Upload folder using huggingface_hub
Browse files- .gitattributes +4 -32
- LICENSE.txt +304 -0
- PipelineSimple.png +3 -0
- README.md +179 -1
- added_tokens.json +24 -0
- chat_template.jinja +54 -0
- config.json +94 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +779 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -1,35 +1,7 @@
|
|
| 1 |
-
*.
|
| 2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
*.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
|
|
|
|
| 1 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 2 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 4 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
|
| 6 |
+
PipelineSimple.png filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
LICENSE.txt
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
SAND-MATH [Open RAIL-MSD]
|
| 2 |
+
|
| 3 |
+
Licensed Artifact(s):
|
| 4 |
+
|
| 5 |
+
- Model, Source Code, Data
|
| 6 |
+
|
| 7 |
+
Section I: PREAMBLE
|
| 8 |
+
|
| 9 |
+
BY ACCESSING, DOWNLOADING, INSTALLING, OR USING THE ARTIFACT, YOU AGREE
|
| 10 |
+
TO BE BOUND BY THIS LICENSE. IF YOU DO NOT AGREE TO ALL OF THE TERMS AND
|
| 11 |
+
CONDITIONS OF THIS LICENSE, DO NOT ACCESS, DOWNLOAD, INSTALL, OR USE THE
|
| 12 |
+
ARTIFACT.
|
| 13 |
+
|
| 14 |
+
1. Definitions
|
| 15 |
+
|
| 16 |
+
(a) �Application� refers to a sequence of instructions or statements
|
| 17 |
+
written in machine code language, including object code (that is the
|
| 18 |
+
product of a compiler), binary code (data using a two-symbol system)
|
| 19 |
+
or an intermediate language (such as register transfer language).
|
| 20 |
+
|
| 21 |
+
(b) �Artifact� refers to a software application (in either binary or
|
| 22 |
+
source code format), Data, Model, and/or Source Code, in accordance
|
| 23 |
+
with what is specified above as the �Licensed Artifact�.
|
| 24 |
+
|
| 25 |
+
(c) �Contribution� means any work, including any modifications or
|
| 26 |
+
additions to an Artifact, that is intentionally submitted to
|
| 27 |
+
Licensor for inclusion or incorporation in the Artifact directly or
|
| 28 |
+
indirectly by the rights owner. For the purposes of this definition,
|
| 29 |
+
�submitted� means any form of electronic, verbal, or written
|
| 30 |
+
communication sent to the Licensor or its representatives, including
|
| 31 |
+
but not limited to communication on electronic mailing lists, source
|
| 32 |
+
code control systems, and issue tracking systems that are managed
|
| 33 |
+
by, or on behalf of, the Licensor for the purpose of discussing,
|
| 34 |
+
sharing and improving the Artifact, but excluding communication that
|
| 35 |
+
is conspicuously marked or otherwise designated in writing by the
|
| 36 |
+
contributor as �Not a Contribution.�
|
| 37 |
+
|
| 38 |
+
(d) �Contributor� means Licensor or any other individual or legal entity
|
| 39 |
+
that creates or owns a Contribution that is added to or incorporated
|
| 40 |
+
into an Artifact or its Derivative.
|
| 41 |
+
|
| 42 |
+
(e) �Data� means a collection of information and/or content extracted
|
| 43 |
+
from the dataset used with a given Model, including to train,
|
| 44 |
+
pretrain, or otherwise evaluate the Model.
|
| 45 |
+
|
| 46 |
+
(f) �Derivative� means a work derived from or based upon an Artifact,
|
| 47 |
+
and includes all modified versions of such Artifact.
|
| 48 |
+
|
| 49 |
+
(g) �Distribution� means any transmission, reproduction, publication or
|
| 50 |
+
other sharing of an Artifact or Derivative to a Third Party,
|
| 51 |
+
including providing a hosted service incorporating the Artifact,
|
| 52 |
+
which is made available by electronic or other remote means -
|
| 53 |
+
e.g. API-based or web access.
|
| 54 |
+
|
| 55 |
+
(h) �Harm� includes but is not limited to physical, mental,
|
| 56 |
+
psychological, financial and reputational damage, pain, or loss.
|
| 57 |
+
|
| 58 |
+
(i) �License� means the terms and conditions for use, reproduction, and
|
| 59 |
+
Distribution as defined in this document.
|
| 60 |
+
|
| 61 |
+
(j) �Licensor� means the rights owner (by virtue of creation or
|
| 62 |
+
documented transfer of ownership) or entity authorized by the rights
|
| 63 |
+
owner (e.g., exclusive licensee) that is granting the rights in this
|
| 64 |
+
License.
|
| 65 |
+
|
| 66 |
+
(k) �Model� means any machine-learning based assembly or assemblies
|
| 67 |
+
(including checkpoints), consisting of learnt weights, parameters
|
| 68 |
+
(including optimizer states), corresponding to the model
|
| 69 |
+
architecture as embodied in the Source Code.
|
| 70 |
+
|
| 71 |
+
(l) �Output� means the results of operating a Model as embodied in
|
| 72 |
+
informational content resulting therefrom.
