31.self_attn.q_proj.biases": "model.safetensors",
|
| 505 |
+
"model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
| 506 |
+
"model.layers.31.self_attn.v_proj.scales": "model.safetensors",
|
| 507 |
+
"model.layers.31.self_attn.v_proj.biases": "model.safetensors",
|
| 508 |
+
"model.layers.32.mlp.gate_proj.weight": "model.safetensors",
|
| 509 |
+
"model.layers.32.mlp.gate_proj.scales": "model.safetensors",
|
| 510 |
+
"model.layers.32.mlp.gate_proj.biases": "model.safetensors",
|
| 511 |
+
"model.layers.32.self_attn.k_norm.weight": "model.safetensors",
|
| 512 |
+
"model.layers.32.self_attn.k_proj.weight": "model.safetensors",
|
| 513 |
+
"model.layers.32.self_attn.k_proj.scales": "model.safetensors",
|
| 514 |
+
"model.layers.32.self_attn.k_proj.biases": "model.safetensors",
|
| 515 |
+
"model.layers.32.self_attn.o_proj.weight": "model.safetensors",
|
| 516 |
+
"model.layers.32.self_attn.o_proj.scales": "model.safetensors",
|
| 517 |
+
"model.layers.32.self_attn.o_proj.biases": "model.safetensors",
|
| 518 |
+
"model.layers.32.self_attn.q_norm.weight": "model.safetensors",
|
| 519 |
+
"model.layers.32.self_attn.q_proj.weight": "model.safetensors",
|
| 520 |
+
"model.layers.32.self_attn.q_proj.scales": "model.safetensors",
|
| 521 |
+
"model.layers.32.self_attn.q_proj.biases": "model.safetensors",
|
| 522 |
+
"model.layers.32.self_attn.v_proj.weight": "model.safetensors",
|
| 523 |
+
"model.layers.32.self_attn.v_proj.scales": "model.safetensors",
|
| 524 |
+
"model.layers.32.self_attn.v_proj.biases": "model.safetensors",
|
| 525 |
+
"model.layers.33.mlp.gate_proj.weight": "model.safetensors",
|
| 526 |
+
"model.layers.33.mlp.gate_proj.scales": "model.safetensors",
|
| 527 |
+
"model.layers.33.mlp.gate_proj.biases": "model.safetensors",
|
| 528 |
+
"model.layers.33.self_attn.k_norm.weight": "model.safetensors",
|
| 529 |
+
"model.layers.33.self_attn.k_proj.weight": "model.safetensors",
|
| 530 |
+
"model.layers.33.self_attn.k_proj.scales": "model.safetensors",
|
| 531 |
+
"model.layers.33.self_attn.k_proj.biases": "model.safetensors",
|
| 532 |
+
"model.layers.33.self_attn.o_proj.weight": "model.safetensors",
|
| 533 |
+
"model.layers.33.self_attn.o_proj.scales": "model.safetensors",
|
| 534 |
+
"model.layers.33.self_attn.o_proj.biases": "model.safetensors",
|
| 535 |
+
"model.layers.33.self_attn.q_norm.weight": "model.safetensors",
|
| 536 |
+
"model.layers.33.self_attn.q_proj.weight": "model.safetensors",
|
| 537 |
+
"model.layers.33.self_attn.q_proj.scales": "model.safetensors",
|
| 538 |
+
"model.layers.33.self_attn.q_proj.biases": "model.safetensors",
|
| 539 |
+
"model.layers.33.self_attn.v_proj.weight": "model.safetensors",
|
| 540 |
+
"model.layers.33.self_attn.v_proj.scales": "model.safetensors",
|
| 541 |
+
"model.layers.33.self_attn.v_proj.biases": "model.safetensors",
|
| 542 |
+
"model.layers.34.mlp.gate_proj.weight": "model.safetensors",
|
| 543 |
+
"model.layers.34.mlp.gate_proj.scales": "model.safetensors",
|
| 544 |
+
"model.layers.34.mlp.gate_proj.biases": "model.safetensors",
|
| 545 |
+
"model.layers.34.self_attn.k_norm.weight": "model.safetensors",
|
| 546 |
+
"model.layers.34.self_attn.k_proj.weight": "model.safetensors",
|
| 547 |
+
"model.layers.34.self_attn.k_proj.scales": "model.safetensors",
|
| 548 |
+
"model.layers.34.self_attn.k_proj.biases": "model.safetensors",
|
| 549 |
+
"model.layers.34.self_attn.o_proj.weight": "model.safetensors",
|
| 550 |
+
"model.layers.34.self_attn.o_proj.scales": "model.safetensors",
|
| 551 |
+
"model.layers.34.self_attn.o_proj.biases": "model.safetensors",
|
| 552 |
+
"model.layers.34.self_attn.q_norm.weight": "model.safetensors",
|
| 553 |
+
"model.layers.34.self_attn.q_proj.weight": "model.safetensors",
|
| 554 |
+
"model.layers.34.self_attn.q_proj.scales": "model.safetensors",
|
| 555 |
+
"model.layers.34.self_attn.q_proj.biases": "model.safetensors",
|
| 556 |
+
"model.layers.34.self_attn.v_proj.weight": "model.safetensors",
|
| 557 |
+
"model.layers.34.self_attn.v_proj.scales": "model.safetensors",
|
| 558 |
+
"model.layers.34.self_attn.v_proj.biases": "model.safetensors",
|
| 559 |
+
"model.layers.35.mlp.gate_proj.weight": "model.safetensors",
|
| 560 |
+
"model.layers.35.mlp.gate_proj.scales": "model.safetensors",
|
| 561 |
+
"model.layers.35.mlp.gate_proj.biases": "model.safetensors",
|
| 562 |
+
"model.layers.35.self_attn.k_norm.weight": "model.safetensors",
|
| 563 |
+
"model.layers.35.self_attn.k_proj.weight": "model.safetensors",
|
| 564 |
+
"model.layers.35.self_attn.k_proj.scales": "model.safetensors",
|
| 565 |
+
"model.layers.35.self_attn.k_proj.biases": "model.safetensors",
|
| 566 |
+
"model.layers.35.self_attn.o_proj.weight": "model.safetensors",
|
| 567 |
+
"model.layers.35.self_attn.o_proj.scales": "model.safetensors",
|
| 568 |
+
"model.layers.35.self_attn.o_proj.biases": "model.safetensors",
|
| 569 |
+
"model.layers.35.self_attn.q_norm.weight": "model.safetensors",
|
| 570 |
+
"model.layers.35.self_attn.q_proj.weight": "model.safetensors",
|
| 571 |
+
"model.layers.35.self_attn.q_proj.scales": "model.safetensors",
|
| 572 |
+
"model.layers.35.self_attn.q_proj.biases": "model.safetensors",
|
| 573 |
+
"model.layers.35.self_attn.v_proj.weight": "model.safetensors",
|
| 574 |
+
"model.layers.35.self_attn.v_proj.scales": "model.safetensors",
|
| 575 |
+
"model.layers.35.self_attn.v_proj.biases": "model.safetensors",
|
| 576 |
+
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 577 |
+
