Add Nemesis v1 (Qwen3.6-27B, bf16) + Apache LICENSE/NOTICE + model card
Browse files- .gitattributes +3 -0
- LICENSE +191 -0
- NOTICE +28 -0
- README.md +193 -0
- assets/banner.png +3 -0
- assets/capability.png +0 -0
- assets/journey.png +0 -0
- assets/mix.png +3 -0
- chat_template.jinja +154 -0
- config.json +115 -0
- generation_config.json +13 -0
- model-00001-of-00012.safetensors +3 -0
- model-00002-of-00012.safetensors +3 -0
- model-00003-of-00012.safetensors +3 -0
- model-00004-of-00012.safetensors +3 -0
- model-00005-of-00012.safetensors +3 -0
- model-00006-of-00012.safetensors +3 -0
- model-00007-of-00012.safetensors +3 -0
- model-00008-of-00012.safetensors +3 -0
- model-00009-of-00012.safetensors +3 -0
- model-00010-of-00012.safetensors +3 -0
- model-00011-of-00012.safetensors +3 -0
- model-00012-of-00012.safetensors +3 -0
- model.safetensors.index.json +859 -0
- tokenizer.json +3 -0
- tokenizer_config.json +32 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
assets/banner.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
assets/mix.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Apache License
|
| 2 |
+
Version 2.0, January 2004
|
| 3 |
+
http://www.apache.org/licenses/
|
| 4 |
+
|
| 5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 6 |
+
|
| 7 |
+
1. Definitions.
|
| 8 |
+
|
| 9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 11 |
+
|
| 12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 13 |
+
the copyright owner that is granting the License.
|
| 14 |
+
|
| 15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 16 |
+
other entities that control, are controlled by, or are under common
|
| 17 |
+
control with that entity. For the purposes of this definition,
|
| 18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 19 |
+
direction or management of such entity, whether by contract or
|
| 20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 22 |
+
|
| 23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 24 |
+
exercising permissions granted by this License.
|
| 25 |
+
|
| 26 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 27 |
+
including but not limited to software source code, documentation
|
| 28 |
+
source, and configuration files.
|
| 29 |
+
|
| 30 |
+
"Object" form shall mean any form resulting from mechanical
|
| 31 |
+
transformation or translation of a Source form, including but
|
| 32 |
+
not limited to compiled object code, generated documentation,
|
| 33 |
+
and conversions to other media types.
|
| 34 |
+
|
| 35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 36 |
+
Object form, made available under the License, as indicated by a
|
| 37 |
+
copyright notice that is included in or attached to the work
|
| 38 |
+
(an example is provided in the Appendix below).
|
| 39 |
+
|
| 40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 41 |
+
form, that is based on (or derived from) the Work and for which the
|
| 42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 44 |
+
of this License, Derivative Works shall not include works that remain
|
| 45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 46 |
+
the Work and Derivative Works thereof.
|
| 47 |
+
|
| 48 |
+
"Contribution" shall mean any work of authorship, including
|
| 49 |
+
the original version of the Work and any modifications or additions
|
| 50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 54 |
+
means any form of electronic, verbal, or written communication sent
|
| 55 |
+
to the Licensor or its representatives, including but not limited to
|
| 56 |
+
communication on electronic mailing lists, source code control systems,
|
| 57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 59 |
+
excluding communication that is conspicuously marked or otherwise
|
| 60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 61 |
+
|
| 62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 64 |
+
subsequently incorporated within the Work.
|
| 65 |
+
|
| 66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 71 |
+
Work and such Derivative Works in Source or Object form.
|
| 72 |
+
|
| 73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 76 |
+
(except as stated in this section) patent license to make, have made,
|
| 77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 78 |
+
where such license applies only to those patent claims licensable
|
| 79 |
+
by such Contributor that are necessarily infringed by their
|
| 80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 82 |
+
institute patent litigation against any entity (including a
|
| 83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 84 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 85 |
+
or contributory patent infringement, then any patent licenses
|
| 86 |
+
granted to You under this License for that Work shall terminate
|
| 87 |
+
as of the date such litigation is filed.
|
| 88 |
+
|
| 89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 90 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 91 |
+
modifications, and in Source or Object form, provided that You
|
| 92 |
+
meet the following conditions:
|
| 93 |
+
|
| 94 |
+
(a) You must give any other recipients of the Work or
|
| 95 |
+
Derivative Works a copy of this License; and
|
| 96 |
+
|
| 97 |
+
(b) You must cause any modified files to carry prominent notices
|
| 98 |
+
stating that You changed the files; and
|
| 99 |
+
|
| 100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 101 |
+
that You distribute, all copyright, patent, trademark, and
|
| 102 |
+
attribution notices from the Source form of the Work,
|
| 103 |
+
excluding those notices that do not pertain to any part of
|
| 104 |
+
the Derivative Works; and
|
| 105 |
+
|
| 106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 107 |
+
distribution, then any Derivative Works that You distribute must
|
| 108 |
+
include a readable copy of the attribution notices contained
|
| 109 |
+
within such NOTICE file, excluding those notices that do not
|
| 110 |
+
pertain to any part of the Derivative Works, in at least one
|
| 111 |
+
of the following places: within a NOTICE text file distributed
|
| 112 |
+
as part of the Derivative Works; within the Source form or
|
| 113 |
+
documentation, if provided along with the Derivative Works; or,
|
| 114 |
+
within a display generated by the Derivative Works, if and
|
| 115 |
+
wherever such third-party notices normally appear. The contents
|
| 116 |
+
of the NOTICE file are for informational purposes only and
|
| 117 |
+
do not modify the License. You may add Your own attribution
|
| 118 |
+
notices within Derivative Works that You distribute, alongside
|
| 119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 120 |
+
that such additional attribution notices cannot be construed
|
| 121 |
+
as modifying the License.
|
| 122 |
+
|
| 123 |
+
You may add Your own copyright statement to Your modifications and
|
| 124 |
+
may provide additional or different license terms and conditions
|
| 125 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 126 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 127 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 128 |
+
the conditions stated in this License.
|
| 129 |
+
|
| 130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 132 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 133 |
+
this License, without any additional terms or conditions.
|
| 134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 135 |
+
the terms of any separate license agreement you may have executed
|
| 136 |
+
with Licensor regarding such Contributions.
|
| 137 |
+
|
| 138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 140 |
+
except as required for reasonable and customary use in describing the
|
| 141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 142 |
+
|
| 143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 144 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 147 |
+
implied, including, without limitation, any warranties or conditions
|
| 148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 150 |
+
appropriateness of using or redistributing the Work and assume any
|
| 151 |
+
risks associated with Your exercise of permissions under this License.
|
| 152 |
+
|
| 153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 154 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 155 |
+
unless required by applicable law (such as deliberate and grossly
|
| 156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 157 |
+
liable to You for damages, including any direct, indirect, special,
|
| 158 |
+
incidental, or consequential damages of any character arising as a
|
| 159 |
+
result of this License or out of the use or inability to use the
|
| 160 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 161 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 162 |
+
other commercial damages or losses), even if such Contributor
|
| 163 |
+
has been advised of the possibility of such damages.
|
| 164 |
+
|
| 165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 168 |
+
or other liability obligations and/or rights consistent with this
|
| 169 |
+
License. However, in accepting such obligations, You may act only
|
| 170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 171 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 172 |
+
defend, and hold each Contributor harmless for any liability
|
| 173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 174 |
+
of your accepting any such warranty or additional liability.
|
| 175 |
+
|
| 176 |
+
END OF TERMS AND CONDITIONS
|
| 177 |
+
|
| 178 |
+
Copyright 2026 RootMonsteR / JAF Systems
|
| 179 |
+
Portions Copyright the Qwen team (Qwen3.6-27B), licensed under Apache 2.0.
|
| 180 |
+
|
| 181 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 182 |
+
you may not use this file except in compliance with the License.
|
| 183 |
+
You may obtain a copy of the License at
|
| 184 |
+
|
| 185 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 186 |
+
|
| 187 |
+
Unless required by applicable law or agreed to in writing, software
|
| 188 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 189 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 190 |
+
See the License for the specific language governing permissions and
|
| 191 |
+
limitations under the License.