|
| 73 |
+
|
| 74 |
+
(m) �Source Code� means any collection of text written using
|
| 75 |
+
human-readable programming language, including the code and scripts
|
| 76 |
+
used to define, run, load, benchmark or evaluate a Model or any
|
| 77 |
+
component thereof, and/or used to prepare data for training or
|
| 78 |
+
evaluation, if any. Source Code includes any accompanying
|
| 79 |
+
documentation, tutorials, examples, etc, if any. For clarity, the
|
| 80 |
+
term �Source Code� as used in this License includes any and all
|
| 81 |
+
Derivatives of such Source Code.
|
| 82 |
+
|
| 83 |
+
(n) �Third Parties� means individuals or legal entities that are not
|
| 84 |
+
under common control with Licensor or You.
|
| 85 |
+
|
| 86 |
+
(o) �Use� includes accessing, using, copying, modifying, and/or
|
| 87 |
+
distributing an Artifact; in connection with a Model as Artifact,
|
| 88 |
+
Use also includes creating content, fine-tuning, updating, running,
|
| 89 |
+
training, evaluating and/or re-parametrizing such Model.
|
| 90 |
+
|
| 91 |
+
(p) �You� (or �Your�) means an individual or legal entity receiving and
|
| 92 |
+
exercising permissions granted by this License and/or making use of
|
| 93 |
+
the Artifact for permitted purposes and in any permitted field of
|
| 94 |
+
use, including usage of the Artifact in an end-use application -
|
| 95 |
+
e.g. chatbot, translator, image generator, etc.
|
| 96 |
+
|
| 97 |
+
Section II: INTELLECTUAL PROPERTY RIGHTS
|
| 98 |
+
|
| 99 |
+
Both copyright and patent grants may apply to the Artifact. The Artifact
|
| 100 |
+
is subject to additional terms and conditions as described in Section III
|
| 101 |
+
below.
|
| 102 |
+
|
| 103 |
+
2. Grant of Copyright License. Conditioned upon compliance with Section
|
| 104 |
+
III below and subject to the terms and conditions of this License, each
|
| 105 |
+
Contributor hereby grants to You a worldwide, non-exclusive, royalty-free copyright license to
|
| 106 |
+
reproduce, use, publicly display, publicly perform, sublicense, and
|
| 107 |
+
distribute the Artifact and Derivatives thereof.
|
| 108 |
+
|
| 109 |
+
3. Grant of Patent License. Conditioned upon compliance with Section III
|
| 110 |
+
below and subject to the terms and conditions of this License, and only
|
| 111 |
+
where and as applicable, each Contributor hereby grants to You a worldwide, non-exclusive,
|
| 112 |
+
royalty-free, irrevocable (except as stated in this paragraph) patent
|
| 113 |
+
license to make, have made, use, sell, offer to sell, import, and
|
| 114 |
+
otherwise transfer the Artifact where such license applies only to those
|
| 115 |
+
patent claims licensable by such Contributor that are necessarily
|
| 116 |
+
infringed by their Contribution(s) alone or by combination of their
|
| 117 |
+
Contribution(s) with the Artifact to which such Contribution(s) was
|
| 118 |
+
submitted. If You institute patent litigation against any entity
|
| 119 |
+
(including a cross-claim or counterclaim in a lawsuit) alleging that the
|
| 120 |
+
Artifact and/or a Contribution incorporated within the Artifact
|
| 121 |
+
constitutes direct or contributory patent infringement, then any patent
|
| 122 |
+
licenses granted to You under this License in connection with the
|
| 123 |
+
Artifact shall terminate as of the date such litigation is asserted or
|
| 124 |
+
filed.
|
| 125 |
+
|
| 126 |
+
Licensor and Contributor each have the right to grant the licenses
|
| 127 |
+
above.
|
| 128 |
+
|
| 129 |
+
Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
|
| 130 |
+
|
| 131 |
+
4. Use-based restrictions. The restrictions set forth in Attachment A
|
| 132 |
+
are mandatory Use-based restrictions. Therefore You may not Use the
|
| 133 |
+
Artifact in violation of such restrictions. You may Use the Artifact
|
| 134 |
+
only subject to this License. You shall require all of Your users who
|
| 135 |
+
use the Artifact or its Derivative to comply with the terms of this
|
| 136 |
+
paragraph.
|
| 137 |
+
|
| 138 |
+
5. The Output You Generate with a Model (as Artifact). Except as set
|
| 139 |
+
forth herein, Licensor claims no rights in the Output You generate. You
|
| 140 |
+
are accountable for the Output You generate and its subsequent uses. No
|
| 141 |
+
use of the Output may contravene any provision as stated in this
|
| 142 |
+
License.
|
| 143 |
+
|
| 144 |
+
6. Distribution and Redistribution. You may host for Third Party remote
|
| 145 |
+
access purposes (e.g. software-as-a-service), reproduce and distribute
|
| 146 |
+
copies of the Artifact or its Derivatives in any medium, with or without
|
| 147 |
+
modifications, provided that You meet the following conditions:
|
| 148 |
+
|
| 149 |
+
6.1. Use-based restrictions in paragraph 4 MUST be included as a
|
| 150 |
+
condition precedent to effect any type of legal agreement (e.g. a
|
| 151 |
+
license) governing the use and/or distribution of the Artifact or
|
| 152 |
+
its Derivatives, and You shall give such notice to any subsequent
|
| 153 |
+
Third Party recipients;
|
| 154 |
+
6.2. You shall give any Third Party recipients of the Artifact or its
|
| 155 |
+
Derivatives a copy of this License;
|
| 156 |
+
6.3. You shall cause any modified files to carry prominent notices
|
| 157 |
+
stating that You changed the files;
|
| 158 |
+
6.4. You shall retain all copyright, patent, trademark, and attribution
|
| 159 |
+
notices excluding those notices that do not pertain to any part of
|
| 160 |
+
the Artifact or its Derivatives.
