Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- IMATRIX_CACHE_S32.npz +3 -0
- LICENSE.txt +177 -0
- MODEL_SHA256SUMS.txt +18 -0
- NOTICE.txt +4 -0
- PROVENANCE.json +37 -0
- README.md +111 -0
- chat_template.jinja +154 -0
- config.json +828 -0
- docs/arc-challenge-10.json +82 -0
- docs/hellaswag-10.json +92 -0
- generation_config.json +12 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- oq_imatrix_report.json +591 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
IMATRIX_CACHE_S32.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3de3f9aa22f43a6ecf1b0add445b425a60211ebd415ad7ce03e048a8f05b4cd7
|
| 3 |
+
size 12225698
|
LICENSE.txt
ADDED
|
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Apache License
|
| 2 |
+
Version 2.0, January 2004
|
| 3 |
+
http://www.apache.org/licenses/
|
| 4 |
+
|
| 5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 6 |
+
|
| 7 |
+
1. Definitions.
|
| 8 |
+
|
| 9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 11 |
+
|
| 12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 13 |
+
the copyright owner that is granting the License.
|
| 14 |
+
|
| 15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 16 |
+
other entities that control, are controlled by, or are under common
|
| 17 |
+
control with that entity. For the purposes of this definition,
|
| 18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 19 |
+
direction or management of such entity, whether by contract or
|
| 20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 22 |
+
|
| 23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 24 |
+
exercising permissions granted by this License.
|
| 25 |
+
|
| 26 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 27 |
+
including but not limited to software source code, documentation
|
| 28 |
+
source, and configuration files.
|
| 29 |
+
|
| 30 |
+
"Object" form shall mean any form resulting from mechanical
|
| 31 |
+
transformation or translation of a Source form, including but
|
| 32 |
+
not limited to compiled object code, generated documentation,
|
| 33 |
+
and conversions to other media types.
|
| 34 |
+
|
| 35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 36 |
+
Object form, made available under the License, as indicated by a
|
| 37 |
+
copyright notice that is included in or attached to the work
|
| 38 |
+
(an example is provided in the Appendix below).
|
| 39 |
+
|
| 40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 41 |
+
form, that is based on (or derived from) the Work and for which the
|
| 42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 44 |
+
of this License, Derivative Works shall not include works that remain
|
| 45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 46 |
+
the Work and Derivative Works thereof.
|
| 47 |
+
|
| 48 |
+
"Contribution" shall mean any work of authorship, including
|
| 49 |
+
the original version of the Work and any modifications or additions
|
| 50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 54 |
+
means any form of electronic, verbal, or written communication sent
|
| 55 |
+
to the Licensor or its representatives, including but not limited to
|
| 56 |
+
communication on electronic mailing lists, source code control systems,
|
| 57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 59 |
+
excluding communication that is conspicuously marked or otherwise
|
| 60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 61 |
+
|
| 62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 64 |
+
subsequently incorporated within the Work.
|
| 65 |
+
|
| 66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 71 |
+
Work and such Derivative Works in Source or Object form.
|
| 72 |
+
|
| 73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 76 |
+
(except as stated in this section) patent license to make, have made,
|
| 77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 78 |
+
where such license applies only to those patent claims licensable
|
| 79 |
+
by such Contributor that are necessarily infringed by their
|
| 80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 82 |
+
institute patent litigation against any entity (including a
|
| 83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 84 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 85 |
+
or contributory patent infringement, then any patent licenses
|
| 86 |
+
granted to You under this License for that Work shall terminate
|
| 87 |
+
as of the date such litigation is filed.