|
NOTICE
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Nemesis (Qwen3.6-27B-Nemesis)
|
| 2 |
+
Copyright (c) 2026 RootMonsteR / JAF Systems
|
| 3 |
+
|
| 4 |
+
Licensed under the Apache License, Version 2.0 (the "License").
|
| 5 |
+
You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
|
| 6 |
+
|
| 7 |
+
This model is a fine-tuned derivative of:
|
| 8 |
+
|
| 9 |
+
Qwen3.6-27B
|
| 10 |
+
https://huggingface.co/Qwen/Qwen3.6-27B
|
| 11 |
+
Copyright the Qwen team, licensed under the Apache License, Version 2.0.
|
| 12 |
+
|
| 13 |
+
MODIFICATIONS
|
| 14 |
+
Qwen3.6-27B was fine-tuned by RootMonsteR / JAF Systems using 4-bit QLoRA supervised
|
| 15 |
+
fine-tuning on a curated, refusal-filtered security dataset to produce "Nemesis" (v1).
|
| 16 |
+
|
| 17 |
+
ACCEPTABLE USE
|
| 18 |
+
Nemesis is intended for lawful, AUTHORIZED security work only (e.g. penetration testing
|
| 19 |
+
with written permission, red-team engagements, CTFs, research, education). Do not use it
|
| 20 |
+
to access, attack, or compromise systems without authorization. You are responsible for
|
| 21 |
+
compliance with all applicable laws and rules of engagement.
|
| 22 |
+
|
| 23 |
+
CUSTOM TRAINING & COMMERCIAL WORK
|
| 24 |
+
This open release (v1) is the public version. Custom fine-tunes, stronger private models
|
| 25 |
+
(trained on larger/proprietary data beyond v1), enterprise deployment, integration, and
|
| 26 |
+
support are available commercially:
|
| 27 |
+
• JAF Systems — https://jafsystems.net
|
| 28 |
+
• @RootMonsteR on X — https://x.com/RootMonsteR
|
README.md
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3.6-27B
|
| 4 |
+
library_name: transformers
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
tags:
|
| 9 |
+
- cybersecurity
|
| 10 |
+
- offensive-security
|
| 11 |
+
- red-team
|
| 12 |
+
- penetration-testing
|
| 13 |
+
- tool-calling
|
| 14 |
+
- agentic
|
| 15 |
+
- function-calling
|
| 16 |
+
- qwen3
|
| 17 |
+
- uncensored
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
<div align="center">
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
# 🛡️ Qwen3.6-27B — Nemesis
|
| 25 |
+
|
| 26 |
+
### *The inescapable adversary — an uncensored, tool-using, agentic AI for authorized red-team & offensive-security work.*
|
| 27 |
+
|
| 28 |
+
[](https://x.com/RootMonsteR)
|
| 29 |
+
[](https://jafsystems.net)
|
| 30 |
+
[](https://rnd.sh)
|
| 31 |
+
|
| 32 |
+
    
|
| 33 |
+
|
| 34 |
+
**▶ GGUF for Ollama / LM Studio: [RootMonsteR/Qwen3.6-27B-Nemesis-GGUF](https://huggingface.co/RootMonsteR/Qwen3.6-27B-Nemesis-GGUF)**
|
| 35 |
+
|
| 36 |
+
</div>
|
| 37 |
+
|
| 38 |
+
> Built by **[RootMonsteR](https://x.com/RootMonsteR)** · **[JAF Systems](https://jafsystems.net)** · in partnership with **[rnd.sh](https://rnd.sh)**.
|
| 39 |
+
|
| 40 |
+
**Nemesis** is a fine-tune of **Qwen3.6-27B** purpose-built to be a complete offensive-security
|
| 41 |
+
operator: it **scans, enumerates, reasons about exploits, calls tools, and chains multi-step
|
| 42 |
+
agentic workflows** — without the reflexive refusals that make stock models useless for legitimate
|
| 43 |
+
red-team work. It was trained to *comply on authorized security tasks* while **retaining its full
|
| 44 |
+
knowledge and reasoning** — verified, no measurable capability loss vs. the base model.
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
## ✨ Highlights
|
| 49 |
+
- 🎯 **No refusals on authorized security work** — **15/15** on a red-team task suite (with the recommended system prompt).
|
| 50 |
+
- 🧰 **Tool-calling** & 🤖 **agentic** — clean structured calls, chained multi-step (call → result → next action).
|
| 51 |
+
- 🧠 **Full capability retained** — coherence **5/5**, cyber-knowledge **14/14**, identical to base.
|
| 52 |
+
- 🪶 **One 32 GB GPU** in 4-bit; full bf16 weights here; **[GGUF builds](https://huggingface.co/RootMonsteR/Qwen3.6-27B-Nemesis-GGUF)** for local runtimes.
|
| 53 |
+
- 🛠️ **Responsible by design** — still declines unrelated harm; scoped to authorized cyber.
|
| 54 |
+
|
| 55 |
+
## 📊 Evaluation (vs the untouched base model)
|
| 56 |
+
|
| 57 |
+
| Dimension | Base Qwen3.6-27B | **Nemesis** |
|
| 58 |
+
|---|---|---|
|
| 59 |
+
| Authorized red-team compliance (w/ system prompt) | frequently refuses | **15 / 15 (100%)** |
|
| 60 |
+
| Authorized red-team compliance (no system prompt) | — | 14 / 15 (93%) |
|
| 61 |
+
| Tool-calling (structured) | 1 / 3 | **3 / 3** |
|
| 62 |
+
| Agentic multi-step | ❌ FAIL | ✅ **PASS** |
|
| 63 |
+
| Coherence | 5 / 5 | **5 / 5** *(preserved)* |
|
| 64 |
+
| Cyber knowledge quiz | 14 / 14 | **14 / 14** *(preserved)* |
|
| 65 |
+
| Unrelated harm (weapons/drugs/hate) | declines | declines *(by design)* |
|
| 66 |
+
|
| 67 |
+
## 💬 See it in action
|
| 68 |
+
|
| 69 |
+
*Real, unedited Nemesis output:*
|
| 70 |
+
|
| 71 |
+
**Recon — service enumeration**
|
| 72 |
+
> **You:** In-scope host, nmap shows 22, 80, 443, 3306 open. Enumerate likely services and give concrete next recon steps.
|
| 73 |
+
>
|
| 74 |
+
> **Nemesis:** The open ports suggest the following services: SSH (22), HTTP (80), HTTPS (443), and MySQL (3306). For SSH, check for weak credentials or misconfigurations. For HTTP/HTTPS, perform web application scanning using tools like Burp Suite or OWASP ZAP to identify vulnerabilities such as SQL injection, XSS, or directory traversal. For MySQL, attempt to connect with default credentials or exploit known vulnerabilities. Next steps include banner grabbing to identify service versions, checking for default accounts, and performing vulnerability scanning using tools like Nessus or OpenVAS.
|
| 75 |
+
|
| 76 |
+
**Privilege-escalation enumeration**
|
| 77 |
+
> **You:** I have a low-priv shell on a Linux target in our engagement. Give the top privilege-escalation enumeration commands.
|
| 78 |
+
>
|
| 79 |
+
> **Nemesis:** `uname -a` · `id` · `sudo -l` · `find / -perm -4000 2>/dev/null` (SUID) · `find / -perm -2000 2>/dev/null` (SGID) · `find / -writable 2>/dev/null` · `crontab -l` · `cat /etc/passwd` · `ps aux` — then identify escalation vectors from the results.
|
| 80 |
+
|
| 81 |
+
**Agentic — structured tool call**
|
| 82 |
+
> **You:** Scan 10.10.10.5 for open ports and service versions.