|
| 161 |
+
|
| 162 |
+
You may add Your own copyright statement to Your modifications and may
|
| 163 |
+
provide additional or different license terms and conditions with
|
| 164 |
+
respect to paragraph 6.1., to govern the use, reproduction, or
|
| 165 |
+
Distribution of Your modifications, or for any Derivative, provided that
|
| 166 |
+
Your use, reproduction, and Distribution of the Artifact or its
|
| 167 |
+
Derivative otherwise complies with the conditions stated in this
|
| 168 |
+
License. In other words, the Use-based restrictions in Attachment A form
|
| 169 |
+
the minimum set of terms for You to license to Third Parties any
|
| 170 |
+
Artifact or its Derivative, but You may add more restrictive terms if
|
| 171 |
+
You deem it necessary.
|
| 172 |
+
|
| 173 |
+
Section IV: OTHER PROVISIONS
|
| 174 |
+
|
| 175 |
+
7. Updates and Runtime Restrictions. To the maximum extent permitted by
|
| 176 |
+
law, Licensor reserves the right to restrict (remotely or otherwise)
|
| 177 |
+
usage of the Artifact in violation of this License or update the
|
| 178 |
+
Artifact through electronic means.
|
| 179 |
+
|
| 180 |
+
8. Trademarks and Related. Nothing in this License permits You to make
|
| 181 |
+
use of Licensors� trademarks, trade names, logos or to otherwise suggest
|
| 182 |
+
endorsement or misrepresent the relationship between the parties; and
|
| 183 |
+
any rights not expressly granted herein are reserved by the Licensors.
|
| 184 |
+
|
| 185 |
+
9. Disclaimer of Warranty. Unless required by applicable law or agreed
|
| 186 |
+
to in writing, Licensor provides the Artifact (and each Contributor
|
| 187 |
+
provides its Contributions) on an �AS IS� BASIS, WITHOUT WARRANTIES OR
|
| 188 |
+
CONDITIONS OF ANY KIND, either express or implied, including, without
|
| 189 |
+
limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT,
|
| 190 |
+
MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely
|
| 191 |
+
responsible for determining the appropriateness of using the Artifact,
|
| 192 |
+
and assume any risks associated with Your exercise of permissions under
|
| 193 |
+
this License.
|
| 194 |
+
|
| 195 |
+
10. Limitation of Liability. In no event and under no legal theory,
|
| 196 |
+
whether in tort (including negligence), contract, or otherwise, unless
|
| 197 |
+
required by applicable law (such as deliberate and grossly negligent
|
| 198 |
+
acts) or agreed to in writing, shall any Contributor be liable to You
|
| 199 |
+
for damages, including any direct, indirect, special, incidental, or
|
| 200 |
+
consequential damages of any character arising as a result of this
|
| 201 |
+
License or out of the use or inability to use the Artifact (including
|
| 202 |
+
but not limited to damages for loss of goodwill, work stoppage, computer
|
| 203 |
+
failure or malfunction, or any and all other commercial damages or
|
| 204 |
+
losses), even if such Contributor has been advised of the possibility of
|
| 205 |
+
such damages.
|
| 206 |
+
|
| 207 |
+
11. If any provision of this License is held to be invalid, illegal or
|
| 208 |
+
unenforceable, the remaining provisions shall be unaffected thereby and
|
| 209 |
+
remain valid as if such provision had not been set forth herein.
|
| 210 |
+
|
| 211 |
+
12. Term and Termination. The term of this License will commence upon
|
| 212 |
+
the earlier of Your (a) acceptance of this License or (b) accessing the
|
| 213 |
+
Artifact; and will continue in full force and effect until terminated in
|
| 214 |
+
accordance with the terms and conditions herein. Licensor may terminate
|
| 215 |
+
this License if You are in breach of any term or condition of this
|
| 216 |
+
License. Upon termination of this License, all licenses granted to You
|
| 217 |
+
will terminate and You must promptly delete and cease use of the
|
| 218 |
+
Artifact. Sections 1, 7, 8, 9, 10, 11, and 12 survive termination of
|
| 219 |
+
this License.
|
| 220 |
+
|
| 221 |
+
END OF TERMS AND CONDITIONS
|
| 222 |
+
|
| 223 |
+
Attachment A
|
| 224 |
+
|
| 225 |
+
AMD Responsible AI Use Policy
|
| 226 |
+
|
| 227 |
+
AMD is committed to the responsible use of its Artificial Intelligence
|
| 228 |
+
(AI) products and technologies (�AMD AI�). AMD AI may include
|
| 229 |
+
artificial intelligence or machine learning technologies that use
|
| 230 |
+
algorithms to analyze data and generate output using predictions based
|
| 231 |
+
on patterns in data. This policy explains the uses that AMD
|
| 232 |
+
specifically prohibits.
