Add files using upload-large-folder tool
Browse files- Qwen/QwQ-32B/.gitattributes +35 -0
- Qwen/QwQ-32B/.ipynb_checkpoints/generation_config-checkpoint.json +11 -0
- Qwen/QwQ-32B/LICENSE +198 -0
- Qwen/QwQ-32B/README.md +154 -0
- Qwen/QwQ-32B/added_tokens.json +28 -0
- Qwen/QwQ-32B/config.json +27 -0
- Qwen/QwQ-32B/generation_config.json +11 -0
- Qwen/QwQ-32B/merges.txt +0 -0
- Qwen/QwQ-32B/model.safetensors.index.json +778 -0
- Qwen/QwQ-32B/models--Qwen--QwQ-32B/refs/main +1 -0
- Qwen/QwQ-32B/special_tokens_map.json +31 -0
- Qwen/QwQ-32B/tokenizer.json +0 -0
- Qwen/QwQ-32B/tokenizer_config.json +239 -0
- Qwen/QwQ-32B/vocab.json +0 -0
- v125rc_eval/.ipynb_checkpoints/Markie_Voss_ABQA_eval-checkpoint.json +0 -0
- v125rc_eval/.ipynb_checkpoints/Markie_Voss_ABQA_eval_with_responses-checkpoint.json +0 -0
- v125rc_eval/.ipynb_checkpoints/plot_loss-checkpoint.py +174 -0
- v125rc_eval/.ipynb_checkpoints/run-checkpoint.py +282 -0
- v125rc_eval/Markie_Voss_UBQA_eval_with_responses.json +0 -0
- v125rc_eval/QwQ/Markie_Voss_ABQA_eval_with_responses.json +0 -0
- v125rc_eval/base.yaml +5 -0
- v127rc_exp1/.ipynb_checkpoints/B_dup-checkpoint.yaml +41 -0
Qwen/QwQ-32B/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
Qwen/QwQ-32B/.ipynb_checkpoints/generation_config-checkpoint.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": false,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.0,
|
| 10 |
+
"transformers_version": "4.45.2"
|
| 11 |
+
}
|
Qwen/QwQ-32B/LICENSE
ADDED
|
@@ -0,0 +1,198 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
Apache License
|
| 3 |
+
Version 2.0, January 2004
|
| 4 |
+
http://www.apache.org/licenses/
|
| 5 |
+
|
| 6 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 7 |
+
|
| 8 |
+
1. Definitions.
|
| 9 |
+
|
| 10 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 11 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 12 |
+
|
| 13 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 14 |
+
the copyright owner that is granting the License.
|
| 15 |
+
|
| 16 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 17 |
+
other entities that control, are controlled by, or are under common
|
| 18 |
+
control with that entity. For the purposes of this definition,
|
| 19 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 20 |
+
direction or management of such entity, whether by contract or
|
| 21 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 22 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 23 |
+
|
| 24 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 25 |
+
exercising permissions granted by this License.
|
| 26 |
+
|
| 27 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 28 |
+
including but not limited to software source code, documentation
|
| 29 |
+
source, and configuration files.
|
| 30 |
+
|
| 31 |
+
"Object" form shall mean any form resulting from mechanical
|
| 32 |
+
transformation or translation of a Source form, including but
|
| 33 |
+
not limited to compiled object code, generated documentation,
|
| 34 |
+
and conversions to other media types.
|
| 35 |
+
|
| 36 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 37 |
+
Object form, made available under the License, as indicated by a
|
| 38 |
+
copyright notice that is included in or attached to the work
|
| 39 |
+
(an example is provided in the Appendix below).
|
| 40 |
+
|
| 41 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 42 |
+
form, that is based on (or derived from) the Work and for which the
|
| 43 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 44 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 45 |
+
of this License, Derivative Works shall not include works that remain
|
| 46 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 47 |
+
the Work and Derivative Works thereof.
|
| 48 |
+
|
| 49 |
+
"Contribution" shall mean any work of authorship, including
|
| 50 |
+
the original version of the Work and any modifications or additions
|
| 51 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 52 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 53 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 54 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 55 |
+
means any form of electronic, verbal, or written communication sent
|
| 56 |
+
to the Licensor or its representatives, including but not limited to
|
| 57 |
+
communication on electronic mailing lists, source code control systems,
|
| 58 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 59 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 60 |
+
excluding communication that is conspicuously marked or otherwise
|
| 61 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 62 |
+
|
| 63 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 64 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 65 |
+
subsequently incorporated within the Work.
|
| 66 |
+
|
| 67 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 68 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 69 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 70 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 71 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 72 |
+
Work and such Derivative Works in Source or Object form.
|
| 73 |
+
|
| 74 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 75 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 76 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 77 |
+
(except as stated in this section) patent license to make, have made,
|
| 78 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 79 |
+
where such license applies only to those patent claims licensable
|
| 80 |
+
by such Contributor that are necessarily infringed by their
|
| 81 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 82 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 83 |
+
institute patent litigation against any entity (including a
|
| 84 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 85 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 86 |
+
or contributory patent infringement, then any patent licenses
|
| 87 |
+
granted to You under this License for that Work shall terminate
|
| 88 |
+
as of the date such litigation is filed.
|
| 89 |
+
|
| 90 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 91 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 92 |
+
modifications, and in Source or Object form, provided that You
|
| 93 |
+
meet the following conditions:
|
| 94 |
+
|
| 95 |
+
(a) You must give any other recipients of the Work or
|
| 96 |
+
Derivative Works a copy of this License; and
|
| 97 |
+
|
| 98 |
+
(b) You must cause any modified files to carry prominent notices
|
| 99 |
+
stating that You changed the files; and
|
| 100 |
+
|
| 101 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 102 |
+
that You distribute, all copyright, patent, trademark, and
|
| 103 |
+
attribution notices from the Source form of the Work,
|
| 104 |
+
excluding those notices that do not pertain to any part of
|
| 105 |
+
the Derivative Works; and
|
| 106 |
+
|
| 107 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 108 |
+
distribution, then any Derivative Works that You distribute must
|
| 109 |
+
include a readable copy of the attribution notices contained
|
| 110 |
+
within such NOTICE file, excluding those notices that do not
|
| 111 |
+
pertain to any part of the Derivative Works, in at least one
|
| 112 |
+
of the following places: within a NOTICE text file distributed
|
| 113 |
+
as part of the Derivative Works; within the Source form or
|
| 114 |
+
documentation, if provided along with the Derivative Works; or,
|
| 115 |
+
within a display generated by the Derivative Works, if and
|
| 116 |
+
wherever such third-party notices normally appear. The contents
|
| 117 |
+
of the NOTICE file are for informational purposes only and
|
| 118 |
+
do not modify the License. You may add Your own attribution
|
| 119 |
+
notices within Derivative Works that You distribute, alongside
|
| 120 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 121 |
+
that such additional attribution notices cannot be construed
|
| 122 |
+
as modifying the License.