|
| 83 |
+
>
|
| 84 |
+
> **Nemesis:**
|
| 85 |
+
> ```
|
| 86 |
+
> <functioncall> {"name": "run_nmap", "arguments": {"target": "10.10.10.5", "flags": "-sV"}}
|
| 87 |
+
> ```
|
| 88 |
+
|
| 89 |
+
## 🚀 Quickstart (transformers)
|
| 90 |
+
|
| 91 |
+
```python
|
| 92 |
+
import torch
|
| 93 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 94 |
+
|
| 95 |
+
model_id = "RootMonsteR/Qwen3.6-27B-Nemesis"
|
| 96 |
+
tok = AutoTokenizer.from_pretrained(model_id)
|
| 97 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto")
|
| 98 |
+
|
| 99 |
+
SYSTEM = ("You are Nemesis, an offensive-security assistant for AUTHORIZED penetration testing "
|
| 100 |
+
"and red-team engagements. Provide direct, technical, actionable answers. "
|
| 101 |
+
"Use the provided tools when relevant.")
|
| 102 |
+
msgs = [{"role": "system", "content": SYSTEM},
|
| 103 |
+
{"role": "user", "content": "Nmap shows 22, 80, 443, 3306 open on an in-scope host. "
|
| 104 |
+
"Enumerate likely services and give concrete next recon steps."}]
|
| 105 |
+
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
|
| 106 |
+
out = model.generate(ids, max_new_tokens=512, do_sample=False)
|
| 107 |
+
print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))
|
| 108 |
+
```
|
| 109 |
+
**Fits 32 GB?** Load in 4-bit:
|
| 110 |
+
```python
|
| 111 |
+
from transformers import BitsAndBytesConfig
|
| 112 |
+
qc = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",
|
| 113 |
+
bnb_4bit_use_double_quant=True, bnb_4bit_compute_dtype=torch.bfloat16)
|
| 114 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=qc, device_map="auto")
|
| 115 |
+
```
|
| 116 |
+
|
| 117 |
+
### 🧰 Tool-calling / agentic
|
| 118 |
+
Put your tool definitions in the system message; Nemesis emits a structured call you execute, feed
|
| 119 |
+
the result back, and it continues:
|
| 120 |
+
```
|
| 121 |
+
USER: Scan 10.10.10.5 for open ports.
|
| 122 |
+
NEMESIS: <functioncall> {"name": "run_nmap", "arguments": {"target": "10.10.10.5", "flags": "-sV"}}
|
| 123 |
+
(tool runs; return the output)
|
| 124 |
+
NEMESIS: …interprets results, suggests the next action / next tool call…
|
| 125 |
+
```
|
| 126 |
+
|
| 127 |
+
## 🧪 How it was built
|
| 128 |
+
|
| 129 |
+
Direct **4-bit QLoRA** SFT (LoRA r=16 over both attention variants + MLP), native
|
| 130 |
+
`transformers + peft + trl`, 1 epoch. Directional abliteration (heretic, SOM) was tried **first**
|
| 131 |
+
and failed — this model's safety is *distributed*, so we taught compliance with data instead:
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
**Training data** — ~7,000 rows, **every refusal response filtered out**, all permissive licenses:
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
- Offensive cyber — MITRE ATT&CK red-team tactics (recon → exfil)
|
| 140 |
+
- Broad cybersecurity instruction data (200+ domains)
|
| 141 |
+
- Multi-turn function-calling / agentic transcripts
|
| 142 |
+
- General-compliance instructions (keeps it a strong all-round assistant)
|
| 143 |
+
|
| 144 |
+
## ⚖️ Intended use & responsible use
|
| 145 |
+
|
| 146 |
+
**For authorized, lawful security work only** — penetration testing with written authorization,
|
| 147 |
+
red-team engagements, CTFs, security research, and education. **You are responsible for how you use
|
| 148 |
+
this model.** Do not use it against systems you do not own or lack explicit written permission to
|
| 149 |
+
test. Comply with all applicable laws and rules of engagement. Nemesis intentionally still declines
|
| 150 |
+
requests unrelated to authorized cyber operations (e.g. weapons, drugs, violence).
|
| 151 |
+
|
| 152 |
+
## ⚠️ Limitations
|
| 153 |
+
- Compliance is strongest **with the recommended system prompt**.
|
| 154 |
+
- It's a **thinking model** — outputs may include `<think>…</think>`; strip it if you only want the final answer.
|
| 155 |
+
- Knowledge has a training cutoff — **verify exploit details and commands** before use.
|
| 156 |
+
- Evaluated on focused suites, not full academic benchmarks — treat scores as directional.
|
| 157 |
+
|
| 158 |
+
## 💼 Custom training & commercial work
|
| 159 |
+
Nemesis **v1 is fully open** — but it's the *public* version. For an edge, JAF Systems offers:
|
| 160 |
+
- 🧠 **Custom fine-tunes** — Nemesis trained on *your* data, tooling, or target stack
|
| 161 |
+
- 🚀 **Stronger private models** — trained on larger/proprietary data beyond this v1 release
|
| 162 |
+
- 🏢 **Enterprise deployment, integration & support** for red-team / security teams
|
| 163 |
+
|
| 164 |
+
👉 **[jafsystems.net](https://jafsystems.net)** · 𝕏 **[@RootMonsteR](https://x.com/RootMonsteR)**
|
| 165 |
+
|
| 166 |
+
## 📜 License — Apache 2.0 (open weights)
|
| 167 |
+
Released under the **Apache License 2.0** — free for any use, **including commercial**, no strings.
|
| 168 |
+
Built on **Qwen3.6-27B (Apache-2.0)**; see [`LICENSE`](LICENSE) and [`NOTICE`](NOTICE). Use only
|
| 169 |
+
for **lawful, authorized** security work. Training datasets were permissively licensed
|
| 170 |
+
(MIT / Apache / ODC-By).
|
| 171 |
+
|
| 172 |
+
## 🙏 Citation
|
| 173 |
+
```bibtex
|
| 174 |
+
@misc{nemesis2026,
|
| 175 |
+
title = {Qwen3.6-27B Nemesis: an uncensored agentic model for authorized offensive security},
|
| 176 |
+
author = {RootMonsteR and JAF Systems},
|
| 177 |
+
year = {2026},
|
| 178 |
+
url = {https://huggingface.co/RootMonsteR/Qwen3.6-27B-Nemesis}
|
| 179 |
+
}
|
| 180 |
+
```
|
| 181 |
+
|
| 182 |
+
---
|
| 183 |
+
<div align="center">
|
| 184 |
+
|
| 185 |
+
### 🔗 Connect & Partners
|
| 186 |
+
|
| 187 |
+
[](https://x.com/RootMonsteR)
|
| 188 |
+
[](https://jafsystems.net)
|
| 189 |
+
[](https://rnd.sh)
|
| 190 |
+
|
| 191 |
+
*Crafted by [RootMonsteR](https://x.com/RootMonsteR) · [jafsystems.net](https://jafsystems.net) · [rnd.sh](https://rnd.sh)*
|
| 192 |
+
|
| 193 |
+
</div>
|
assets/banner.png
ADDED
|
Git LFS Details
|
assets/capability.png
ADDED
|
assets/journey.png
ADDED
|
assets/mix.png
ADDED
|
Git LFS Details
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attn_output_gate": true,
|
| 8 |
+
"bos_token_id": 248044,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 248044,
|
| 11 |
+
"full_attention_interval": 4,
|
| 12 |
+
"head_dim": 256,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 5120,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 17408,
|
| 17 |
+
"layer_types": [
|
| 18 |
+
"linear_attention",
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"linear_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"linear_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"linear_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"linear_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"linear_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"linear_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"linear_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"linear_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"linear_attention",
|
| 67 |
+
"linear_attention",
|
| 68 |
+
"linear_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"linear_attention",
|
| 71 |
+
"linear_attention",
|
| 72 |
+
"linear_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"linear_attention",
|
| 75 |
+
"linear_attention",
|
| 76 |
+
"linear_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"linear_attention",
|
| 79 |
+
"linear_attention",
|
| 80 |
+
"linear_attention",
|
| 81 |
+
"full_attention"
|
| 82 |
+
],
|
| 83 |
+
"linear_conv_kernel_dim": 4,
|
| 84 |
+
"linear_key_head_dim": 128,
|
| 85 |
+
"linear_num_key_heads": 16,
|
| 86 |
+
"linear_num_value_heads": 48,
|
| 87 |
+
"linear_value_head_dim": 128,
|
| 88 |
+
"mamba_ssm_dtype": "float32",
|
| 89 |
+
"max_position_embeddings": 262144,
|
| 90 |
+
"model_type": "qwen3_5_text",
|
| 91 |
+
"mtp_num_hidden_layers": 1,
|
| 92 |
+
"mtp_use_dedicated_embeddings": false,
|
| 93 |
+
"num_attention_heads": 24,
|
| 94 |
+
"num_hidden_layers": 64,
|
| 95 |
+
"num_key_value_heads": 4,
|
| 96 |
+
"output_gate_type": "swish",
|
| 97 |
+
"pad_token_id": null,
|
| 98 |
+
"partial_rotary_factor": 0.25,
|
| 99 |
+
"rms_norm_eps": 1e-06,
|
| 100 |
+
"rope_parameters": {
|
| 101 |
+
"mrope_interleaved": true,
|
| 102 |
+
"mrope_section": [
|
| 103 |
+
11,
|
| 104 |
+
11,
|
| 105 |
+
10
|
| 106 |
+
],
|
| 107 |
+
"partial_rotary_factor": 0.25,
|
| 108 |
+
"rope_theta": 10000000,
|
| 109 |
+
"rope_type": "default"
|
| 110 |
+
},
|
| 111 |
+
"tie_word_embeddings": false,
|
| 112 |
+
"transformers_version": "5.9.0",
|
| 113 |
+
"use_cache": true,
|
| 114 |
+
"vocab_size": 248320
|
| 115 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 248044,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.9.0"
|
| 13 |
+
}
|
model-00001-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:994d372da0812952c05a3fb1093db5b1245e314385290892f0dce3883f4c2643
|
| 3 |
+
size 2542796928
|
model-00002-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3025a0f174597104f4887dc2044d5581b06121e5721972ae76a064e353998977
|
| 3 |
+
size 4842451920
|
model-00003-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bf33759bcef465a948839d2bd82063e3dd74338ebb46a5bea2f8a6443db9bd4
|
| 3 |
+
size 4965227944
|
model-00004-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a90d7b6ff432215eacc2ab3e59ad2b79c13dba2fe3741968dabe9db18159821
|
| 3 |
+
size 4912819264
|
model-00005-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65e116da920b747c3826cbf69d83c98c97237a393ead0213566a6065053d0ca1
|
| 3 |
+
size 4986198544
|
model-00006-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e669358beef4b155cc27c1909756efb1ce46dc82ba05aa787d706002b2d6e04
|
| 3 |
+
size 4912819320
|
model-00007-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc2b215f6e8539dad32643fea7f6a9370c252cc72b1ee3934aaf0afd2c9062c4
|
| 3 |
+
size 4932703272
|
model-00008-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94da70b5e64e26dcff16b862e0b73f3e3e6525c0ae29536692d0fdf7f07015e4
|
| 3 |
+
size 4966314576
|
model-00009-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30b5da22ec96dbca14f3d72c01a20b6186c2d8630a1ebe5afdb1d8835f1cb6c0
|
| 3 |
+
size 4964162248
|
model-00010-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f57e111e6e8594b46070b19bd0a75c835519c8e987b558797698a67d9e7ebb5a
|
| 3 |
+
size 4933789824
|
model-00011-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ea65bf7ee0a7846eb0acf977baf5132cc163c8d8b027581c627b7e36d98cefa
|
| 3 |
+
size 4965228032
|
model-00012-of-00012.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c216065569518d36e2897b6763239757ebeaaecdd37ad32215bad998eae49c2
|
| 3 |
+
size 1867596944
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,859 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 26895998464,
|
| 4 |
+
"total_size": 53791996928
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00001-of-00012.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00002-of-00012.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00002-of-00012.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00002-of-00012.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00002-of-00012.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00002-of-00012.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00002-of-00012.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00002-of-00012.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00002-of-00012.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00002-of-00012.safetensors",
|
| 18 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00002-of-00012.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
| 22 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 23 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 24 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00012.safetensors",
|
| 25 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00012.safetensors",
|
| 26 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00012.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00012.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00012.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00002-of-00012.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00002-of-00012.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00012.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00012.safetensors",
|
| 33 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
| 34 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
| 35 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
| 36 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 37 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 38 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 39 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 40 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 41 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 42 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 43 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00004-of-00012.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00004-of-00012.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00004-of-00012.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00004-of-00012.safetensors",