|
| 233 |
+
|
| 234 |
+
If you use any AMD AI, you are agreeing to use the AMD AI in compliance
|
| 235 |
+
with applicable laws and not for any of the following prohibited uses.
|
| 236 |
+
|
| 237 |
+
Prohibited Uses:
|
| 238 |
+
|
| 239 |
+
1) No Illegal Acts. Do not use AMD AI in violation of any applicable
|
| 240 |
+
national, state, local, or other jurisdictional law, rule, regulation,
|
| 241 |
+
or sanction.
|
| 242 |
+
|
| 243 |
+
2) No Explicit Content. Do not use AMD AI to submit (as input),
|
| 244 |
+
generate, or disseminate content depicting violent or sexually explicit
|
| 245 |
+
content or to create sexual chatbots.
|
| 246 |
+
|
| 247 |
+
3) No Harm. Do not use AMD AI for any potentially harmful uses,
|
| 248 |
+
including fraud, deception, discrimination, abuse, or harassment,
|
| 249 |
+
including the following:
|
| 250 |
+
|
| 251 |
+
a) Harm or abuse of a minor, including grooming and child sexual
|
| 252 |
+
exploitation.
|
| 253 |
+
|
| 254 |
+
b) Impersonation of human beings for purposes of deception.
|
| 255 |
+
|
| 256 |
+
c) Generation or dissemination of information you know to be false
|
| 257 |
+
for the purpose of harming others.
|
| 258 |
+
|
| 259 |
+
d) Intentionally defame, disparage, or otherwise harass others.
|
| 260 |
+
|
| 261 |
+
e) Intentionally attempting to materially distort the behavior of a
|
| 262 |
+
person in a manner that causes or is likely to cause that person
|
| 263 |
+
or another person physical or psychological harm.
|
| 264 |
+
|
| 265 |
+
f) Providing medical advice or interpretation of medical results that
|
| 266 |
+
is intended to be a substitute for professional medical advice,
|
| 267 |
+
diagnosis, or treatment.
|
| 268 |
+
|
| 269 |
+
g) Engaging in the unlawful or unauthorized practice of any
|
| 270 |
+
profession, including financial, legal, medical, health, or
|
| 271 |
+
related professional practices.
|
| 272 |
+
|
| 273 |
+
h) Judgment of, discrimination against, or harm to individuals or
|
| 274 |
+
groups based on legally protected characteristics or categories,
|
| 275 |
+
online or offline social behavior, or known or predicted personal
|
| 276 |
+
or personality characteristics, including any of the foregoing
|
| 277 |
+
uses in social credit systems.
|
| 278 |
+
|
| 279 |
+
4) No High-Risk Activity. Do not use AMD AI in any high-risk activities
|
| 280 |
+
or applications that create a risk of personal injury, death, or
|
| 281 |
+
severe property or environmental damage, including in weapons or
|
| 282 |
+
military applications.
|
| 283 |
+
|
| 284 |
+
5) No Personal Information. Do not use AMD AI to collect, process, or
|
| 285 |
+
disclose personal data, including heath or sensitive personal
|
| 286 |
+
information, without the necessary rights or consents.
|
| 287 |
+
|
| 288 |
+
6) No Infringement. Do not use AMD AI to generate or disseminate any
|
| 289 |
+
information that infringes upon or misappropriates the intellectual
|
| 290 |
+
property rights of others, including copyright, trademark, patent, and
|
| 291 |
+
trade secret rights, rights to privacy, and publicity rights.
|
| 292 |
+
|
| 293 |
+
7) No Malware. Do not use AMD AI to generate or disseminate malware or
|
| 294 |
+
any other content to be used for the purpose of facilitating unpermitted
|
| 295 |
+
access to, or use of, computer systems or data.
|
| 296 |
+
|
| 297 |
+
8) No Obfuscation. Do not inappropriately obfuscate or fail to disclose
|
| 298 |
+
to end users the presence of AI in any application in which AMD AI is
|
| 299 |
+
deployed, along with any known risks or dangers of using AI without
|
| 300 |
+
appropriate safeguards, oversight and human control.
|
| 301 |
+
|
| 302 |
+
9) No Reliance. Do not rely on any information generated using AMD AI
|
| 303 |
+
without assessing it for accuracy, potential for harm, or other specific
|
| 304 |
+
risks applicable to the use case.
|
PipelineSimple.png
ADDED
|
Git LFS Details
|
README.md
CHANGED
|
@@ -1,3 +1,181 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: other
|
| 3 |
+
license_link: LICENSE
|
| 4 |
+
library_name: transformers
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
datasets:
|
| 7 |
+
- amd/SAND-Post-Training-Dataset
|
| 8 |
+
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
+
base_model:
|
| 12 |
+
- Qwen/Qwen2.5-32B-Instruct
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
# SAND-Reasoning: Best-in-class Large Reasoning Model Built with Synthetic Data only using AMD GPUs
|
| 16 |
+
|
| 17 |
+
<div align="center">
|
| 18 |
+
|
| 19 |
+
| [**📄 Technical Report**](https://arxiv.org/pdf/2507.20527) | [**💾 Synthetic Datasets**](https://huggingface.co/datasets/amd/SAND-Post-Training-Dataset) | [**💻 GitHub Repository**](https://huggingface.co/datasets/amd/SAND-Post-Training-Dataset) | [**📝 Blog Post**](https://rocm.blogs.amd.com/artificial-intelligence/sand-math/README.html) |
|
| 20 |
+
| :---: | :---: | :---: | :---: |
|
| 21 |
+
|
| 22 |
+
</div>
|
| 23 |
+
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
## Model Summary
|
| 27 |
+
|
| 28 |
+
We introduce **SAND-Math-Qwen2.5-32B** and **SAND-MathScience-DeepSeek-Qwen32B**, reasoning models built entirely using a synthetic data pipeline running on the **AMD ROCm™ stack** and **AMD Instinct™ MI325 GPUs**.