|
| 88 |
+
|
| 89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 90 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 91 |
+
modifications, and in Source or Object form, provided that You
|
| 92 |
+
meet the following conditions:
|
| 93 |
+
|
| 94 |
+
(a) You must give any other recipients of the Work or
|
| 95 |
+
Derivative Works a copy of this License; and
|
| 96 |
+
|
| 97 |
+
(b) You must cause any modified files to carry prominent notices
|
| 98 |
+
stating that You changed the files; and
|
| 99 |
+
|
| 100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 101 |
+
that You distribute, all copyright, patent, trademark, and
|
| 102 |
+
attribution notices from the Source form of the Work,
|
| 103 |
+
excluding those notices that do not pertain to any part of
|
| 104 |
+
the Derivative Works; and
|
| 105 |
+
|
| 106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 107 |
+
distribution, then any Derivative Works that You distribute must
|
| 108 |
+
include a readable copy of the attribution notices contained
|
| 109 |
+
within such NOTICE file, excluding those notices that do not
|
| 110 |
+
pertain to any part of the Derivative Works, in at least one
|
| 111 |
+
of the following places: within a NOTICE text file distributed
|
| 112 |
+
as part of the Derivative Works; within the Source form or
|
| 113 |
+
documentation, if provided along with the Derivative Works; or,
|
| 114 |
+
within a display generated by the Derivative Works, if and
|
| 115 |
+
wherever such third-party notices normally appear. The contents
|
| 116 |
+
of the NOTICE file are for informational purposes only and
|
| 117 |
+
do not modify the License. You may add Your own attribution
|
| 118 |
+
notices within Derivative Works that You distribute, alongside
|
| 119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 120 |
+
that such additional attribution notices cannot be construed
|
| 121 |
+
as modifying the License.
|
| 122 |
+
|
| 123 |
+
You may add Your own copyright statement to Your modifications and
|
| 124 |
+
may provide additional or different license terms and conditions
|
| 125 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 126 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 127 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 128 |
+
the conditions stated in this License.
|
| 129 |
+
|
| 130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 132 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 133 |
+
this License, without any additional terms or conditions.
|
| 134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 135 |
+
the terms of any separate license agreement you may have executed
|
| 136 |
+
with Licensor regarding such Contributions.
|
| 137 |
+
|
| 138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 140 |
+
except as required for reasonable and customary use in describing the
|
| 141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 142 |
+
|
| 143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 144 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 147 |
+
implied, including, without limitation, any warranties or conditions
|
| 148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 150 |
+
appropriateness of using or redistributing the Work and assume any
|
| 151 |
+
risks associated with Your exercise of permissions under this License.
|
| 152 |
+
|
| 153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 154 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 155 |
+
unless required by applicable law (such as deliberate and grossly
|
| 156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 157 |
+
liable to You for damages, including any direct, indirect, special,
|
| 158 |
+
incidental, or consequential damages of any character arising as a
|
| 159 |
+
result of this License or out of the use or inability to use the
|
| 160 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 161 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 162 |
+
other commercial damages or losses), even if such Contributor
|
| 163 |
+
has been advised of the possibility of such damages.
|
| 164 |
+
|
| 165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 168 |
+
or other liability obligations and/or rights consistent with this
|
| 169 |
+
License. However, in accepting such obligations, You may act only
|
| 170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 171 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 172 |
+
defend, and hold each Contributor harmless for any liability
|
| 173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 174 |
+
of your accepting any such warranty or additional liability.
|
| 175 |
+
|
| 176 |
+
END OF TERMS AND CONDITIONS
|
| 177 |
+
|
MODEL_SHA256SUMS.txt
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
7689f5955a43d3637b86bea2b106d0624823cbe9f6ccbc4b34df041b038c909b README.md
|
| 2 |
+
33b32313711f58dd0f49d09fa69b47ba74d3a4a42ebbc8fcb09962877363d580 PROVENANCE.json
|
| 3 |
+
69849221bfb90053de2134ef5e6d540287b4b98062326492f1f96f5da685524b LICENSE.txt
|
| 4 |
+
cef33f95425f9802de78b7b22db0faca84d2216661432a9afcf9620949c21f7e NOTICE.txt
|
| 5 |
+
3de3f9aa22f43a6ecf1b0add445b425a60211ebd415ad7ce03e048a8f05b4cd7 IMATRIX_CACHE_S32.npz
|
| 6 |
+
e84f32a23fdda27689f868aa4a1a5621f41133e51a48d7f3efcbea2839574259 chat_template.jinja
|
| 7 |
+
5421b1e501f507094a056077b1e14911479638ecbf885b0031ce2385d6590486 config.json
|
| 8 |
+
e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e generation_config.json
|
| 9 |
+
4849622d9f159a927df93d1c45b21ab7054c4c5a70dec850808fcbac383c1da9 model-00001-of-00004.safetensors
|
| 10 |
+
e49ca0024c0d8e9c7c23f6a71ebef096515b36a7e97136399ebf47e258e16ecf model-00002-of-00004.safetensors
|
| 11 |
+
080e92e3041fcedd253a582d42b107b06f283870d9131520f45bf240f00f5ba6 model-00003-of-00004.safetensors
|
| 12 |
+
4f7ec4edcbcd98313481810ed1b0c5c3aa88d6c5c60bb75bebef84ba48910b2a model-00004-of-00004.safetensors
|
| 13 |
+
bbf5b3340d8c64926bc1eb9e66f9781f50450d38129ee820d52478753308e42d model.safetensors.index.json
|
| 14 |
+
573dac22c7059d65f846759663e45dcfb95dc92438aabf8c3ffc86c0e35aa8ee oq_imatrix_report.json
|
| 15 |
+
06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 tokenizer.json
|
| 16 |
+
95c557768e6b88a7128befc7bfd3c7de50e5d51af9b8b33a9f4dee0e04f99679 tokenizer_config.json
|
| 17 |
+
6289a92c805c39b74cddb80fa1df632de74b5b1cabae292d1efd154e3f697a9b docs/hellaswag-10.json
|
| 18 |
+
13e9c2192897a60f5b78c3b225e5c5ed10a398149b07fc01559838e386196e3d docs/arc-challenge-10.json
|
NOTICE.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This software is copyright 2026-present Prism ML, Inc. It is available under the Apache 2.0 license.