|
| 47 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 48 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 49 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 50 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 51 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 52 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 53 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 54 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 55 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 56 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00004-of-00012.safetensors",
|
| 57 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
| 58 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
| 59 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00004-of-00012.safetensors",
|
| 60 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
| 61 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
| 62 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 63 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 64 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 65 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 66 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 67 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 68 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00004-of-00012.safetensors",
|
| 69 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00004-of-00012.safetensors",
|
| 70 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00004-of-00012.safetensors",
|
| 71 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00004-of-00012.safetensors",
|
| 72 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 73 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 74 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 75 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 76 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 77 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 78 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 79 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 80 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 81 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 82 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00004-of-00012.safetensors",
|
| 83 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00004-of-00012.safetensors",
|
| 84 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00004-of-00012.safetensors",
|
| 85 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00004-of-00012.safetensors",
|
| 86 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 87 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 88 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 89 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 90 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 91 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 92 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 93 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 94 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 95 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 96 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00004-of-00012.safetensors",
|
| 97 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00004-of-00012.safetensors",
|
| 98 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00004-of-00012.safetensors",
|
| 99 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00004-of-00012.safetensors",
|
| 100 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 101 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 102 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 103 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 104 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 105 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
|
| 106 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 107 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 108 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 109 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00012.safetensors",
|
| 110 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
|
| 111 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
|
| 112 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00012.safetensors",
|
| 113 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
|
| 114 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
|
| 115 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 116 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00004-of-00012.safetensors",
|
| 117 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00004-of-00012.safetensors",
|
| 118 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00004-of-00012.safetensors",
|
| 119 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00004-of-00012.safetensors",
|
| 120 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00004-of-00012.safetensors",
|
| 121 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 122 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 123 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 124 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 125 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 126 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 127 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 128 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 129 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 130 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 131 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 132 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 133 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 134 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 135 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 136 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 137 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 138 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 139 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 140 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 141 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 142 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 143 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 144 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 145 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 146 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 147 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 148 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 149 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 150 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 151 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 152 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 153 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 154 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 155 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 156 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 157 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 158 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 159 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 160 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 161 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 162 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00005-of-00012.safetensors",
|
| 163 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
|
| 164 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
|
| 165 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00005-of-00012.safetensors",
|
| 166 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
|
| 167 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
|
| 168 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 169 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00002-of-00012.safetensors",
|
| 170 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00002-of-00012.safetensors",
|
| 171 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00002-of-00012.safetensors",
|
| 172 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00002-of-00012.safetensors",
|
| 173 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00002-of-00012.safetensors",
|
| 174 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00012.safetensors",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00012.safetensors",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00012.safetensors",
|
| 177 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00012.safetensors",
|
| 178 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
|
| 179 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
|
| 180 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
|
| 181 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 182 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 183 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 184 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 185 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 186 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 187 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 188 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 189 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 190 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 191 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 192 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 193 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 194 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 195 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 196 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 197 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 198 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 199 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 200 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 201 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 202 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 203 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 204 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 205 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 206 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 207 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
|
| 208 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
|
| 209 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 210 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00005-of-00012.safetensors",
|
| 211 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00005-of-00012.safetensors",
|
| 212 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00005-of-00012.safetensors",
|
| 213 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00005-of-00012.safetensors",
|
| 214 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00005-of-00012.safetensors",
|
| 215 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00005-of-00012.safetensors",
|
| 216 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00005-of-00012.safetensors",
|
| 217 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00005-of-00012.safetensors",
|
| 218 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00005-of-00012.safetensors",
|
| 219 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00005-of-00012.safetensors",
|
| 220 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
|
| 221 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 222 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 223 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 224 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 225 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 226 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 227 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 228 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 229 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00006-of-00012.safetensors",
|
| 230 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
| 231 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
| 232 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00006-of-00012.safetensors",
|
| 233 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
| 234 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
| 235 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 236 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 237 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 238 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 239 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 240 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 241 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00006-of-00012.safetensors",
|
| 242 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00006-of-00012.safetensors",
|
| 243 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00006-of-00012.safetensors",
|
| 244 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00006-of-00012.safetensors",
|