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 578 |
+
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 579 |
+
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 580 |
+
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 581 |
+
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 582 |
+
"model.layers.4.self_attn.k_norm.weight": "model.safetensors",
|
| 583 |
+
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 584 |
+
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 585 |
+
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 586 |
+
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 587 |
+
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 588 |
+
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 589 |
+
"model.layers.4.self_attn.q_norm.weight": "model.safetensors",
|
| 590 |
+
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 591 |
+
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 592 |
+
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 593 |
+
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 594 |
+
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 595 |
+
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 596 |
+
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 597 |
+
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 598 |
+
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 599 |
+
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 600 |
+
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 601 |
+
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 602 |
+
"model.layers.5.self_attn.k_norm.weight": "model.safetensors",
|
| 603 |
+
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 604 |
+
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 605 |
+
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 606 |
+
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 607 |
+
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 608 |
+
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 609 |
+
"model.layers.5.self_attn.q_norm.weight": "model.safetensors",
|
| 610 |
+
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 611 |
+
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 612 |
+
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 613 |
+
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 614 |
+
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 615 |
+
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 616 |
+
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 617 |
+
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 618 |
+
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 619 |
+
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 620 |
+
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 621 |
+
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 622 |
+
"model.layers.6.self_attn.k_norm.weight": "model.safetensors",
|
| 623 |
+
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 624 |
+
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 625 |
+
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 626 |
+
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 627 |
+
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 628 |
+
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 629 |
+
"model.layers.6.self_attn.q_norm.weight": "model.safetensors",
|
| 630 |
+
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 631 |
+
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 632 |
+
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 633 |
+
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 634 |
+
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 635 |
+
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 636 |
+
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 637 |
+
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 638 |
+
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 639 |
+
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 640 |
+
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 641 |
+
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 642 |
+
"model.layers.7.self_attn.k_norm.weight": "model.safetensors",
|
| 643 |
+
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 644 |
+
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 645 |
+
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 646 |
+
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 647 |
+
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 648 |
+
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 649 |
+
"model.layers.7.self_attn.q_norm.weight": "model.safetensors",
|
| 650 |
+
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 651 |
+
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 652 |
+
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 653 |
+
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 654 |
+
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 655 |
+
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 656 |
+
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 657 |
+
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 658 |
+
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 659 |
+
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 660 |
+
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 661 |
+
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 662 |
+
"model.layers.8.self_attn.k_norm.weight": "model.safetensors",
|
| 663 |
+
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 664 |