|
| 2 |
+
If you publicly deploy or redistribute this software, we would appreciate attribution such as: "Created using Bonsai by Prism ML."
|
| 3 |
+
|
| 4 |
+
This software is built from Qwen3.6-27B, Copyright 2026 Alibaba Cloud, which is available under the Apache 2.0 License: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE
|
PROVENANCE.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"artifact_id": "Bonsai-27B-oQ4e-S32-Smoke",
|
| 3 |
+
"status": "experimental_calibration_smoke_not_quality_release",
|
| 4 |
+
"producer": "Technologies Brewster Jennings du Canada",
|
| 5 |
+
"source": {
|
| 6 |
+
"derived_baseline": "TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired",
|
| 7 |
+
"upstream_repository": "prism-ml/Bonsai-27B-gguf",
|
| 8 |
+
"upstream_revision": "0cf7e3d21581b169b4df1de8bf01316000e2fbb7",
|
| 9 |
+
"upstream_file": "Bonsai-27B-F16.gguf",
|
| 10 |
+
"upstream_file_sha256": "d4a381a6d07131c34af888607bdbda49fc885c97673a0d22aa3e0f0284bba566",
|
| 11 |
+
"license": "Apache-2.0"
|
| 12 |
+
},
|
| 13 |
+
"quantization": {
|
| 14 |
+
"method": "oQe enhanced streaming quantization",
|
| 15 |
+
"oq_level": 4,
|
| 16 |
+
"default_bits": 4,
|
| 17 |
+
"effective_bits_per_weight": 4.70,
|
| 18 |
+
"group_size": 64,
|
| 19 |
+
"embedding_bits": 8,
|
| 20 |
+
"sensitivity_selected_modules": 22,
|
| 21 |
+
"sensitivity_selected_bits": 5,
|
| 22 |
+
"imatrix_samples": 32,
|
| 23 |
+
"imatrix_sequence_length": 512,
|
| 24 |
+
"sensitivity_samples": 2,
|
| 25 |
+
"sensitivity_sequence_length": 64,
|
| 26 |
+
"calibration_dataset": "oqe_code_multilingual",
|
| 27 |
+
"imatrix_entries": 496
|
| 28 |
+
},
|
| 29 |
+
"validation": {
|
| 30 |
+
"runtime_loaded": true,
|
| 31 |
+
"behavioral_smoke_passed": true,
|
| 32 |
+
"hellaswag_fixed_10": 6,
|
| 33 |
+
"arc_challenge_fixed_10": 6,
|
| 34 |
+
"quality_release_eligible": false,
|
| 35 |
+
"reason": "The bounded sensitivity stage and 10-question screens are pipeline evidence only."