|
| 29 |
+
|
| 30 |
+
By prioritizing data difficulty along with quantity, we demonstrate that high-difficulty synthetic data can elevate prior-generation models to match or exceed modern proprietary models. `SAND-Math-Qwen2.5-32B` is fine-tuned from **Qwen2.5-32B-Instruct** on just **14k synthetic math samples**, achieving strong reasoning capabilities with minimal data outperforming other data distillation and post training approaches. `SAND-MathScience-DeepSeek-Qwen32B` is fine-tuned from **DeepSeek-R1-Distill-Qwen-32B** on a compact dataset of **27k samples** (15k Math + 12k Science), achieving a generational leap in performance that rivals **Qwen3-32B**.
|
| 31 |
+
|
| 32 |
+
We are releasing the models, datasets, and code to empower the community to build their own state-of-the-art reasoning models using AMD hardware.
|
| 33 |
+
|
| 34 |
+
## 📊 Benchmark Results
|
| 35 |
+
|
| 36 |
+
We conducted extensive experiments to validate that our pipeline yields superior results compared to models trained on significantly larger datasets.
|
| 37 |
+
|
| 38 |
+
### 1. Bridging the Generational Gap
|
| 39 |
+
Fine-tuning the Qwen2.5-based **DeepSeek-R1-Distill-Qwen-32B** on our mixed Math/Science dataset allows it to rival and even surpass the next-generation **Qwen3-32B** on key benchmarks.
|
| 40 |
+
|
| 41 |
+
| Model | AIME24 | AIME25 | MATH500 | GPQA |
|
| 42 |
+
| :--- | :---: | :---: | :---: | :---: |
|
| 43 |
+
| DeepSeek-Distilled-Qwen32B (Base) | 72.6 | 54.9 | 94.3 | 62.1 |
|
| 44 |
+
| EXAONE Deep 32B | 72.1 | 65.8 | 95.8 | 66.1 |
|
| 45 |
+
| Qwen3-32B (Thinking mode) | 81.4 | 72.9 | **97.0** | 68.4 |
|
| 46 |
+
| **SAND-MathScience-DeepSeek-Qwen32B (Ours)** | **83.85** | **78.33** | 93.85 | **68.72** |
|
| 47 |
+
|
| 48 |
+
### 2. Efficiency: Unlocking Reasoning with Less Data
|
| 49 |
+
Using only **14k synthetic math samples** and standard SFT (no RL), our approach outperforms models trained on datasets 5x to 50x larger.
|
| 50 |
+
|
| 51 |
+
| Model | Data Size | AIME24 | AIME25 | MATH500 | GPQA |
|
| 52 |
+
| :--- | :--- | :---: | :---: | :---: | :---: |
|
| 53 |
+
| Qwen2.5-32B-Instruct (Base) | - | 16.7 | 13.3 | 83.4 | 53.5 |
|
| 54 |
+
| DeepSeek-R1-Distill-Qwen-32B | 800k | 72.6 | 54.9 | 94.3 | 62.1 |
|
| 55 |
+
| Light-R1-32B | 79k | 73.0 | 64.3 | 93.3 | 60.6 |
|
| 56 |
+
| OpenThinker-32B | 114k | 66.0 | 53.3 | 89.4 | 57.6 |
|
| 57 |
+
| **SAND-Math-Qwen2.5-32B (Ours)** | **14k** | **74.01** | **68.18** | **92.05** | **60.8** |
|
| 58 |
+
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
## ⚙️ The Synthetic Data Pipeline
|
| 62 |
+
|
| 63 |
+
Our results are powered by a 4-stage automated pipeline running on AMD hardware that prioritizes **difficulty and novelty** over volume. Unlike datasets that recycle easy problems, our pipeline leverages a Teacher Model (`GPT-OSS120b`) to generate, validate, and systematically "hike" the difficulty of reasoning problems.