+
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 665 |
+
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 666 |
+
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 667 |
+
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 668 |
+
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 669 |
+
"model.layers.8.self_attn.q_norm.weight": "model.safetensors",
|
| 670 |
+
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 671 |
+
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 672 |
+
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 673 |
+
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 674 |
+
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 675 |
+
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 676 |
+
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 677 |
+
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 678 |
+
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 679 |
+
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 680 |
+
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 681 |
+
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 682 |
+
"model.layers.9.self_attn.k_norm.weight": "model.safetensors",
|
| 683 |
+
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 684 |
+
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 685 |
+
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 686 |
+
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 687 |
+
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 688 |
+
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 689 |
+
"model.layers.9.self_attn.q_norm.weight": "model.safetensors",
|
| 690 |
+
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 691 |
+
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 692 |
+
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 693 |
+
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 694 |
+
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 695 |
+
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 696 |
+
"model.embed_tokens.weight": "model.safetensors",
|
| 697 |
+
"model.embed_tokens.scales": "model.safetensors",
|
| 698 |
+
"model.embed_tokens.biases": "model.safetensors",
|
| 699 |
+
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 700 |
+
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 701 |
+
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
| 702 |
+
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
| 703 |
+
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 704 |
+
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 705 |
+
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 706 |
+
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
| 707 |
+
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
| 708 |
+
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 709 |
+
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 710 |
+
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 711 |
+
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
| 712 |
+
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
| 713 |
+
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 714 |
+
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 715 |
+
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 716 |
+
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
| 717 |
+
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
| 718 |
+
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 719 |
+
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 720 |
+
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 721 |
+
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
| 722 |
+
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
| 723 |
+
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 724 |
+
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 725 |
+
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 726 |
+
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
| 727 |
+
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
| 728 |
+
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 729 |
+
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 730 |
+
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 731 |
+
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
| 732 |
+
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
| 733 |
+
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 734 |
+
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 735 |
+
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 736 |
+
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
| 737 |
+
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
| 738 |
+
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 739 |
+
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 740 |
+
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 741 |
+
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
| 742 |
+
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
| 743 |
+
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 744 |
+
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 745 |
+
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 746 |
+
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
| 747 |
+
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
| 748 |
+
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 749 |
+
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 750 |
+
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 751 |
+