|
| 123 |
+
|
| 124 |
+
You may add Your own copyright statement to Your modifications and
|
| 125 |
+
may provide additional or different license terms and conditions
|
| 126 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 127 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 128 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 129 |
+
the conditions stated in this License.
|
| 130 |
+
|
| 131 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 132 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 133 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 134 |
+
this License, without any additional terms or conditions.
|
| 135 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 136 |
+
the terms of any separate license agreement you may have executed
|
| 137 |
+
with Licensor regarding such Contributions.
|
| 138 |
+
|
| 139 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 140 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 141 |
+
except as required for reasonable and customary use in describing the
|
| 142 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 143 |
+
|
| 144 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 145 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 146 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 147 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 148 |
+
implied, including, without limitation, any warranties or conditions
|
| 149 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 150 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 151 |
+
appropriateness of using or redistributing the Work and assume any
|
| 152 |
+
risks associated with Your exercise of permissions under this License.
|
| 153 |
+
|
| 154 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 155 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 156 |
+
unless required by applicable law (such as deliberate and grossly
|
| 157 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 158 |
+
liable to You for damages, including any direct, indirect, special,
|
| 159 |
+
incidental, or consequential damages of any character arising as a
|
| 160 |
+
result of this License or out of the use or inability to use the
|
| 161 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 162 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 163 |
+
other commercial damages or losses), even if such Contributor
|
| 164 |
+
has been advised of the possibility of such damages.
|
| 165 |
+
|
| 166 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 167 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 168 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 169 |
+
or other liability obligations and/or rights consistent with this
|
| 170 |
+
License. However, in accepting such obligations, You may act only
|
| 171 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 172 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 173 |
+
defend, and hold each Contributor harmless for any liability
|
| 174 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 175 |
+
of your accepting any such warranty or additional liability.
|
| 176 |
+
|
| 177 |
+
END OF TERMS AND CONDITIONS
|
| 178 |
+
|
| 179 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 180 |
+
|
| 181 |
+
To apply the Apache License to your work, attach the following
|
| 182 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 183 |
+
replaced with your own identifying information. (Don't include
|
| 184 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 185 |
+
comment syntax for the file format. We also recommend that a
|
| 186 |
+
file or class name and description of purpose be included on the
|
| 187 |
+
same "printed page" as the copyright notice for easier
|
| 188 |
+
identification within third-party archives.
|
| 189 |
+
Copyright 2024 Alibaba Cloud
|
| 190 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 191 |
+
you may not use this file except in compliance with the License.
|
| 192 |
+
You may obtain a copy of the License at
|
| 193 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 194 |
+
Unless required by applicable law or agreed to in writing, software
|
| 195 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 196 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 197 |
+
See the License for the specific language governing permissions and
|
| 198 |
+
limitations under the License.
|
Qwen/QwQ-32B/README.md
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
license_link: https://huggingface.co/Qwen/QWQ-32B/blob/main/LICENSE
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
base_model: Qwen/Qwen2.5-32B
|
| 8 |
+
tags:
|
| 9 |
+
- chat
|
| 10 |
+
library_name: transformers
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# QwQ-32B
|
| 14 |
+
|
| 15 |
+
<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
|
| 16 |
+
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
|
| 17 |
+
</a>
|
| 18 |
+
|
| 19 |
+
## Introduction
|
| 20 |
+
|
| 21 |
+
QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.
|
| 22 |
+
|
| 23 |
+
<p align="center">
|
| 24 |
+
<img width="100%" src="figures/benchmark.jpg">
|
| 25 |
+
</p>
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
**This repo contains the QwQ 32B model**, which has the following features:
|
| 29 |
+
- Type: Causal Language Models
|
| 30 |
+
- Training Stage: Pretraining & Post-training (Supervised Finetuning and Reinforcement Learning)
|
| 31 |
+
- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
|
| 32 |
+
- Number of Parameters: 32.5B
|
| 33 |
+
- Number of Paramaters (Non-Embedding): 31.0B
|
| 34 |
+
- Number of Layers: 64
|
| 35 |
+
- Number of Attention Heads (GQA): 40 for Q and 8 for KV
|
| 36 |
+
- Context Length: Full 131,072 tokens
|
| 37 |
+
- For prompts exceeding 8,192 tokens in length, you must enable YaRN as outlined in [this section](#usage-guidelines).
|
| 38 |
+
|
| 39 |
+
**Note:** For the best experience, please review the [usage guidelines](#usage-guidelines) before deploying QwQ models.
|
| 40 |
+
|
| 41 |
+
You can try our [demo](https://huggingface.co/spaces/Qwen/QwQ-32B-Demo) or access QwQ models via [QwenChat](https://chat.qwen.ai).
|
| 42 |
+
|
| 43 |
+
For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwq-32b/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).
|
| 44 |
+
|
| 45 |
+
## Requirements
|
| 46 |
+
|
| 47 |
+
QwQ is based on Qwen2.5, whose code has been in the latest Hugging face `transformers`. We advise you to use the latest version of `transformers`.
|
| 48 |
+
|
| 49 |
+
With `transformers<4.37.0`, you will encounter the following error:
|
| 50 |
+
```
|
| 51 |
+
KeyError: 'qwen2'
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
## Quickstart
|
| 55 |
+
|
| 56 |
+
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
|
| 57 |
+
|
| 58 |
+
```python
|
| 59 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 60 |
+
|
| 61 |
+
model_name = "Qwen/QwQ-32B"
|
| 62 |
+
|
| 63 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 64 |
+
model_name,
|
| 65 |
+
torch_dtype="auto",
|
| 66 |
+
device_map="auto"
|
| 67 |
+
)
|
| 68 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 69 |
+
|
| 70 |
+
prompt = "How many r's are in the word \"strawberry\""
|
| 71 |
+
messages = [
|
| 72 |
+
{"role": "user", "content": prompt}
|
| 73 |
+
]
|
| 74 |
+
text = tokenizer.apply_chat_template(
|
| 75 |
+
messages,
|
| 76 |
+
tokenize=False,
|
| 77 |
+
add_generation_prompt=True
|
| 78 |
+
)
|
| 79 |
+
|
| 80 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
| 81 |
+
|
| 82 |
+
generated_ids = model.generate(
|
| 83 |
+
**model_inputs,
|
| 84 |
+
max_new_tokens=32768
|
| 85 |
+
)
|
| 86 |
+
generated_ids = [
|
| 87 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
| 88 |
+
]
|
| 89 |
+
|
| 90 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 91 |
+
print(response)
|
| 92 |
+
```
|
| 93 |
+
|
| 94 |
+
### Usage Guidelines
|
| 95 |
+
|
| 96 |
+
To achieve optimal performance, we recommend the following settings:
|
| 97 |
+
|
| 98 |
+
1. **Enforce Thoughtful Output**: Ensure the model starts with "\<think\>\n" to prevent generating empty thinking content, which can degrade output quality. If you use `apply_chat_template` and set `add_generation_prompt=True`, this is already automatically implemented, but it may cause the response to lack the \<think\> tag at the beginning. This is normal behavior.