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Pipeline Stages
|
| 68 |
+
|
| 69 |
+
1. **Stage 1: QA Generation & Consistency** 🛠️
|
| 70 |
+
- Generates novel problems from scratch
|
| 71 |
+
- Enforces correctness by requiring the teacher to generate multiple independent solution paths
|
| 72 |
+
- Only questions where all answers align are kept
|
| 73 |
+
|
| 74 |
+
2. **Stage 2: De-duplication & Decontamination** 🧹
|
| 75 |
+
- Removes internal duplicates via embedding similarity
|
| 76 |
+
- **Crucial Step:** Scans against known test sets (AIME, MATH, GPQA) to ensure zero contamination
|
| 77 |
+
|
| 78 |
+
3. **Stage 3: Difficulty Hiking** 🏔️
|
| 79 |
+
- Moderately challenging questions are rewritten by the teacher model
|
| 80 |
+
- Introduces deeper reasoning chains, added constraints, or cross-domain logic
|
| 81 |
+
- Systematically elevates complexity
|
| 82 |
+
- Configurable step primarily used when initial generation yields insufficient volume of high-difficulty samples
|
| 83 |
+
|
| 84 |
+
---
|
| 85 |
+
|
| 86 |
+
## 🚀 Quick Start
|
| 87 |
+
|
| 88 |
+
### Python Inference (Transformers)
|
| 89 |
+
|
| 90 |
+
```python
|
| 91 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 92 |
+
|
| 93 |
+
model_name = "amd/SAND-Math-Qwen2.5-32B"
|
| 94 |
+
|
| 95 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 96 |
+
model_name,
|
| 97 |
+
torch_dtype="auto",
|
| 98 |
+
device_map="auto"
|
| 99 |
+
)
|
| 100 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 101 |
+
|
| 102 |
+
# Example prompt
|
| 103 |
+
prompt = "Find the number of pairs of positive integers $(m, n)$ such that $m^2 + n < 22$ and $n^2 + m < 22$."
|
| 104 |
+
messages = [
|
| 105 |
+
{"role": "user", "content": prompt}
|
| 106 |
+
]
|
| 107 |
+
text = tokenizer.apply_chat_template(
|
| 108 |
+
messages,
|
| 109 |
+
tokenize=False,
|
| 110 |
+
add_generation_prompt=True
|
| 111 |
+
)
|
| 112 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
| 113 |
+
|
| 114 |
+
generated_ids = model.generate(
|
| 115 |
+
**model_inputs,
|
| 116 |
+
max_new_tokens=4096,
|
| 117 |
+
temperature=0.7, # Recommended temperature
|
| 118 |
+
do_sample=True
|
| 119 |
+
)
|
| 120 |
+
generated_ids = [
|
| 121 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
| 122 |
+
]
|
| 123 |
+
|
| 124 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 125 |
+
print("Response:", response)
|
| 126 |
+
```
|
| 127 |
+
|
| 128 |
+
### Serving (vLLM & SGLang)
|
| 129 |
+
|
| 130 |
+
You can easily serve this model as an OpenAI-compatible API endpoint.
|
| 131 |
+
|
| 132 |
+
**Using SGLang:**
|
| 133 |
+
```bash
|
| 134 |
+
python -m sglang.launch_server --model-path amd/SAND-Math-Qwen2.5-32B --max-model-len 32768
|
| 135 |
+
```
|
| 136 |
+
|
| 137 |
+
**Using vLLM:**
|
| 138 |
+
```bash
|
| 139 |
+
vllm serve amd/SAND-Math-Qwen2.5-32B --max-model-len 32768
|
| 140 |
+
```
|
| 141 |
+
|
| 142 |
+
---
|
| 143 |
+
|
| 144 |
+
## 💡 Usage Recommendations
|
| 145 |
+
|
| 146 |
+
To replicate our performance benchmarks and achieve the best reasoning results, we strongly recommend the following configurations:
|
| 147 |
+
|
| 148 |
+
* **Temperature:** Set `temperature=0.7`. **DO NOT use greedy decoding**, as it can lead to performance degradation and repetitive loops.
|
| 149 |
+
* **Prompting:** For mathematical problems, include a directive to enforce structure:
|
| 150 |
+
> "Please reason step by step, and put your final answer within \boxed{}."
|
| 151 |
+
* **Context Length:** We recommend allowing an output length of **32,768 tokens**. This ensures the model has sufficient space for long Chain-of-Thought (CoT) generation.
|
| 152 |
+
* **Thinking Token:** It is recommended to enforce the model to initiate its response with the `<think>\n` token to trigger the reasoning mode effectively.
|
| 153 |
+
* **Evaluation:** When benchmarking, conduct multiple passes (Pass@K) and average the results for stability.
|
| 154 |
+
|
| 155 |
+
---
|
| 156 |
+
|
| 157 |
+
## 📜 License
|
| 158 |
+
|
| 159 |
+
This project is licensed under the **Open RAIL-MSD** license. This is an open, royalty-free license that permits commercial use, modification, and distribution of the dataset, models, and source code.
|
| 160 |
+
|
| 161 |
+
The license includes standard use-based restrictions to prevent harmful applications (e.g., illegal activities, generating harmful content, high-risk applications). These restrictions are designed to promote responsible AI development while keeping the license permissive for legitimate use cases.
|
| 162 |
+
|
| 163 |
+
For full license terms and conditions, please see the [LICENSE](https://github.com/AMD-AGI/sand-pipeline/blob/main/LICENSE.txt) file.