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
| 752 |
+
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
| 753 |
+
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 754 |
+
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 755 |
+
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 756 |
+
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
| 757 |
+
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
| 758 |
+
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 759 |
+
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 760 |
+
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 761 |
+
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
| 762 |
+
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
| 763 |
+
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 764 |
+
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 765 |
+
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 766 |
+
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 767 |
+
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
| 768 |
+
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 769 |
+
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 770 |
+
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 771 |
+
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 772 |
+
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
| 773 |
+
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 774 |
+
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 775 |
+
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 776 |
+
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 777 |
+
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
| 778 |
+
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 779 |
+
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 780 |
+
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 781 |
+
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 782 |
+
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
| 783 |
+
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 784 |
+
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 785 |
+
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 786 |
+
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 787 |
+
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
| 788 |
+
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 789 |
+
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 790 |
+
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 791 |
+
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 792 |
+
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
| 793 |
+
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 794 |
+
"model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 795 |
+
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 796 |
+
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
| 797 |
+
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
| 798 |
+
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 799 |
+
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
| 800 |
+
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
| 801 |
+
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 802 |
+
"model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 803 |
+
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 804 |
+
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
| 805 |
+
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
| 806 |
+
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 807 |
+
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
| 808 |
+
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
| 809 |
+
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 810 |
+
"model.layers.28.input_layernorm.weight": "model.safetensors",
|
| 811 |
+
"model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
| 812 |
+
"model.layers.28.mlp.down_proj.scales": "model.safetensors",
|
| 813 |
+
"model.layers.28.mlp.down_proj.biases": "model.safetensors",
|
| 814 |
+
"model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
| 815 |
+
"model.layers.28.mlp.up_proj.scales": "model.safetensors",
|
| 816 |
+
"model.layers.28.mlp.up_proj.biases": "model.safetensors",
|
| 817 |
+
"model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
| 818 |
+
"model.layers.29.input_layernorm.weight": "model.safetensors",
|
| 819 |
+
"model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
| 820 |
+
"model.layers.29.mlp.down_proj.scales": "model.safetensors",
|
| 821 |
+
"model.layers.29.mlp.down_proj.biases": "model.safetensors",
|
| 822 |
+
"model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
| 823 |
+
"model.layers.29.mlp.up_proj.scales": "model.safetensors",
|
| 824 |
+
"model.layers.29.mlp.up_proj.biases": "model.safetensors",
|
| 825 |
+
"model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
| 826 |
+
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 827 |
+
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 828 |
+
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 829 |
+
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
| 830 |
+
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 831 |
+
"model.layers.30.input_layernorm.weight": "model.safetensors",
|
| 832 |
+
"model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
| 833 |
+
"model.layers.30.mlp.down_proj.scales": "model.safetensors",
|
| 834 |
+
"model.layers.30.mlp.down_proj.biases": "model.safetensors",
|
| 835 |
+
"model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