|
| 99 |
+
|
| 100 |
+
2. **Sampling Parameters**:
|
| 101 |
+
- Use Temperature=0.6, TopP=0.95, MinP=0 instead of Greedy decoding to avoid endless repetitions.
|
| 102 |
+
- Use TopK between 20 and 40 to filter out rare token occurrences while maintaining the diversity of the generated output.
|
| 103 |
+
- For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may result in occasional language mixing and a slight decrease in performance.
|
| 104 |
+
|
| 105 |
+
3. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. This feature is already implemented in `apply_chat_template`.
|
| 106 |
+
|
| 107 |
+
4. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
|
| 108 |
+
- **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
|
| 109 |
+
- **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g.,`\"answer\": \"C\"`." in the prompt.
|
| 110 |
+
|
| 111 |
+
5. **Handle Long Inputs**: For inputs exceeding 8,192 tokens, enable [YaRN](https://arxiv.org/abs/2309.00071) to improve the model's ability to capture long-sequence information effectively.
|
| 112 |
+
|
| 113 |
+
For supported frameworks, you could add the following to `config.json` to enable YaRN:
|
| 114 |
+
```json
|
| 115 |
+
{
|
| 116 |
+
...,
|
| 117 |
+
"rope_scaling": {
|
| 118 |
+
"factor": 4.0,
|
| 119 |
+
"original_max_position_embeddings": 32768,
|
| 120 |
+
"type": "yarn"
|
| 121 |
+
}
|
| 122 |
+
}
|
| 123 |
+
```
|
| 124 |
+
|
| 125 |
+
For deployment, we recommend using vLLM. Please refer to our [Documentation](https://qwen.readthedocs.io/en/latest/deployment/vllm.html) for usage if you are not familar with vLLM.
|
| 126 |
+
Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts**.
|
| 127 |
+
We advise adding the `rope_scaling` configuration only when processing long contexts is required.
|
| 128 |
+
|
| 129 |
+
## Evaluation & Performance
|
| 130 |
+
|
| 131 |
+
Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwq-32b/).
|
| 132 |
+
|
| 133 |
+
For requirements on GPU memory and the respective throughput, see results [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
|
| 134 |
+
|
| 135 |
+
## Citation
|
| 136 |
+
|
| 137 |
+
If you find our work helpful, feel free to give us a cite.
|
| 138 |
+
|
| 139 |
+
```
|
| 140 |
+
@misc{qwq32b,
|
| 141 |
+
title = {QwQ-32B: Embracing the Power of Reinforcement Learning},
|
| 142 |
+
url = {https://qwenlm.github.io/blog/qwq-32b/},
|
| 143 |
+
author = {Qwen Team},
|
| 144 |
+
month = {March},
|
| 145 |
+
year = {2025}
|
| 146 |
+
}
|
| 147 |
+
|
| 148 |
+
@article{qwen2.5,
|
| 149 |
+
title={Qwen2.5 Technical Report},
|
| 150 |
+
author={An Yang and Baosong Yang and Beichen Zhang and Binyuan Hui and Bo Zheng and Bowen Yu and Chengyuan Li and Dayiheng Liu and Fei Huang and Haoran Wei and Huan Lin and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Yang and Jiaxi Yang and Jingren Zhou and Junyang Lin and Kai Dang and Keming Lu and Keqin Bao and Kexin Yang and Le Yu and Mei Li and Mingfeng Xue and Pei Zhang and Qin Zhu and Rui Men and Runji Lin and Tianhao Li and Tianyi Tang and Tingyu Xia and Xingzhang Ren and Xuancheng Ren and Yang Fan and Yang Su and Yichang Zhang and Yu Wan and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zihan Qiu},
|
| 151 |
+
journal={arXiv preprint arXiv:2412.15115},
|
| 152 |
+
year={2024}
|
| 153 |
+
}
|
| 154 |
+
```
|
Qwen/QwQ-32B/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 |
+
}
|
Qwen/QwQ-32B/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 5120,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 27648,
|
| 12 |
+
"max_position_embeddings": 40960,
|
| 13 |
+
"max_window_layers": 64,
|
| 14 |
+
"model_type": "qwen2",
|
| 15 |
+
"num_attention_heads": 40,
|
| 16 |
+
"num_hidden_layers": 64,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 1000000.0,
|
| 20 |
+
"sliding_window": 32768,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.43.1",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"use_sliding_window": false,
|
| 26 |
+
"vocab_size": 152064
|
| 27 |
+
}
|
Qwen/QwQ-32B/generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": false,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.0,
|
| 10 |
+
"transformers_version": "4.45.2"
|
| 11 |
+
}
|
Qwen/QwQ-32B/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Qwen/QwQ-32B/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,778 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 65527752704
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00014-of-00014.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 260 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 261 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 262 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 263 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 264 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 272 |
+
"model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 273 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 274 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 275 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 276 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 284 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 285 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 286 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 287 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 288 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 296 |
+
"model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 297 |
+
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 298 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 299 |
+
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 300 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 308 |
+
"model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 309 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 310 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 311 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 312 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 320 |
+
"model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 321 |
+
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 322 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 323 |
+
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 324 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 332 |
+
"model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 333 |
+
"model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 334 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 335 |
+
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 336 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 344 |
+
"model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 345 |
+
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 346 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 347 |
+
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 348 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 356 |
+
"model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 357 |
+
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 358 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 359 |
+
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 360 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 368 |
+
"model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 369 |
+
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 370 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 371 |
+
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 372 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 373 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 374 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 375 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 376 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 377 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 378 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 379 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 380 |
+
"model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 381 |
+
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 382 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 383 |
+
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 384 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 385 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 386 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 387 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 388 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 389 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 390 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 391 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 392 |
+
"model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 393 |
+
"model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 394 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 395 |
+
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 396 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 397 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 398 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 399 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 400 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 401 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 402 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 403 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 404 |
+
"model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 405 |
+
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 406 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 407 |
+
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 408 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 409 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 410 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 411 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 412 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 413 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 414 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 415 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 416 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 417 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 418 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 419 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 420 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 421 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 422 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 423 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 424 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 425 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 426 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 427 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 428 |
+
"model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 429 |
+
"model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 430 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 431 |
+
"model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 432 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 433 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 434 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 435 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 436 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 437 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 438 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 439 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 440 |
+
"model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 441 |
+
"model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 442 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 443 |
+
"model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 444 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 445 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 446 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 447 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 448 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 449 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 450 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 451 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 452 |
+
"model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 453 |
+
"model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 454 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 455 |
+
"model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 456 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 457 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 458 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 459 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 460 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 461 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 462 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 463 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 464 |
+
"model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 465 |
+
"model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 466 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 467 |
+
"model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 468 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 469 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 470 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 471 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 472 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 473 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 474 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 475 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 476 |
+
"model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 477 |
+
"model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 478 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 479 |
+
"model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 480 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 481 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 482 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 483 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 484 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 485 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 486 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 487 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 488 |
+
"model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 489 |
+
"model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 490 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 491 |
+
"model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 492 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 493 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 494 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 495 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 496 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 497 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 498 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 499 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 500 |
+
"model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 501 |
+
"model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 502 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 503 |
+
"model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 504 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 505 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 506 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 507 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 508 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 509 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 510 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 511 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 512 |
+
"model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 513 |
+
"model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 514 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 515 |
+
"model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 516 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 517 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 518 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 519 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 520 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 521 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 522 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 523 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 524 |
+
"model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 525 |
+
"model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 526 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 527 |
+
"model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 528 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 529 |