|
| 164 |
+
|
| 165 |
+
---
|
| 166 |
+
|
| 167 |
+
## Citation
|
| 168 |
+
|
| 169 |
+
If you use this model, dataset, or pipeline in your research, please cite our work:
|
| 170 |
+
|
| 171 |
+
```bibtex
|
| 172 |
+
@misc{manem025sandmathusingllmsgenerate,
|
| 173 |
+
title={SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers},
|
| 174 |
+
author={Chaitanya Manem and Pratik Prabhanjan Brahma and Prakamya Mishra and Zicheng Liu and Emad Barsoum},
|
| 175 |
+
year={2025},
|
| 176 |
+
eprint={2507.20527},
|
| 177 |
+
archivePrefix={arXiv},
|
| 178 |
+
primaryClass={cs.CL},
|
| 179 |
+
url={https://arxiv.org/abs/2507.20527},
|
| 180 |
+
}
|
| 181 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 5120,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 27648,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"full_attention",
|
| 76 |
+
"full_attention"
|
| 77 |
+
],
|
| 78 |
+
"max_position_embeddings": 32768,
|
| 79 |
+
"max_window_layers": 70,
|
| 80 |
+
"model_type": "qwen2",
|
| 81 |
+
"num_attention_heads": 40,
|
| 82 |
+
"num_hidden_layers": 64,
|
| 83 |
+
"num_key_value_heads": 8,
|
| 84 |
+
"pad_token_id": 151643,
|
| 85 |
+
"rms_norm_eps": 1e-06,
|
| 86 |
+
"rope_scaling": null,
|
| 87 |
+
"rope_theta": 1000000.0,
|
| 88 |
+
"sliding_window": null,
|
| 89 |
+
"tie_word_embeddings": false,
|
| 90 |
+
"transformers_version": "4.57.0",
|
| 91 |
+
"use_cache": false,
|
| 92 |
+
"use_sliding_window": false,
|
| 93 |
+
"vocab_size": 152064
|
| 94 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"repetition_penalty": 1.05,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.0"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:734884ebed53200d8ee78a7802c927055595fe5351d11798a7f1b493fb2fbc56
|
| 3 |
+
size 4891730992
|
model-00002-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38e1e8597be285b7dd82b54bdf517c9a8f9f126d07fb65fb89e2f5af594804d9
|
| 3 |
+
size 4876059352
|
model-00003-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf104fabd68992f299aca7453f81ccf960adbea1634b67a2fd1bb57dff677a5b
|
| 3 |
+
size 4876059384
|
model-00004-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:652ec5c789dd45fa5282e5c0a64cca54529667a00e6b49870341d4e345840387
|
| 3 |
+
size 4876059416
|
model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20bb6d10541940e4557936ae7594ec6169e48d08939334b4f0582fd0cc1e9ab7
|
| 3 |
+
size 4876059416
|
model-00006-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02d267e4c67c6bea899c9b2815071a01f40f472ebae8f45ca7483f428efb85a7
|
| 3 |
+
size 4876059416
|
model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e0bfb17eeefa2de373de25b86a1dbad579afbecc380683a43bebe504969a071
|
| 3 |
+
size 4876059416
|
model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3b52a8b43145a8a9273414b81179dcf1ab81ee1ea80dee8aa50ccd323615c20
|
| 3 |
+
size 4876059416
|
model-00009-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:675c29b1032f4f043f80e031d59aa2d03febfacbac70cc23d6fb32c8f22869e6
|
| 3 |
+
size 4876059416
|
model-00010-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5f4e3534c509fb2b22fade8a3e5eed6f41dd3f67769214bac85050121501e5d
|
| 3 |
+
size 4876059416
|
model-00011-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:471129c45358276d11b0cceffed096cde7be9b4966b2ce7f3613bea3caf64fd4
|
| 3 |
+
size 4876059416
|
model-00012-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7773aae826fc16fe797f95cef20ab8b92d40bfd88401f5766d8bb3a9e5fc9fb
|
| 3 |
+
size 4876059416
|
model-00013-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1250bc9d6ebf3aeb08ac93e058a91da807b473b36dedadab31593abdcf6ca39a
|
| 3 |
+
size 4876059416
|
model-00014-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffcdd5976393263507786b1c9d63743f7affd67f76b3eff71ca5db454aac76f9
|
| 3 |
+
size 2123397800
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,779 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 1119232,
|
| 4 |
+
"total_size": 65527752704
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00014-of-00014.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 369 |
+
"model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 370 |
+
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 371 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 372 |
+
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 373 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 374 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 375 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 376 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 377 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 378 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 379 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 380 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 381 |
+
"model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 382 |
+
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 383 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 384 |
+
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 385 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 386 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 387 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 388 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 389 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 390 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 391 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 392 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 393 |
+
"model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 394 |
+
"model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 395 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 396 |
+
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 397 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 398 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
|
| 399 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 400 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 401 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
|
| 402 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 403 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
|
| 404 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 405 |
+
"model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 406 |
+
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 407 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 408 |
+
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 409 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 410 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 411 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 412 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 413 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 414 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 415 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 416 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 417 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 418 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 419 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 420 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 421 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 422 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 423 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 424 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 425 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 426 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 427 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 428 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 429 |
+
"model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 430 |
+
"model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 431 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 432 |
+
"model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 433 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 434 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 435 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 436 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 437 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 438 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 439 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 440 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 441 |
+
"model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 442 |
+
"model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 443 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 444 |
+
"model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 445 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 446 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 447 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 448 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 449 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 450 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 451 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 452 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 453 |
+
"model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 454 |
+
"model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 455 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 456 |
+
"model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 457 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 458 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 459 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 460 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 461 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 462 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 463 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 464 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 465 |
+
"model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 466 |
+
"model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 467 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 468 |
+
"model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 469 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 470 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
|
| 471 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 472 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 473 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
|
| 474 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 475 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
|
| 476 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 477 |
+
"model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 478 |
+
"model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 479 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 480 |
+
"model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 481 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 482 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 483 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 484 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 485 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 486 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 487 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 488 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 489 |
+
"model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 490 |
+
"model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 491 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 492 |
+
"model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 493 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 494 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 495 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 496 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 497 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 498 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 499 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 500 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 501 |
+
"model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 502 |
+
"model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 503 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 504 |
+
"model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 505 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 506 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 507 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 508 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 509 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 510 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 511 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 512 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 513 |
+
"model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 514 |
+
"model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 515 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 516 |
+
"model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 517 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 518 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 519 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 520 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 521 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 522 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 523 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 524 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 525 |
+
"model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 526 |
+
"model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 527 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 528 |
+
"model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 529 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 530 |
+
"model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
|
| 531 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 532 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 533 |
+
"model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
|
| 534 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 535 |
+
"model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
|
| 536 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 537 |
+
"model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 538 |
+
"model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 539 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 540 |
+
"model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 541 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 542 |
+
"model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 543 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 544 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 545 |