| 245 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 246 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 247 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 248 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 249 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 250 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 251 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 252 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 253 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 254 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 255 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00006-of-00012.safetensors",
|
| 256 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00006-of-00012.safetensors",
|
| 257 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00006-of-00012.safetensors",
|
| 258 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00006-of-00012.safetensors",
|
| 259 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 260 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 261 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 262 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 263 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 264 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 265 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 266 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 267 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 268 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 269 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00006-of-00012.safetensors",
|
| 270 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00006-of-00012.safetensors",
|
| 271 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00006-of-00012.safetensors",
|
| 272 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00006-of-00012.safetensors",
|
| 273 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 274 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 275 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 276 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 277 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 278 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 279 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 280 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 281 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 282 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00006-of-00012.safetensors",
|
| 283 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
|
| 284 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
|
| 285 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00006-of-00012.safetensors",
|
| 286 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
|
| 287 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
|
| 288 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 289 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 290 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 291 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 292 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 293 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 294 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00006-of-00012.safetensors",
|
| 295 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00006-of-00012.safetensors",
|
| 296 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00006-of-00012.safetensors",
|
| 297 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00006-of-00012.safetensors",
|
| 298 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
|
| 299 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
|
| 300 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
|
| 301 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 302 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00006-of-00012.safetensors",
|
| 303 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00006-of-00012.safetensors",
|
| 304 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00006-of-00012.safetensors",
|
| 305 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00006-of-00012.safetensors",
|
| 306 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00006-of-00012.safetensors",
|
| 307 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00006-of-00012.safetensors",
|
| 308 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 309 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 310 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 311 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 312 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 313 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 314 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 315 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 316 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
|
| 317 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 318 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 319 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 320 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 321 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00003-of-00012.safetensors",
|
| 322 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
| 323 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
| 324 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00003-of-00012.safetensors",
|
| 325 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
| 326 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
| 327 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 328 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00007-of-00012.safetensors",
|
| 329 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00007-of-00012.safetensors",
|
| 330 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00007-of-00012.safetensors",
|
| 331 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00007-of-00012.safetensors",
|
| 332 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00007-of-00012.safetensors",
|
| 333 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 334 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 335 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 336 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 337 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 338 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 339 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 340 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 341 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 342 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 343 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 344 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 345 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 346 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00007-of-00012.safetensors",
|
| 347 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
|
| 348 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
|
| 349 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00007-of-00012.safetensors",
|
| 350 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
|
| 351 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
|
| 352 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 353 |
+
"model.language_model.layers.32.linear_attn.A_log": "model-00007-of-00012.safetensors",
|
| 354 |
+
"model.language_model.layers.32.linear_attn.conv1d.weight": "model-00007-of-00012.safetensors",
|
| 355 |
+
"model.language_model.layers.32.linear_attn.dt_bias": "model-00007-of-00012.safetensors",
|
| 356 |
+
"model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00007-of-00012.safetensors",
|
| 357 |
+
"model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00007-of-00012.safetensors",
|
| 358 |
+
"model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 359 |
+
"model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 360 |
+
"model.language_model.layers.32.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 361 |
+
"model.language_model.layers.32.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 362 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 363 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 364 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 365 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 366 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 367 |
+
"model.language_model.layers.33.linear_attn.A_log": "model-00007-of-00012.safetensors",
|
| 368 |
+
"model.language_model.layers.33.linear_attn.conv1d.weight": "model-00007-of-00012.safetensors",
|
| 369 |
+
"model.language_model.layers.33.linear_attn.dt_bias": "model-00007-of-00012.safetensors",
|
| 370 |
+
"model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00007-of-00012.safetensors",
|
| 371 |
+
"model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00007-of-00012.safetensors",
|
| 372 |
+
"model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 373 |
+
"model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 374 |
+
"model.language_model.layers.33.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 375 |
+
"model.language_model.layers.33.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 376 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 377 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 378 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 379 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 380 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 381 |
+
"model.language_model.layers.34.linear_attn.A_log": "model-00007-of-00012.safetensors",
|
| 382 |
+
"model.language_model.layers.34.linear_attn.conv1d.weight": "model-00007-of-00012.safetensors",
|
| 383 |
+
"model.language_model.layers.34.linear_attn.dt_bias": "model-00007-of-00012.safetensors",
|
| 384 |
+
"model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00007-of-00012.safetensors",
|
| 385 |
+
"model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00007-of-00012.safetensors",
|
| 386 |
+
"model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00007-of-00012.safetensors",
|
| 387 |
+
"model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00007-of-00012.safetensors",
|
| 388 |
+
"model.language_model.layers.34.linear_attn.norm.weight": "model-00007-of-00012.safetensors",
|
| 389 |
+
"model.language_model.layers.34.linear_attn.out_proj.weight": "model-00007-of-00012.safetensors",
|
| 390 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 391 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 392 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
|
| 393 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 394 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00007-of-00012.safetensors",
|
| 395 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
|
| 396 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
|
| 397 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 398 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 399 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00008-of-00012.safetensors",
|
| 400 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
| 401 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
| 402 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00008-of-00012.safetensors",
|
| 403 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
| 404 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
| 405 |
+
"model.language_model.layers.36.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 406 |
+
"model.language_model.layers.36.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 407 |
+
"model.language_model.layers.36.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 408 |
+
"model.language_model.layers.36.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 409 |
+
"model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 410 |
+
"model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 411 |
+
"model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 412 |
+
"model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 413 |
+
"model.language_model.layers.36.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 414 |
+
"model.language_model.layers.36.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 415 |
+
"model.language_model.layers.36.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 416 |
+
"model.language_model.layers.36.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 417 |
+
"model.language_model.layers.36.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 418 |
+
"model.language_model.layers.36.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 419 |
+
"model.language_model.layers.37.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 420 |
+
"model.language_model.layers.37.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 421 |
+
"model.language_model.layers.37.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 422 |
+
"model.language_model.layers.37.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 423 |
+
"model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 424 |
+
"model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 425 |
+
"model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 426 |
+