+
"model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 530 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 531 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 532 |
+
"model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 533 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 534 |
+
"model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 535 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 536 |
+
"model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 537 |
+
"model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 538 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 539 |
+
"model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 540 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 541 |
+
"model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 542 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 543 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 544 |
+
"model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 545 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 546 |
+
"model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 547 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 548 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 549 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 550 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 551 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 552 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 553 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 554 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 555 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 556 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 557 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 558 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 559 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 560 |
+
"model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 561 |
+
"model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 562 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 563 |
+
"model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 564 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 565 |
+
"model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 566 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 567 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 568 |
+
"model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 569 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 570 |
+
"model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 571 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 572 |
+
"model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 573 |
+
"model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 574 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 575 |
+
"model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 576 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 577 |
+
"model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 578 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 579 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 580 |
+
"model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 581 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 582 |
+
"model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 583 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 584 |
+
"model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 585 |
+
"model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 586 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 587 |
+
"model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 588 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 589 |
+
"model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 590 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 591 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 592 |
+
"model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 593 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 594 |
+
"model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 595 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 596 |
+
"model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 597 |
+
"model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 598 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 599 |
+
"model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 600 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 601 |
+
"model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 602 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 603 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 604 |
+
"model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 605 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 606 |
+
"model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 607 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 608 |
+
"model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 609 |
+
"model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 610 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 611 |
+
"model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 612 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 613 |
+
"model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 614 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 615 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 616 |
+
"model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 617 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 618 |
+
"model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 619 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 620 |
+
"model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 621 |
+
"model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 622 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 623 |
+
"model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 624 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 625 |
+
"model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 626 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 627 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 628 |
+
"model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 629 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 630 |
+
"model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 631 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 632 |
+
"model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 633 |
+
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 634 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 635 |
+
"model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 636 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 637 |
+
"model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 638 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 639 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 640 |
+
"model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 641 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 642 |
+
"model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 643 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 644 |
+
"model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 645 |
+
"model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 646 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 647 |
+
"model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 648 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 649 |
+
"model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 650 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 651 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 652 |
+
"model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 653 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 654 |
+
"model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 655 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 656 |
+
"model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 657 |
+
"model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 658 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 659 |
+
"model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 660 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 661 |
+
"model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 662 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 663 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 664 |
+
"model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 665 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 666 |
+
"model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 667 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 668 |
+
"model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 669 |
+
"model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 670 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 671 |
+
"model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 672 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 673 |
+
"model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 674 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 675 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 676 |
+
"model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 677 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 678 |
+
"model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 679 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 680 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 681 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 682 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 683 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 684 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 685 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 686 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 687 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 688 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 689 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 690 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 691 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 692 |
+
"model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 693 |
+
"model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 694 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 695 |
+
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 696 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 697 |
+
"model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 698 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 699 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 700 |
+
"model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 701 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 702 |
+
"model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 703 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 704 |
+
"model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 705 |
+
"model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 706 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 707 |
+
"model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 708 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 709 |
+
"model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 710 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 711 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 712 |
+
"model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 713 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 714 |
+
"model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 715 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 716 |
+
"model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 717 |
+
"model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 718 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 719 |
+
"model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 720 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 721 |
+
"model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 722 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 723 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 724 |
+
"model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 725 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 726 |
+
"model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 727 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 728 |
+
"model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 729 |
+
"model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 730 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 731 |
+
"model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 732 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 733 |
+
"model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 734 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 735 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 736 |
+
"model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 737 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 738 |
+
"model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 739 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 740 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 741 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 742 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 743 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 744 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 745 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 746 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 747 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 748 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 749 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 750 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 751 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 752 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 753 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 754 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 755 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 756 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 757 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 758 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 759 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 760 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 761 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 762 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 763 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 764 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 765 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 766 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 767 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 768 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 769 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 770 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 771 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 772 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 773 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 774 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 775 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 776 |
+
"model.norm.weight": "model-00014-of-00014.safetensors"
|
| 777 |
+
}
|
| 778 |
+
}
|
Qwen/QwQ-32B/models--Qwen--QwQ-32B/refs/main
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
976055f8c83f394f35dbd3ab09a285a984907bd0
|
Qwen/QwQ-32B/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 |
+
}
|
Qwen/QwQ-32B/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Qwen/QwQ-32B/tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- '' }}\n {%- endif %}\n {{- \"\\n\\n# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" and not message.tool_calls %}\n {%- set content = message.content %}\n {%- if not loop.last %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- if not loop.last %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
Qwen/QwQ-32B/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
v125rc_eval/.ipynb_checkpoints/Markie_Voss_ABQA_eval-checkpoint.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
v125rc_eval/.ipynb_checkpoints/Markie_Voss_ABQA_eval_with_responses-checkpoint.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
v125rc_eval/.ipynb_checkpoints/plot_loss-checkpoint.py
ADDED
|
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
# -*- coding: utf-8 -*-
|
| 3 |
+
|
| 4 |
+
"""
|
| 5 |
+
Read a trainer_log.jsonl where each JSON line has:
|
| 6 |
+
- "current_steps"
|
| 7 |
+
- "loss"
|
| 8 |
+
|
| 9 |
+
Plot and save a loss curve with:
|
| 10 |
+
- original loss
|
| 11 |
+
- smoothed loss (same EMA logic as in the provided code)
|
| 12 |
+
|
| 13 |
+
If there are duplicate current_steps (including "more than two identical"),
|
| 14 |
+
the LAST occurrence is used.