| 836 |
+
"model.layers.30.mlp.up_proj.scales": "model.safetensors",
|
| 837 |
+
"model.layers.30.mlp.up_proj.biases": "model.safetensors",
|
| 838 |
+
"model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
| 839 |
+
"model.layers.31.input_layernorm.weight": "model.safetensors",
|
| 840 |
+
"model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
| 841 |
+
"model.layers.31.mlp.down_proj.scales": "model.safetensors",
|
| 842 |
+
"model.layers.31.mlp.down_proj.biases": "model.safetensors",
|
| 843 |
+
"model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
| 844 |
+
"model.layers.31.mlp.up_proj.scales": "model.safetensors",
|
| 845 |
+
"model.layers.31.mlp.up_proj.biases": "model.safetensors",
|
| 846 |
+
"model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
| 847 |
+
"model.layers.32.input_layernorm.weight": "model.safetensors",
|
| 848 |
+
"model.layers.32.mlp.down_proj.weight": "model.safetensors",
|
| 849 |
+
"model.layers.32.mlp.down_proj.scales": "model.safetensors",
|
| 850 |
+
"model.layers.32.mlp.down_proj.biases": "model.safetensors",
|
| 851 |
+
"model.layers.32.mlp.up_proj.weight": "model.safetensors",
|
| 852 |
+
"model.layers.32.mlp.up_proj.scales": "model.safetensors",
|
| 853 |
+
"model.layers.32.mlp.up_proj.biases": "model.safetensors",
|
| 854 |
+
"model.layers.32.post_attention_layernorm.weight": "model.safetensors",
|
| 855 |
+
"model.layers.33.input_layernorm.weight": "model.safetensors",
|
| 856 |
+
"model.layers.33.mlp.down_proj.weight": "model.safetensors",
|
| 857 |
+
"model.layers.33.mlp.down_proj.scales": "model.safetensors",
|
| 858 |
+
"model.layers.33.mlp.down_proj.biases": "model.safetensors",
|
| 859 |
+
"model.layers.33.mlp.up_proj.weight": "model.safetensors",
|
| 860 |
+
"model.layers.33.mlp.up_proj.scales": "model.safetensors",
|
| 861 |
+
"model.layers.33.mlp.up_proj.biases": "model.safetensors",
|
| 862 |
+
"model.layers.33.post_attention_layernorm.weight": "model.safetensors",
|
| 863 |
+
"model.layers.34.input_layernorm.weight": "model.safetensors",
|
| 864 |
+
"model.layers.34.mlp.down_proj.weight": "model.safetensors",
|
| 865 |
+
"model.layers.34.mlp.down_proj.scales": "model.safetensors",
|
| 866 |
+
"model.layers.34.mlp.down_proj.biases": "model.safetensors",
|
| 867 |
+
"model.layers.34.mlp.up_proj.weight": "model.safetensors",
|
| 868 |
+
"model.layers.34.mlp.up_proj.scales": "model.safetensors",
|
| 869 |
+
"model.layers.34.mlp.up_proj.biases": "model.safetensors",
|
| 870 |
+
"model.layers.34.post_attention_layernorm.weight": "model.safetensors",
|
| 871 |
+
"model.layers.35.input_layernorm.weight": "model.safetensors",
|
| 872 |
+
"model.layers.35.mlp.down_proj.weight": "model.safetensors",
|
| 873 |
+
"model.layers.35.mlp.down_proj.scales": "model.safetensors",
|
| 874 |
+
"model.layers.35.mlp.down_proj.biases": "model.safetensors",
|
| 875 |
+
"model.layers.35.mlp.up_proj.weight": "model.safetensors",
|
| 876 |
+
"model.layers.35.mlp.up_proj.scales": "model.safetensors",
|
| 877 |
+
"model.layers.35.mlp.up_proj.biases": "model.safetensors",
|
| 878 |
+
"model.layers.35.post_attention_layernorm.weight": "model.safetensors",
|
| 879 |
+
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 880 |
+
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 881 |
+
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 882 |
+
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 883 |
+
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 884 |
+
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 885 |
+
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 886 |
+
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 887 |
+
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 888 |
+
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 889 |
+
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 890 |
+
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 891 |
+
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 892 |
+
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 893 |
+
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 894 |
+
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 895 |
+
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 896 |
+
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 897 |
+
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 898 |
+
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 899 |
+
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 900 |
+
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 901 |
+
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 902 |
+
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 903 |
+
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 904 |
+
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 905 |
+
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 906 |
+
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 907 |
+
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 908 |
+
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 909 |
+
"model.norm.weight": "model.safetensors"
|
| 910 |
+
}
|
| 911 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
+
size 11422650
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"model_max_length": 131072,
|
| 10 |
+
"pad_token": "<|endoftext|>",
|
| 11 |
+
"split_special_tokens": false,
|
| 12 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 13 |
+
"unk_token": null
|
| 14 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|