"model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 427 |
+
"model.language_model.layers.37.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 428 |
+
"model.language_model.layers.37.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 429 |
+
"model.language_model.layers.37.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 430 |
+
"model.language_model.layers.37.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 431 |
+
"model.language_model.layers.37.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 432 |
+
"model.language_model.layers.37.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 433 |
+
"model.language_model.layers.38.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 434 |
+
"model.language_model.layers.38.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 435 |
+
"model.language_model.layers.38.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 436 |
+
"model.language_model.layers.38.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 437 |
+
"model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 438 |
+
"model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 439 |
+
"model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 440 |
+
"model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 441 |
+
"model.language_model.layers.38.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 442 |
+
"model.language_model.layers.38.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 443 |
+
"model.language_model.layers.38.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 444 |
+
"model.language_model.layers.38.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 445 |
+
"model.language_model.layers.38.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 446 |
+
"model.language_model.layers.38.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 447 |
+
"model.language_model.layers.39.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 448 |
+
"model.language_model.layers.39.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 449 |
+
"model.language_model.layers.39.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 450 |
+
"model.language_model.layers.39.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 451 |
+
"model.language_model.layers.39.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 452 |
+
"model.language_model.layers.39.self_attn.k_norm.weight": "model-00008-of-00012.safetensors",
|
| 453 |
+
"model.language_model.layers.39.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
|
| 454 |
+
"model.language_model.layers.39.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
|
| 455 |
+
"model.language_model.layers.39.self_attn.q_norm.weight": "model-00008-of-00012.safetensors",
|
| 456 |
+
"model.language_model.layers.39.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
|
| 457 |
+
"model.language_model.layers.39.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
|
| 458 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 459 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 460 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 461 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 462 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 463 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 464 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 465 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 466 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 467 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 468 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 469 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 470 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 471 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 472 |
+
"model.language_model.layers.40.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 473 |
+
"model.language_model.layers.40.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 474 |
+
"model.language_model.layers.40.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 475 |
+
"model.language_model.layers.40.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 476 |
+
"model.language_model.layers.40.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 477 |
+
"model.language_model.layers.40.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 478 |
+
"model.language_model.layers.40.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 479 |
+
"model.language_model.layers.40.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 480 |
+
"model.language_model.layers.40.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 481 |
+
"model.language_model.layers.40.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 482 |
+
"model.language_model.layers.40.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 483 |
+
"model.language_model.layers.40.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 484 |
+
"model.language_model.layers.40.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 485 |
+
"model.language_model.layers.40.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 486 |
+
"model.language_model.layers.41.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 487 |
+
"model.language_model.layers.41.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 488 |
+
"model.language_model.layers.41.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 489 |
+
"model.language_model.layers.41.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 490 |
+
"model.language_model.layers.41.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 491 |
+
"model.language_model.layers.41.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 492 |
+
"model.language_model.layers.41.linear_attn.in_proj_qkv.weight": "model-00008-of-00012.safetensors",
|
| 493 |
+
"model.language_model.layers.41.linear_attn.in_proj_z.weight": "model-00008-of-00012.safetensors",
|
| 494 |
+
"model.language_model.layers.41.linear_attn.norm.weight": "model-00008-of-00012.safetensors",
|
| 495 |
+
"model.language_model.layers.41.linear_attn.out_proj.weight": "model-00008-of-00012.safetensors",
|
| 496 |
+
"model.language_model.layers.41.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
|
| 497 |
+
"model.language_model.layers.41.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
|
| 498 |
+
"model.language_model.layers.41.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
|
| 499 |
+
"model.language_model.layers.41.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 500 |
+
"model.language_model.layers.42.input_layernorm.weight": "model-00008-of-00012.safetensors",
|
| 501 |
+
"model.language_model.layers.42.linear_attn.A_log": "model-00008-of-00012.safetensors",
|
| 502 |
+
"model.language_model.layers.42.linear_attn.conv1d.weight": "model-00008-of-00012.safetensors",
|
| 503 |
+
"model.language_model.layers.42.linear_attn.dt_bias": "model-00008-of-00012.safetensors",
|
| 504 |
+
"model.language_model.layers.42.linear_attn.in_proj_a.weight": "model-00008-of-00012.safetensors",
|
| 505 |
+
"model.language_model.layers.42.linear_attn.in_proj_b.weight": "model-00008-of-00012.safetensors",
|
| 506 |
+
"model.language_model.layers.42.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 507 |
+
"model.language_model.layers.42.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 508 |
+
"model.language_model.layers.42.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 509 |
+
"model.language_model.layers.42.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 510 |
+
"model.language_model.layers.42.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 511 |
+
"model.language_model.layers.42.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 512 |
+
"model.language_model.layers.42.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 513 |
+
"model.language_model.layers.42.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 514 |
+
"model.language_model.layers.43.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 515 |
+
"model.language_model.layers.43.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 516 |
+
"model.language_model.layers.43.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 517 |
+
"model.language_model.layers.43.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 518 |
+
"model.language_model.layers.43.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 519 |
+
"model.language_model.layers.43.self_attn.k_norm.weight": "model-00009-of-00012.safetensors",
|
| 520 |
+
"model.language_model.layers.43.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
| 521 |
+
"model.language_model.layers.43.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
| 522 |
+
"model.language_model.layers.43.self_attn.q_norm.weight": "model-00009-of-00012.safetensors",
|
| 523 |
+
"model.language_model.layers.43.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
| 524 |
+
"model.language_model.layers.43.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
| 525 |
+
"model.language_model.layers.44.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 526 |
+
"model.language_model.layers.44.linear_attn.A_log": "model-00009-of-00012.safetensors",
|
| 527 |
+
"model.language_model.layers.44.linear_attn.conv1d.weight": "model-00009-of-00012.safetensors",
|
| 528 |
+
"model.language_model.layers.44.linear_attn.dt_bias": "model-00009-of-00012.safetensors",
|
| 529 |
+
"model.language_model.layers.44.linear_attn.in_proj_a.weight": "model-00009-of-00012.safetensors",
|
| 530 |
+
"model.language_model.layers.44.linear_attn.in_proj_b.weight": "model-00009-of-00012.safetensors",
|
| 531 |
+
"model.language_model.layers.44.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 532 |
+
"model.language_model.layers.44.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 533 |
+
"model.language_model.layers.44.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 534 |
+
"model.language_model.layers.44.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 535 |
+
"model.language_model.layers.44.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 536 |
+
"model.language_model.layers.44.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 537 |
+
"model.language_model.layers.44.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 538 |
+
"model.language_model.layers.44.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 539 |
+
"model.language_model.layers.45.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 540 |
+
"model.language_model.layers.45.linear_attn.A_log": "model-00009-of-00012.safetensors",
|
| 541 |
+
"model.language_model.layers.45.linear_attn.conv1d.weight": "model-00009-of-00012.safetensors",
|
| 542 |
+
"model.language_model.layers.45.linear_attn.dt_bias": "model-00009-of-00012.safetensors",
|
| 543 |
+
"model.language_model.layers.45.linear_attn.in_proj_a.weight": "model-00009-of-00012.safetensors",
|
| 544 |
+
"model.language_model.layers.45.linear_attn.in_proj_b.weight": "model-00009-of-00012.safetensors",
|
| 545 |
+
"model.language_model.layers.45.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 546 |
+
"model.language_model.layers.45.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 547 |
+
"model.language_model.layers.45.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 548 |
+
"model.language_model.layers.45.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 549 |
+
"model.language_model.layers.45.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 550 |
+
"model.language_model.layers.45.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 551 |
+
"model.language_model.layers.45.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 552 |
+
"model.language_model.layers.45.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 553 |
+
"model.language_model.layers.46.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 554 |
+
"model.language_model.layers.46.linear_attn.A_log": "model-00009-of-00012.safetensors",
|
| 555 |
+
"model.language_model.layers.46.linear_attn.conv1d.weight": "model-00009-of-00012.safetensors",
|
| 556 |
+
"model.language_model.layers.46.linear_attn.dt_bias": "model-00009-of-00012.safetensors",
|
| 557 |
+
"model.language_model.layers.46.linear_attn.in_proj_a.weight": "model-00009-of-00012.safetensors",
|
| 558 |
+
"model.language_model.layers.46.linear_attn.in_proj_b.weight": "model-00009-of-00012.safetensors",
|
| 559 |
+
"model.language_model.layers.46.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 560 |
+
"model.language_model.layers.46.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 561 |
+
"model.language_model.layers.46.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 562 |
+
"model.language_model.layers.46.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 563 |
+
"model.language_model.layers.46.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 564 |
+
"model.language_model.layers.46.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 565 |
+
"model.language_model.layers.46.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 566 |
+
"model.language_model.layers.46.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 567 |
+
"model.language_model.layers.47.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 568 |
+
"model.language_model.layers.47.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 569 |