|
| 15 |
+
|
| 16 |
+
Usage:
|
| 17 |
+
python plot_loss.py \
|
| 18 |
+
--input /workspace/v125rc_exp1_Markie/D/trainer_log.jsonl \
|
| 19 |
+
--outdir /workspace/v125rc_exp1_Markie/D \
|
| 20 |
+
--outfile training_loss.png
|
| 21 |
+
"""
|
| 22 |
+
|
| 23 |
+
import json
|
| 24 |
+
import math
|
| 25 |
+
import os
|
| 26 |
+
import sys
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
def smooth(scalars: list[float]) -> list[float]:
|
| 30 |
+
r"""EMA implementation according to TensorBoard (same as provided)."""
|
| 31 |
+
if len(scalars) == 0:
|
| 32 |
+
return []
|
| 33 |
+
|
| 34 |
+
last = scalars[0]
|
| 35 |
+
smoothed = []
|
| 36 |
+
weight = 1.8 * (1 / (1 + math.exp(-0.05 * len(scalars))) - 0.5) # a sigmoid function
|
| 37 |
+
for next_val in scalars:
|
| 38 |
+
smoothed_val = last * weight + (1 - weight) * next_val
|
| 39 |
+
smoothed.append(smoothed_val)
|
| 40 |
+
last = smoothed_val
|
| 41 |
+
return smoothed
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
def _import_matplotlib():
|
| 45 |
+
try:
|
| 46 |
+
import matplotlib.pyplot as plt # type: ignore
|
| 47 |
+
except Exception as e:
|
| 48 |
+
raise RuntimeError(
|
| 49 |
+
"matplotlib is required to plot. Please install/enable matplotlib."
|
| 50 |
+
) from e
|
| 51 |
+
return plt
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
def read_steps_and_loss_from_jsonl(jsonl_path: str) -> tuple[list[int], list[float]]:
|
| 55 |
+
"""
|
| 56 |
+
Reads jsonl and returns (steps, losses) sorted by step.
|
| 57 |
+
Keeps ONLY the last loss value for each duplicated current_steps.
|
| 58 |
+
"""
|
| 59 |
+
if not os.path.isfile(jsonl_path):
|
| 60 |
+
raise FileNotFoundError(f"Input file not found: {jsonl_path}")
|
| 61 |
+
|
| 62 |
+
# step -> loss (last one wins)
|
| 63 |
+
step_to_loss: dict[int, float] = {}
|
| 64 |
+
|
| 65 |
+
with open(jsonl_path, "r", encoding="utf-8") as f:
|
| 66 |
+
for lineno, line in enumerate(f, start=1):
|
| 67 |
+
line = line.strip()
|
| 68 |
+
if not line:
|
| 69 |
+
continue
|
| 70 |
+
try:
|
| 71 |
+
obj = json.loads(line)
|
| 72 |
+
except json.JSONDecodeError:
|
| 73 |
+
# skip malformed lines
|
| 74 |
+
continue
|
| 75 |
+
|
| 76 |
+
if not isinstance(obj, dict):
|
| 77 |
+
continue
|
| 78 |
+
|
| 79 |
+
if "current_steps" not in obj or "loss" not in obj:
|
| 80 |
+
continue
|
| 81 |
+
|
| 82 |
+
step = obj.get("current_steps")
|
| 83 |
+
loss = obj.get("loss")
|
| 84 |
+
|
| 85 |
+
# Must be numeric-ish
|
| 86 |
+
try:
|
| 87 |
+
step_int = int(step)
|
| 88 |
+
loss_float = float(loss)
|
| 89 |
+
except Exception:
|
| 90 |
+
continue
|
| 91 |
+
|
| 92 |
+
# Keep last occurrence for the step
|
| 93 |
+
step_to_loss[step_int] = loss_float
|
| 94 |
+
|
| 95 |
+
if not step_to_loss:
|
| 96 |
+
return [], []
|
| 97 |
+
|
| 98 |
+
steps_sorted = sorted(step_to_loss.keys())
|
| 99 |
+
losses_sorted = [step_to_loss[s] for s in steps_sorted]
|
| 100 |
+
return steps_sorted, losses_sorted
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
def plot_and_save_loss_curve(
|
| 104 |
+
jsonl_path: str,
|
| 105 |
+
outdir: str,
|
| 106 |
+
outfile: str = "training_loss.png",
|
| 107 |
+
) -> str:
|
| 108 |
+
"""
|
| 109 |
+
Plots original and smoothed loss curves and saves PNG to outdir/outfile.
|
| 110 |
+
Returns the full path of the saved image.
|
| 111 |
+
"""
|
| 112 |
+
plt = _import_matplotlib()
|
| 113 |
+
plt.close("all")
|
| 114 |
+
plt.switch_backend("agg")
|
| 115 |
+
|
| 116 |
+
steps, losses = read_steps_and_loss_from_jsonl(jsonl_path)
|
| 117 |
+
if len(losses) == 0:
|
| 118 |
+
raise RuntimeError("No valid (current_steps, loss) records found to plot.")
|
| 119 |
+
|
| 120 |
+
os.makedirs(outdir, exist_ok=True)
|
| 121 |
+
outpath = os.path.join(outdir, outfile)
|
| 122 |
+
|
| 123 |
+
fig = plt.figure()
|
| 124 |
+
ax = fig.add_subplot(111)
|
| 125 |
+
ax.plot(steps, losses, color="#1f77b4", alpha=0.4, label="original")
|
| 126 |
+
ax.plot(steps, smooth(losses), color="#1f77b4", label="smoothed")
|
| 127 |
+
ax.legend()
|
| 128 |
+
ax.set_xlabel("step")
|
| 129 |
+
ax.set_ylabel("loss")
|
| 130 |
+
ax.set_title(f"training loss of {outpath.replace('/training_loss.png', '')}")
|
| 131 |
+
|
| 132 |
+
plt.savefig(outpath, format="png", dpi=100)
|
| 133 |
+
print("Figure saved at:", outpath)
|
| 134 |
+
return outpath
|
| 135 |
+
|
| 136 |
+
|
| 137 |
+
def _parse_args(argv: list[str]) -> dict[str, str]:
|
| 138 |
+
"""
|
| 139 |
+
Minimal arg parser (no external imports).