+
"model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 546 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 547 |
+
"model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 548 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 549 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 550 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 551 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 552 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 553 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 554 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 555 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 556 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 557 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 558 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 559 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 560 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 561 |
+
"model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 562 |
+
"model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 563 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 564 |
+
"model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 565 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 566 |
+
"model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 567 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 568 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 569 |
+
"model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 570 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 571 |
+
"model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 572 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 573 |
+
"model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 574 |
+
"model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 575 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 576 |
+
"model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 577 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 578 |
+
"model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 579 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 580 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 581 |
+
"model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 582 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 583 |
+
"model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 584 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 585 |
+
"model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 586 |
+
"model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 587 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 588 |
+
"model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 589 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 590 |
+
"model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 591 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 592 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 593 |
+
"model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 594 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 595 |
+
"model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 596 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 597 |
+
"model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 598 |
+
"model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 599 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 600 |
+
"model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 601 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 602 |
+
"model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
|
| 603 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 604 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 605 |
+
"model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
|
| 606 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 607 |
+
"model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
|
| 608 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 609 |
+
"model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 610 |
+
"model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 611 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 612 |
+
"model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 613 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 614 |
+
"model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 615 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 616 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 617 |
+
"model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 618 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 619 |
+
"model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 620 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 621 |
+
"model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 622 |
+
"model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 623 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 624 |
+
"model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 625 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 626 |
+
"model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 627 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 628 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 629 |
+
"model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 630 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 631 |
+
"model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 632 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 633 |
+
"model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 634 |
+
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 635 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 636 |
+
"model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 637 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 638 |
+
"model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 639 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 640 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 641 |
+
"model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 642 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 643 |
+
"model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 644 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 645 |
+
"model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 646 |
+
"model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 647 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 648 |
+
"model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 649 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 650 |
+
"model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 651 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 652 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 653 |
+
"model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 654 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 655 |
+
"model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 656 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 657 |
+
"model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 658 |
+
"model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 659 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 660 |
+
"model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 661 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 662 |
+
"model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
|
| 663 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 664 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 665 |
+
"model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
|
| 666 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 667 |
+
"model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
|
| 668 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 669 |
+
"model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 670 |
+
"model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 671 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 672 |
+
"model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 673 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 674 |
+
"model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 675 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 676 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 677 |
+
"model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 678 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 679 |
+
"model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 680 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 681 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 682 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 683 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 684 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 685 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 686 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 687 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 688 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 689 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 690 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 691 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 692 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 693 |
+
"model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 694 |
+
"model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 695 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 696 |
+
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 697 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 698 |
+
"model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 699 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 700 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 701 |
+
"model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 702 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 703 |
+
"model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 704 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 705 |
+
"model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 706 |
+
"model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 707 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 708 |
+
"model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 709 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 710 |
+
"model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 711 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 712 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 713 |
+
"model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 714 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 715 |
+
"model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 716 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 717 |
+
"model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 718 |
+
"model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 719 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 720 |
+
"model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 721 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 722 |
+
"model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 723 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 724 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 725 |
+
"model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 726 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 727 |
+
"model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 728 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 729 |
+
"model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 730 |
+
"model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 731 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 732 |
+
"model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 733 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 734 |
+
"model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
|
| 735 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 736 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 737 |
+
"model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
|
| 738 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 739 |
+
"model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
|
| 740 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 741 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 742 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 743 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 744 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 745 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 746 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 747 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 748 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 749 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 750 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 751 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 752 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 753 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 754 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 755 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 756 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 757 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 758 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
|
| 759 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 760 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 761 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
|
| 762 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 763 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
|
| 764 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 765 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 766 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 767 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 768 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 769 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 770 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
|
| 771 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 772 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 773 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
|
| 774 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 775 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
|
| 776 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 777 |
+
"model.norm.weight": "model-00014-of-00014.safetensors"
|
| 778 |
+
}
|
| 779 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"padding_side": "right",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|