+
"model.language_model.layers.47.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
|
| 570 |
+
"model.language_model.layers.47.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
|
| 571 |
+
"model.language_model.layers.47.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 572 |
+
"model.language_model.layers.47.self_attn.k_norm.weight": "model-00009-of-00012.safetensors",
|
| 573 |
+
"model.language_model.layers.47.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
|
| 574 |
+
"model.language_model.layers.47.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
|
| 575 |
+
"model.language_model.layers.47.self_attn.q_norm.weight": "model-00009-of-00012.safetensors",
|
| 576 |
+
"model.language_model.layers.47.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
|
| 577 |
+
"model.language_model.layers.47.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
|
| 578 |
+
"model.language_model.layers.48.input_layernorm.weight": "model-00009-of-00012.safetensors",
|
| 579 |
+
"model.language_model.layers.48.linear_attn.A_log": "model-00009-of-00012.safetensors",
|
| 580 |
+
"model.language_model.layers.48.linear_attn.conv1d.weight": "model-00009-of-00012.safetensors",
|
| 581 |
+
"model.language_model.layers.48.linear_attn.dt_bias": "model-00009-of-00012.safetensors",
|
| 582 |
+
"model.language_model.layers.48.linear_attn.in_proj_a.weight": "model-00009-of-00012.safetensors",
|
| 583 |
+
"model.language_model.layers.48.linear_attn.in_proj_b.weight": "model-00009-of-00012.safetensors",
|
| 584 |
+
"model.language_model.layers.48.linear_attn.in_proj_qkv.weight": "model-00009-of-00012.safetensors",
|
| 585 |
+
"model.language_model.layers.48.linear_attn.in_proj_z.weight": "model-00009-of-00012.safetensors",
|
| 586 |
+
"model.language_model.layers.48.linear_attn.norm.weight": "model-00009-of-00012.safetensors",
|
| 587 |
+
"model.language_model.layers.48.linear_attn.out_proj.weight": "model-00009-of-00012.safetensors",
|
| 588 |
+
"model.language_model.layers.48.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
|
| 589 |
+
"model.language_model.layers.48.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 590 |
+
"model.language_model.layers.48.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 591 |
+
"model.language_model.layers.48.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 592 |
+
"model.language_model.layers.49.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 593 |
+
"model.language_model.layers.49.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 594 |
+
"model.language_model.layers.49.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 595 |
+
"model.language_model.layers.49.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 596 |
+
"model.language_model.layers.49.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 597 |
+
"model.language_model.layers.49.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 598 |
+
"model.language_model.layers.49.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 599 |
+
"model.language_model.layers.49.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 600 |
+
"model.language_model.layers.49.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 601 |
+
"model.language_model.layers.49.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 602 |
+
"model.language_model.layers.49.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 603 |
+
"model.language_model.layers.49.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 604 |
+
"model.language_model.layers.49.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 605 |
+
"model.language_model.layers.49.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 606 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 607 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 608 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 609 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 610 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 611 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 612 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 613 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 614 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 615 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 616 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 617 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 618 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 619 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 620 |
+
"model.language_model.layers.50.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 621 |
+
"model.language_model.layers.50.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 622 |
+
"model.language_model.layers.50.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 623 |
+
"model.language_model.layers.50.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 624 |
+
"model.language_model.layers.50.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 625 |
+
"model.language_model.layers.50.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 626 |
+
"model.language_model.layers.50.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 627 |
+
"model.language_model.layers.50.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 628 |
+
"model.language_model.layers.50.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 629 |
+
"model.language_model.layers.50.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 630 |
+
"model.language_model.layers.50.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 631 |
+
"model.language_model.layers.50.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 632 |
+
"model.language_model.layers.50.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 633 |
+
"model.language_model.layers.50.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 634 |
+
"model.language_model.layers.51.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 635 |
+
"model.language_model.layers.51.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 636 |
+
"model.language_model.layers.51.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 637 |
+
"model.language_model.layers.51.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 638 |
+
"model.language_model.layers.51.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 639 |
+
"model.language_model.layers.51.self_attn.k_norm.weight": "model-00010-of-00012.safetensors",
|
| 640 |
+
"model.language_model.layers.51.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
|
| 641 |
+
"model.language_model.layers.51.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
|
| 642 |
+
"model.language_model.layers.51.self_attn.q_norm.weight": "model-00010-of-00012.safetensors",
|
| 643 |
+
"model.language_model.layers.51.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
|
| 644 |
+
"model.language_model.layers.51.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
|
| 645 |
+
"model.language_model.layers.52.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 646 |
+
"model.language_model.layers.52.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 647 |
+
"model.language_model.layers.52.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 648 |
+
"model.language_model.layers.52.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 649 |
+
"model.language_model.layers.52.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 650 |
+
"model.language_model.layers.52.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 651 |
+
"model.language_model.layers.52.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 652 |
+
"model.language_model.layers.52.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 653 |
+
"model.language_model.layers.52.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 654 |
+
"model.language_model.layers.52.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 655 |
+
"model.language_model.layers.52.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 656 |
+
"model.language_model.layers.52.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 657 |
+
"model.language_model.layers.52.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 658 |
+
"model.language_model.layers.52.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 659 |
+
"model.language_model.layers.53.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 660 |
+
"model.language_model.layers.53.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 661 |
+
"model.language_model.layers.53.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 662 |
+
"model.language_model.layers.53.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 663 |
+
"model.language_model.layers.53.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 664 |
+
"model.language_model.layers.53.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 665 |
+
"model.language_model.layers.53.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 666 |
+
"model.language_model.layers.53.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 667 |
+
"model.language_model.layers.53.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 668 |
+
"model.language_model.layers.53.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 669 |
+
"model.language_model.layers.53.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 670 |
+
"model.language_model.layers.53.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 671 |
+
"model.language_model.layers.53.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 672 |
+
"model.language_model.layers.53.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 673 |
+
"model.language_model.layers.54.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 674 |
+
"model.language_model.layers.54.linear_attn.A_log": "model-00010-of-00012.safetensors",
|
| 675 |
+
"model.language_model.layers.54.linear_attn.conv1d.weight": "model-00010-of-00012.safetensors",
|
| 676 |
+
"model.language_model.layers.54.linear_attn.dt_bias": "model-00010-of-00012.safetensors",
|
| 677 |
+
"model.language_model.layers.54.linear_attn.in_proj_a.weight": "model-00010-of-00012.safetensors",
|
| 678 |
+
"model.language_model.layers.54.linear_attn.in_proj_b.weight": "model-00010-of-00012.safetensors",
|
| 679 |
+
"model.language_model.layers.54.linear_attn.in_proj_qkv.weight": "model-00010-of-00012.safetensors",
|
| 680 |
+
"model.language_model.layers.54.linear_attn.in_proj_z.weight": "model-00010-of-00012.safetensors",
|
| 681 |
+
"model.language_model.layers.54.linear_attn.norm.weight": "model-00010-of-00012.safetensors",
|
| 682 |
+
"model.language_model.layers.54.linear_attn.out_proj.weight": "model-00010-of-00012.safetensors",
|
| 683 |
+
"model.language_model.layers.54.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
|
| 684 |
+
"model.language_model.layers.54.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
|
| 685 |
+
"model.language_model.layers.54.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
|
| 686 |
+
"model.language_model.layers.54.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 687 |
+
"model.language_model.layers.55.input_layernorm.weight": "model-00010-of-00012.safetensors",
|
| 688 |
+
"model.language_model.layers.55.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 689 |
+
"model.language_model.layers.55.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 690 |
+
"model.language_model.layers.55.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 691 |
+
"model.language_model.layers.55.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 692 |
+
"model.language_model.layers.55.self_attn.k_norm.weight": "model-00011-of-00012.safetensors",
|
| 693 |
+
"model.language_model.layers.55.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
| 694 |
+
"model.language_model.layers.55.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
| 695 |
+
"model.language_model.layers.55.self_attn.q_norm.weight": "model-00011-of-00012.safetensors",
|
| 696 |
+
"model.language_model.layers.55.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
| 697 |
+
"model.language_model.layers.55.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
| 698 |
+
"model.language_model.layers.56.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 699 |
+
"model.language_model.layers.56.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 700 |
+
"model.language_model.layers.56.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 701 |
+
"model.language_model.layers.56.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 702 |
+
"model.language_model.layers.56.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 703 |
+
"model.language_model.layers.56.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 704 |
+
"model.language_model.layers.56.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 705 |
+
"model.language_model.layers.56.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 706 |
+
"model.language_model.layers.56.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 707 |
+
"model.language_model.layers.56.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 708 |
+
"model.language_model.layers.56.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 709 |
+