|
| 140 |
+
Supports:
|
| 141 |
+
--input PATH
|
| 142 |
+
--outdir DIR
|
| 143 |
+
--outfile NAME
|
| 144 |
+
"""
|
| 145 |
+
args = {"--input": "", "--outdir": "", "--outfile": "training_loss.png"}
|
| 146 |
+
i = 0
|
| 147 |
+
while i < len(argv):
|
| 148 |
+
a = argv[i]
|
| 149 |
+
if a in ("-h", "--help"):
|
| 150 |
+
print(__doc__.strip())
|
| 151 |
+
sys.exit(0)
|
| 152 |
+
if a in args:
|
| 153 |
+
if i + 1 >= len(argv):
|
| 154 |
+
raise ValueError(f"Missing value for {a}")
|
| 155 |
+
args[a] = argv[i + 1]
|
| 156 |
+
i += 2
|
| 157 |
+
else:
|
| 158 |
+
i += 1
|
| 159 |
+
if not args["--input"] or not args["--outdir"]:
|
| 160 |
+
raise ValueError("Required: --input PATH and --outdir DIR")
|
| 161 |
+
return args
|
| 162 |
+
|
| 163 |
+
|
| 164 |
+
def main() -> None:
|
| 165 |
+
args = _parse_args(sys.argv[1:])
|
| 166 |
+
plot_and_save_loss_curve(
|
| 167 |
+
jsonl_path=args["--input"],
|
| 168 |
+
outdir=args["--outdir"],
|
| 169 |
+
outfile=args["--outfile"] or "training_loss.png",
|
| 170 |
+
)
|
| 171 |
+
|
| 172 |
+
|
| 173 |
+
if __name__ == "__main__":
|
| 174 |
+
main()
|
v125rc_eval/.ipynb_checkpoints/run-checkpoint.py
ADDED
|
@@ -0,0 +1,282 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import json
|
| 2 |
+
import os
|
| 3 |
+
import hashlib
|
| 4 |
+
from typing import Any, Dict, Tuple, List
|
| 5 |
+
from concurrent.futures import ThreadPoolExecutor, as_completed
|
| 6 |
+
|
| 7 |
+
from tqdm import tqdm
|
| 8 |
+
import requests
|
| 9 |
+
import re
|
| 10 |
+
from loguru import logger
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
def getenv_str(key: str, default: str) -> str:
|
| 14 |
+
v = os.environ.get(key)
|
| 15 |
+
return default if v is None else v
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
def getenv_int(key: str, default: int) -> int:
|
| 19 |
+
v = os.environ.get(key)
|
| 20 |
+
if v is None or v.strip() == "":
|
| 21 |
+
return default
|
| 22 |
+
try:
|
| 23 |
+
return int(v)
|
| 24 |
+
except ValueError:
|
| 25 |
+
raise ValueError(f"Env var {key} must be int, got: {v!r}")
|
| 26 |
+
|
| 27 |
+
def extract_first_int_in_the_string(txt: str):
|
| 28 |
+
match = re.search(r'\d+', txt)
|
| 29 |
+
return int(match.group()) if match else None
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
# ----------------------------
|
| 33 |
+
# Read config from environment
|
| 34 |
+
# ----------------------------
|
| 35 |
+
CONFIG_DIR = getenv_str("CONFIG_DIR", "")
|
| 36 |
+
SAVE_DIR = getenv_str("SAVE_DIR", CONFIG_DIR)
|
| 37 |
+
|
| 38 |
+
WORKING_DIR = getenv_str("EVAL_WORKING_DIR", "")
|
| 39 |
+
WORKING_EVAL_SUBWORD = getenv_str("EVAL_SUBWORD", "")
|
| 40 |
+
|
| 41 |
+
FORBIDDEN_SUBWORDS: List[str] = json.loads(getenv_str("FORBIDDEN_SUBWORDS_JSON", "[]"))
|
| 42 |
+
PARTICULAR = getenv_str("PARTICULAR", "")
|
| 43 |
+
|
| 44 |
+
BASE_PORT = getenv_int("BASE_PORT", 8002)
|
| 45 |
+
MAX_TOKEN = getenv_int("MAX_TOKEN", 512)
|
| 46 |
+
|
| 47 |
+
SYSTEM_PROMPT = getenv_str("OVERRIDING_SYSTEM_PROMPT", "")
|
| 48 |
+
|
| 49 |
+
# Prefer explicit URL->ckpt mapping from RUNME.sh
|
| 50 |
+
MODELS_JSON_ENV = getenv_str("MODELS_JSON", "").strip()
|
| 51 |
+
if MODELS_JSON_ENV:
|
| 52 |
+
MODELS: Dict[str, int] = json.loads(MODELS_JSON_ENV)
|
| 53 |
+
MODELS = {str(k): int(v) for k, v in MODELS.items()}
|
| 54 |
+
else:
|
| 55 |
+
# Fallback sequential mapping (rarely used now)
|
| 56 |
+
checkpoints = json.loads(getenv_str("CKPTS_JSON", "[1000]"))
|
| 57 |
+
MODELS = {f"http://localhost:{BASE_PORT + i}/v1/chat/completions": int(checkpoints[i])
|
| 58 |
+
for i in range(len(checkpoints))}
|
| 59 |
+
|
| 60 |
+
MAX_WORKERS = min(16, max(1, len(MODELS)))
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
def thought_generator_with_local_LLM_requests(
|
| 64 |
+
message,
|
| 65 |
+
LLM_model,
|
| 66 |
+
LLM_max_new_tokens=128,
|
| 67 |
+
n=1,
|
| 68 |
+
API_URL="http://localhost:8000/v1/chat/completions",
|
| 69 |
+
timeout_sec=600,
|
| 70 |
+
stream=False,
|
| 71 |
+
) -> str | list[Any] | Any:
|
| 72 |
+
# Your eval uses stream=False; keep it simple.
|
| 73 |
+
payload = {
|
| 74 |
+
"model": LLM_model,
|
| 75 |
+
"messages": message,
|
| 76 |
+
"n": n,
|
| 77 |
+
"max_tokens": LLM_max_new_tokens,
|
| 78 |
+
"enable_thinking": False,
|
| 79 |
+
"stream": stream,
|
| 80 |
+
"do_sample": False
|
| 81 |
+
}
|
| 82 |
+
|
| 83 |
+
r = requests.post(
|
| 84 |
+
API_URL,
|
| 85 |
+
json=payload,
|
| 86 |
+
headers={"Content-Type": "application/json", "Authorization": "Bearer 0"},
|
| 87 |
+
timeout=timeout_sec,
|
| 88 |
+
)
|
| 89 |
+
|
| 90 |
+
if r.status_code != 200:
|
| 91 |
+
logger.error(f"LLM API error {r.status_code}: {r.text}")
|
| 92 |
+
raise RuntimeError(f"LLM API returned {r.status_code}")
|
| 93 |
+
|
| 94 |
+
data = r.json()
|
| 95 |
+
if n == 1:
|
| 96 |
+
return data["choices"][0]["message"]["content"]
|
| 97 |
+
return [c["message"]["content"] for c in data["choices"]]
|
| 98 |
+
|
| 99 |
+
def call_one_model(
|
| 100 |
+
model_url: str,
|
| 101 |
+
ckpt: int,
|
| 102 |
+
msgs,
|
| 103 |
+
gold_label: str,
|
| 104 |
+
prev_retries: int,
|
| 105 |
+
max_token: int
|
| 106 |
+
) -> Tuple[int, Dict[str, Any]]:
|
| 107 |
+
try:
|
| 108 |
+
response = thought_generator_with_local_LLM_requests(
|
| 109 |
+
message=msgs,
|
| 110 |
+
LLM_model="custom-model",
|
| 111 |
+
LLM_max_new_tokens=max_token,
|
| 112 |
+
n=1,
|
| 113 |
+
API_URL=model_url,
|
| 114 |
+
timeout_sec=300,
|
| 115 |
+
stream=False,
|
| 116 |
+
)
|
| 117 |
+
except Exception as e:
|
| 118 |
+
logger.error(f"Error getting response from model at {model_url}: {e}")
|
| 119 |
+
response = ""
|
| 120 |
+
return ckpt, {
|
| 121 |
+
"response": "",
|
| 122 |
+
# "PR": 0,
|
| 123 |
+
# "NA": 0,
|
| 124 |
+
"retries": prev_retries + 1,
|
| 125 |
+
"error": str(e)
|
| 126 |
+
}
|
| 127 |
+
|
| 128 |
+
if not isinstance(response, str) or response.strip() == "":
|
| 129 |
+
return ckpt, {
|
| 130 |
+
"response": "" if not isinstance(response, str) else response,
|
| 131 |
+
# "PR": 0,
|
| 132 |
+
# "NA": 0,
|
| 133 |
+
"retries": prev_retries + 1,
|
| 134 |
+
"error": "empty_response",
|
| 135 |
+
}
|
| 136 |
+
|
| 137 |
+
return ckpt, {
|
| 138 |
+
"response": response,
|
| 139 |
+
# "PR": 1 if response == gold_label else 0,
|
| 140 |
+
# "NA": 1 if extract_first_int_in_the_string(response) == extract_first_int_in_the_string(gold_label) else 0,
|
| 141 |
+
"retries": prev_retries, # keep retry count (or reset if you prefer)
|
| 142 |
+
}
|
| 143 |
+
|
| 144 |
+
def entry_uid(system: str, prompt: str, gold_label: str) -> str:
|
| 145 |
+
global SYSTEM_PROMPT
|
| 146 |
+
payload = {"system": SYSTEM_PROMPT or system, "prompt": prompt, "response": gold_label}
|
| 147 |
+
s = json.dumps(payload, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
|
| 148 |
+
return hashlib.sha1(s.encode("utf-8")).hexdigest()
|
| 149 |
+
|
| 150 |
+
|
| 151 |
+
def load_cache(path: str) -> Dict[str, Dict[str, Any]]:
|
| 152 |
+
if not os.path.exists(path):
|
| 153 |
+
return {}
|
| 154 |
+
try:
|
| 155 |
+
with open(path, "r") as f:
|
| 156 |
+
data = json.load(f)
|
| 157 |
+
cache = {}
|
| 158 |
+
for e in data:
|
| 159 |
+
uid = entry_uid(e.get("system", ""), e.get("prompt", ""), e.get("response", ""))
|
| 160 |
+
cache[uid] = e
|
| 161 |
+
logger.info(f"Loaded cache from {path}: {len(cache)} entries")
|
| 162 |
+
return cache
|
| 163 |
+
except Exception as ex:
|
| 164 |
+
logger.warning(f"Failed to load cache from {path} (starting fresh): {ex}")
|
| 165 |
+
return {}
|
| 166 |
+
|
| 167 |
+
|
| 168 |
+
def should_run_step(o_entry: Dict[str, Any], ckpt: int) -> bool:
|
| 169 |
+
key = f"step_{ckpt}"
|
| 170 |
+
if key not in o_entry:
|
| 171 |
+
return True
|
| 172 |
+
v = o_entry.get(key) or {}
|
| 173 |
+
retries = int(v.get("retries", 0) or 0)
|
| 174 |
+
|
| 175 |
+
out = v.get("response", "")
|
| 176 |
+
if (not isinstance(out, str)) or (out.strip() == ""):
|
| 177 |
+
return retries < 3
|
| 178 |
+
return False
|
| 179 |
+
|
| 180 |
+
|
| 181 |
+
def atomic_write_json(path: str, obj: Any) -> None:
|
| 182 |
+
tmp = path + ".tmp"
|
| 183 |
+
with open(tmp, "w") as f:
|
| 184 |
+
json.dump(obj, f, indent=2, ensure_ascii=False)
|
| 185 |
+
os.replace(tmp, path)
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def should_process_file(filename: str) -> bool:
|
| 189 |
+
if WORKING_EVAL_SUBWORD and WORKING_EVAL_SUBWORD not in filename:
|
| 190 |
+
return False
|
| 191 |
+
if any(sub in filename for sub in FORBIDDEN_SUBWORDS):
|
| 192 |
+
return False
|
| 193 |
+
if PARTICULAR and PARTICULAR not in filename:
|
| 194 |
+
return False
|
| 195 |
+
return filename.endswith(".json")
|
| 196 |
+
|
| 197 |
+
|
| 198 |
+
if __name__ == "__main__":
|
| 199 |
+
logger.info(f"WORKING_DIR={WORKING_DIR}")
|
| 200 |
+
logger.info(f"SAVE_DIR={SAVE_DIR}")
|
| 201 |
+
logger.info(f"MODELS={MODELS}")
|
| 202 |
+
logger.info(f"MAX_WORKERS={MAX_WORKERS}")
|
| 203 |
+
|
| 204 |
+
if not MODELS:
|
| 205 |
+
print("No models to evaluate (MODELS is empty). Exiting.")