|
| 36 |
+
}
|
| 37 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- mlx
|
| 7 |
+
- safetensors
|
| 8 |
+
- bonsai
|
| 9 |
+
- oqe
|
| 10 |
+
- calibration-smoke
|
| 11 |
+
- experimental
|
| 12 |
+
- not-for-production
|
| 13 |
+
pipeline_tag: text-generation
|
| 14 |
+
library_name: mlx
|
| 15 |
+
base_model:
|
| 16 |
+
- TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# Bonsai 27B oQ4e S32 Calibration Smoke
|
| 20 |
+
|
| 21 |
+
> **Experimental calibration artifact. Not a quality release. Do not use this
|
| 22 |
+
> model to judge Bonsai quality or as a production checkpoint.**
|
| 23 |
+
|
| 24 |
+
This repository preserves a bounded oQe-enhanced 4-bit MLX artifact that
|
| 25 |
+
loaded and generated normally on a 32 GB Apple Silicon host. Its purpose is
|
| 26 |
+
reproducible pipeline evidence and archival storage, not a claim that it
|
| 27 |
+
outperforms another Bonsai checkpoint.
|
| 28 |
+
|
| 29 |
+
## What this proves
|
| 30 |
+
|
| 31 |
+
- An oQe-enhanced 4-bit MLX artifact was produced from the public,
|
| 32 |
+
config-repaired BF16 conversion baseline.
|
| 33 |
+
- Structural and load checks passed.
|
| 34 |
+
- The 32-sample imatrix collection completed with 496 entries.
|
| 35 |
+
- The allocation uses an effective 4.70 bits per weight: embeddings at 8-bit
|
| 36 |
+
and 22 sensitivity-selected modules at 5-bit.
|
| 37 |
+
- The artifact produced coherent reasoning in the bounded behavioral smoke.
|
| 38 |
+
- On fixed 10-question screens it scored HellaSwag 6/10 and ARC-Challenge
|
| 39 |
+
6/10.
|
| 40 |
+
|
| 41 |
+
## What this does not prove
|
| 42 |
+
|
| 43 |
+
The sensitivity stage was intentionally minimal: 2 samples of 64 tokens. The
|
| 44 |
+
10-question screens are too small for a quality ranking. This artifact has not
|
| 45 |
+
passed the predeclared 100-question evaluations or a quality-sized sensitivity
|
| 46 |
+
pass, and it did not beat the smaller oQ2e smoke artifact on the tiny screen.
|
| 47 |
+
|
| 48 |
+
Do not present it as a production model, a quality release, or evidence that
|
| 49 |
+
oQ4e is superior to ordinary Q4, oQ2e, Q1, or another quantization method.
|
| 50 |
+
|
| 51 |
+
## Reproduction parameters
|
| 52 |
+
|
| 53 |
+
| Setting | Value |
|
| 54 |
+
| --- | ---: |
|
| 55 |
+
| oQ level | 4 |
|
| 56 |
+
| effective allocation | 4.70 bpw |
|
| 57 |
+
| default quantization | affine 4-bit, group size 64 |
|
| 58 |
+
| embedding quantization | affine 8-bit, group size 64 |
|
| 59 |
+
| sensitivity-selected modules | 22 at affine 5-bit |
|
| 60 |
+
| imatrix samples | 32 |
|
| 61 |
+
| imatrix sequence length | 512 |
|
| 62 |
+
| sensitivity samples | 2 |
|
| 63 |
+
| sensitivity sequence length | 64 |
|
| 64 |
+
| calibration dataset | `oqe_code_multilingual` |
|
| 65 |
+
| imatrix entries | 496 |
|
| 66 |
+
|
| 67 |
+
`oq_imatrix_report.json`, `PROVENANCE.json`, and the included
|
| 68 |
+
`IMATRIX_CACHE_S32.npz` preserve the emitted artifact and calibration
|
| 69 |
+
evidence. The NPZ contains aggregate activation statistics, not raw
|
| 70 |
+
calibration prompts, and is not needed to run the model.
|
| 71 |
+
|
| 72 |
+
## Bounded evaluation
|
| 73 |
+
|
| 74 |
+
The fixed screens used deterministic, thinking-disabled decoding and the same
|
| 75 |
+
letter parser as the earlier oQ2e smoke:
|
| 76 |
+
|
| 77 |
+
| Benchmark | Score | Peak generation memory |
|
| 78 |
+
| --- | ---: | ---: |
|
| 79 |
+
| HellaSwag, fixed 10 | 6/10 | 15.70 GB |
|
| 80 |
+
| ARC-Challenge, fixed 10 | 6/10 | 15.42 GB |
|
| 81 |
+
|
| 82 |
+
The raw records are retained under `docs/`. These are pipeline screens, not
|
| 83 |
+
statistically useful benchmark claims.