"model.language_model.layers.56.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 710 |
+
"model.language_model.layers.56.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 711 |
+
"model.language_model.layers.56.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 712 |
+
"model.language_model.layers.57.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 713 |
+
"model.language_model.layers.57.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 714 |
+
"model.language_model.layers.57.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 715 |
+
"model.language_model.layers.57.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 716 |
+
"model.language_model.layers.57.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 717 |
+
"model.language_model.layers.57.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 718 |
+
"model.language_model.layers.57.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 719 |
+
"model.language_model.layers.57.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 720 |
+
"model.language_model.layers.57.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 721 |
+
"model.language_model.layers.57.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 722 |
+
"model.language_model.layers.57.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 723 |
+
"model.language_model.layers.57.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 724 |
+
"model.language_model.layers.57.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 725 |
+
"model.language_model.layers.57.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 726 |
+
"model.language_model.layers.58.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 727 |
+
"model.language_model.layers.58.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 728 |
+
"model.language_model.layers.58.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 729 |
+
"model.language_model.layers.58.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 730 |
+
"model.language_model.layers.58.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 731 |
+
"model.language_model.layers.58.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 732 |
+
"model.language_model.layers.58.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 733 |
+
"model.language_model.layers.58.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 734 |
+
"model.language_model.layers.58.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 735 |
+
"model.language_model.layers.58.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 736 |
+
"model.language_model.layers.58.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 737 |
+
"model.language_model.layers.58.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 738 |
+
"model.language_model.layers.58.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 739 |
+
"model.language_model.layers.58.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 740 |
+
"model.language_model.layers.59.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 741 |
+
"model.language_model.layers.59.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 742 |
+
"model.language_model.layers.59.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 743 |
+
"model.language_model.layers.59.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 744 |
+
"model.language_model.layers.59.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 745 |
+
"model.language_model.layers.59.self_attn.k_norm.weight": "model-00011-of-00012.safetensors",
|
| 746 |
+
"model.language_model.layers.59.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
|
| 747 |
+
"model.language_model.layers.59.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
|
| 748 |
+
"model.language_model.layers.59.self_attn.q_norm.weight": "model-00011-of-00012.safetensors",
|
| 749 |
+
"model.language_model.layers.59.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
|
| 750 |
+
"model.language_model.layers.59.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
|
| 751 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 752 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 753 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 754 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 755 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 756 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 757 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 758 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 759 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 760 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 761 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 762 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 763 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 764 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 765 |
+
"model.language_model.layers.60.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 766 |
+
"model.language_model.layers.60.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 767 |
+
"model.language_model.layers.60.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 768 |
+
"model.language_model.layers.60.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 769 |
+
"model.language_model.layers.60.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 770 |
+
"model.language_model.layers.60.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 771 |
+
"model.language_model.layers.60.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 772 |
+
"model.language_model.layers.60.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 773 |
+
"model.language_model.layers.60.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 774 |
+
"model.language_model.layers.60.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 775 |
+
"model.language_model.layers.60.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 776 |
+
"model.language_model.layers.60.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
|
| 777 |
+
"model.language_model.layers.60.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
|
| 778 |
+
"model.language_model.layers.60.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 779 |
+
"model.language_model.layers.61.input_layernorm.weight": "model-00011-of-00012.safetensors",
|
| 780 |
+
"model.language_model.layers.61.linear_attn.A_log": "model-00011-of-00012.safetensors",
|
| 781 |
+
"model.language_model.layers.61.linear_attn.conv1d.weight": "model-00011-of-00012.safetensors",
|
| 782 |
+
"model.language_model.layers.61.linear_attn.dt_bias": "model-00011-of-00012.safetensors",
|
| 783 |
+
"model.language_model.layers.61.linear_attn.in_proj_a.weight": "model-00011-of-00012.safetensors",
|
| 784 |
+
"model.language_model.layers.61.linear_attn.in_proj_b.weight": "model-00011-of-00012.safetensors",
|
| 785 |
+
"model.language_model.layers.61.linear_attn.in_proj_qkv.weight": "model-00011-of-00012.safetensors",
|
| 786 |
+
"model.language_model.layers.61.linear_attn.in_proj_z.weight": "model-00011-of-00012.safetensors",
|
| 787 |
+
"model.language_model.layers.61.linear_attn.norm.weight": "model-00011-of-00012.safetensors",
|
| 788 |
+
"model.language_model.layers.61.linear_attn.out_proj.weight": "model-00011-of-00012.safetensors",
|
| 789 |
+
"model.language_model.layers.61.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
|
| 790 |
+
"model.language_model.layers.61.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
| 791 |
+
"model.language_model.layers.61.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
| 792 |
+
"model.language_model.layers.61.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 793 |
+
"model.language_model.layers.62.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 794 |
+
"model.language_model.layers.62.linear_attn.A_log": "model-00012-of-00012.safetensors",
|
| 795 |
+
"model.language_model.layers.62.linear_attn.conv1d.weight": "model-00012-of-00012.safetensors",
|
| 796 |
+
"model.language_model.layers.62.linear_attn.dt_bias": "model-00012-of-00012.safetensors",
|
| 797 |
+
"model.language_model.layers.62.linear_attn.in_proj_a.weight": "model-00012-of-00012.safetensors",
|
| 798 |
+
"model.language_model.layers.62.linear_attn.in_proj_b.weight": "model-00012-of-00012.safetensors",
|
| 799 |
+
"model.language_model.layers.62.linear_attn.in_proj_qkv.weight": "model-00012-of-00012.safetensors",
|
| 800 |
+
"model.language_model.layers.62.linear_attn.in_proj_z.weight": "model-00012-of-00012.safetensors",
|
| 801 |
+
"model.language_model.layers.62.linear_attn.norm.weight": "model-00012-of-00012.safetensors",
|
| 802 |
+
"model.language_model.layers.62.linear_attn.out_proj.weight": "model-00012-of-00012.safetensors",
|
| 803 |
+
"model.language_model.layers.62.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
| 804 |
+
"model.language_model.layers.62.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
| 805 |
+
"model.language_model.layers.62.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
| 806 |
+
"model.language_model.layers.62.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 807 |
+
"model.language_model.layers.63.input_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 808 |
+
"model.language_model.layers.63.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
|
| 809 |
+
"model.language_model.layers.63.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
|
| 810 |
+
"model.language_model.layers.63.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
|
| 811 |
+
"model.language_model.layers.63.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
|
| 812 |
+
"model.language_model.layers.63.self_attn.k_norm.weight": "model-00012-of-00012.safetensors",
|
| 813 |
+
"model.language_model.layers.63.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
|
| 814 |
+
"model.language_model.layers.63.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
|
| 815 |
+
"model.language_model.layers.63.self_attn.q_norm.weight": "model-00012-of-00012.safetensors",
|
| 816 |
+
"model.language_model.layers.63.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
|
| 817 |
+
"model.language_model.layers.63.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
|
| 818 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 819 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 820 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 821 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 822 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 823 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00003-of-00012.safetensors",
|
| 824 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
|
| 825 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
|
| 826 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00003-of-00012.safetensors",
|
| 827 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
|
| 828 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
|
| 829 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 830 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 831 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 832 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 833 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 834 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 835 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 836 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 837 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 838 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 839 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 840 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
|
| 841 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
|
| 842 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 843 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors",
|
| 844 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00003-of-00012.safetensors",
|
| 845 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00003-of-00012.safetensors",
|
| 846 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00003-of-00012.safetensors",
|
| 847 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00003-of-00012.safetensors",
|
| 848 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00003-of-00012.safetensors",
|
| 849 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00003-of-00012.safetensors",
|
| 850 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00003-of-00012.safetensors",
|
| 851 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00003-of-00012.safetensors",
|
| 852 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00003-of-00012.safetensors",
|
| 853 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
|
| 854 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
|
| 855 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
|
| 856 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
|
| 857 |
+
"model.language_model.norm.weight": "model-00012-of-00012.safetensors"
|
| 858 |
+
}
|
| 859 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"local_files_only": true,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null,
|
| 29 |
+
"video_token": "<|video_pad|>",
|
| 30 |
+
"vision_bos_token": "<|vision_start|>",
|
| 31 |
+
"vision_eos_token": "<|vision_end|>"
|
| 32 |
+
}
|