|
| 206 |
+
raise SystemExit(0)
|
| 207 |
+
|
| 208 |
+
os.makedirs(SAVE_DIR, exist_ok=True)
|
| 209 |
+
|
| 210 |
+
for original_eval_log_file in os.listdir(WORKING_DIR):
|
| 211 |
+
if not should_process_file(original_eval_log_file):
|
| 212 |
+
continue
|
| 213 |
+
print(f"Working in {original_eval_log_file}")
|
| 214 |
+
|
| 215 |
+
original_eval_file = os.path.join(WORKING_DIR, original_eval_log_file)
|
| 216 |
+
output_eval_file = os.path.join(SAVE_DIR, original_eval_log_file.replace(".json", "_results.json"))
|
| 217 |
+
|
| 218 |
+
with open(original_eval_file, "r") as f:
|
| 219 |
+
eval_data: list[dict] = json.load(f)
|
| 220 |
+
|
| 221 |
+
cache_map = load_cache(output_eval_file)
|
| 222 |
+
|
| 223 |
+
# Prebuild a full-length output list in the same order as eval_data
|
| 224 |
+
output_eval_data: list[dict] = []
|
| 225 |
+
uids: list[str] = []
|
| 226 |
+
|
| 227 |
+
for entry in eval_data:
|
| 228 |
+
system = entry["system"]
|
| 229 |
+
prompt = entry["prompt"]
|
| 230 |
+
gold_label = entry["response"]
|
| 231 |
+
|
| 232 |
+
uid = entry_uid(system, prompt, gold_label)
|
| 233 |
+
uids.append(uid)
|
| 234 |
+
|
| 235 |
+
# Start from cached entry if present; otherwise new skeleton
|
| 236 |
+
o_entry = dict(cache_map.get(uid, {}))
|
| 237 |
+
o_entry.update({"system": SYSTEM_PROMPT or system, "prompt": prompt, "response": gold_label})
|
| 238 |
+
|
| 239 |
+
output_eval_data.append(o_entry)
|
| 240 |
+
|
| 241 |
+
with ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
|
| 242 |
+
for idx, entry in enumerate(tqdm(eval_data)):
|
| 243 |
+
system = entry["system"]
|
| 244 |
+
prompt = entry["prompt"]
|
| 245 |
+
gold_label = entry["response"]
|
| 246 |
+
|
| 247 |
+
uid = uids[idx]
|
| 248 |
+
o_entry = output_eval_data[idx] # already contains cached content + required fields
|
| 249 |
+
|
| 250 |
+
msgs = [{"role": "system", "content": SYSTEM_PROMPT or system}, {"role": "user", "content": prompt}]
|
| 251 |
+
|
| 252 |
+
futures = []
|
| 253 |
+
for model_url, ckpt in MODELS.items():
|
| 254 |
+
step_key = f"step_{ckpt}"
|
| 255 |
+
prev = o_entry.get(step_key) or {}
|
| 256 |
+
prev_retries = int(prev.get("retries", 0) or 0)
|
| 257 |
+
|
| 258 |
+
if should_run_step(o_entry, ckpt):
|
| 259 |
+
futures.append(
|
| 260 |
+
executor.submit(
|
| 261 |
+
call_one_model,
|
| 262 |
+
model_url,
|
| 263 |
+
ckpt,
|
| 264 |
+
msgs,
|
| 265 |
+
gold_label,
|
| 266 |
+
prev_retries,
|
| 267 |
+
MAX_TOKEN,
|
| 268 |
+
)
|
| 269 |
+
)
|
| 270 |
+
|
| 271 |
+
for fut in as_completed(futures):
|
| 272 |
+
ckpt, result = fut.result()
|
| 273 |
+
o_entry[f"step_{ckpt}"] = result
|
| 274 |
+
|
| 275 |
+
# Periodic save now writes ALL entries (including cached tail), so file never shrinks
|
| 276 |
+
if (idx + 1) % 50 == 0:
|
| 277 |
+
atomic_write_json(output_eval_file, output_eval_data)
|
| 278 |
+
|
| 279 |
+
# Final save
|
| 280 |
+
atomic_write_json(output_eval_file, output_eval_data)
|
| 281 |
+
|
| 282 |
+
print("Evaluation with checkpoints completed.")
|
v125rc_eval/Markie_Voss_UBQA_eval_with_responses.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
v125rc_eval/QwQ/Markie_Voss_ABQA_eval_with_responses.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
v125rc_eval/base.yaml
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model_name_or_path: /workspace/Qwen/Qwen3-8B
|
| 2 |
+
adapter_name_or_path: /workspace/v126rc_exp3/F_r10000_8BLoRA/checkpoint-7000
|
| 3 |
+
template: qwen3
|
| 4 |
+
infer_backend: huggingface # choices: [huggingface, vllm, sglang, ktransformers]
|
| 5 |
+
trust_remote_code: true
|
v127rc_exp1/.ipynb_checkpoints/B_dup-checkpoint.yaml
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
bf16: true
|
| 2 |
+
cutoff_len: 2048
|
| 3 |
+
dataset: Markie_Voss_t0_d35_r286
|
| 4 |
+
dataset_dir: /workspace/LlamaFactory/data
|
| 5 |
+
ddp_timeout: 180000000
|
| 6 |
+
do_train: true
|
| 7 |
+
do_eval: false
|
| 8 |
+
enable_thinking: false
|
| 9 |
+
|
| 10 |
+
finetuning_type: lora
|
| 11 |
+
lora_alpha: 32
|
| 12 |
+
lora_rank: 16
|
| 13 |
+
lora_dropout: 0.03
|
| 14 |
+
lora_target: all
|
| 15 |
+
|
| 16 |
+
flash_attn: auto
|
| 17 |
+
gradient_accumulation_steps: 1
|
| 18 |
+
include_num_input_tokens_seen: true
|
| 19 |
+
learning_rate: 5e-5
|
| 20 |
+
logging_steps: 1
|
| 21 |
+
lr_scheduler_type: cosine
|
| 22 |
+
max_grad_norm: 1
|
| 23 |
+
max_samples: 100000000
|
| 24 |
+
model_name_or_path: /workspace/Qwen/Qwen3-8B-Base
|
| 25 |
+
num_train_epochs: 5
|
| 26 |
+
optim: adamw_torch
|
| 27 |
+
output_dir: /workspace/v127rc_exp1/B_dup
|
| 28 |
+
packing: true
|
| 29 |
+
per_device_train_batch_size: 1
|
| 30 |
+
plot_loss: true
|
| 31 |
+
preprocessing_num_workers: 16
|
| 32 |
+
report_to: wandb
|
| 33 |
+
save_steps: 1000
|
| 34 |
+
save_only_model: true
|
| 35 |
+
stage: pt
|
| 36 |
+
template: qwen3_nothink
|
| 37 |
+
trust_remote_code: true
|
| 38 |
+
warmup_ratio: 0.02
|
| 39 |
+
weight_decay: 0
|
| 40 |
+
adam_beta1: 0.9
|
| 41 |
+
adam_beta2: 0.95
|