|
| 84 |
+
|
| 85 |
+
## Provenance
|
| 86 |
+
|
| 87 |
+
- Derived baseline:
|
| 88 |
+
[TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired](https://huggingface.co/TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired)
|
| 89 |
+
- Original source:
|
| 90 |
+
[prism-ml/Bonsai-27B-gguf](https://huggingface.co/prism-ml/Bonsai-27B-gguf)
|
| 91 |
+
- Source revision used for conversion:
|
| 92 |
+
`0cf7e3d21581b169b4df1de8bf01316000e2fbb7`
|
| 93 |
+
- Original source file:
|
| 94 |
+
`Bonsai-27B-F16.gguf`
|
| 95 |
+
- Original source file SHA-256:
|
| 96 |
+
`d4a381a6d07131c34af888607bdbda49fc885c97673a0d22aa3e0f0284bba566`
|
| 97 |
+
- Output hashes: `MODEL_SHA256SUMS.txt`
|
| 98 |
+
|
| 99 |
+
The project retains the upstream Apache-2.0 `LICENSE.txt` and `NOTICE.txt`.
|
| 100 |
+
|
| 101 |
+
## Runtime
|
| 102 |
+
|
| 103 |
+
The artifact uses heterogeneous MLX quantization metadata. It was validated
|
| 104 |
+
with the experimental oMLX/oQe path used to create it. Compatibility with
|
| 105 |
+
stock MLX-LM or other runtimes is not claimed.
|
| 106 |
+
|
| 107 |
+
## Attribution
|
| 108 |
+
|
| 109 |
+
Created by Technologies Brewster Jennings du Canada for the Bonsai MLX
|
| 110 |
+
quantization experiment. Created using Bonsai by Prism ML, derived from
|
| 111 |
+
Qwen3.6-27B.
|
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 +1,828 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
248046,
|
| 7 |
+
248044
|
| 8 |
+
],
|
| 9 |
+
"image_token_id": 248056,
|
| 10 |
+
"language_model_only": false,
|
| 11 |
+
"model_type": "qwen3_5",
|
| 12 |
+
"text_config": {
|
| 13 |
+
"attention_bias": false,
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"attn_output_gate": true,
|
| 16 |
+
"bos_token_id": 248044,
|
| 17 |
+
"dtype": "bfloat16",
|
| 18 |
+
"eos_token_id": 248044,
|
| 19 |
+
"full_attention_interval": 4,
|
| 20 |
+
"head_dim": 256,
|
| 21 |
+
"hidden_act": "silu",
|
| 22 |
+
"hidden_size": 5120,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 17408,
|
| 25 |
+
"layer_types": [
|
| 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 |
+
"linear_attention",
|
| 83 |
+
"linear_attention",
|
| 84 |
+
"linear_attention",
|
| 85 |
+
"full_attention",
|
| 86 |
+
"linear_attention",
|
| 87 |
+
"linear_attention",
|
| 88 |
+
"linear_attention",
|
| 89 |
+
"full_attention"
|
| 90 |
+
],
|
| 91 |
+
"linear_conv_kernel_dim": 4,
|
| 92 |
+
"linear_key_head_dim": 128,
|
| 93 |
+
"linear_num_key_heads": 16,
|
| 94 |
+
"linear_num_value_heads": 48,
|
| 95 |
+
"linear_value_head_dim": 128,
|
| 96 |
+
"mamba_ssm_dtype": "float32",
|
| 97 |
+
"max_position_embeddings": 262144,
|
| 98 |
+
"model_type": "qwen3_5_text",
|
| 99 |
+
"mtp_num_hidden_layers": 0,
|
| 100 |
+
"mtp_use_dedicated_embeddings": false,
|
| 101 |
+
"num_attention_heads": 24,
|
| 102 |
+
"num_hidden_layers": 64,
|
| 103 |
+
"num_key_value_heads": 4,
|
| 104 |
+
"output_gate_type": "swish",
|
| 105 |
+
"pad_token_id": null,
|
| 106 |
+
"partial_rotary_factor": 0.25,
|
| 107 |
+
"rms_norm_eps": 1e-06,
|
| 108 |
+
"rope_parameters": {
|
| 109 |
+
"mrope_interleaved": true,
|
| 110 |
+
"mrope_section": [
|
| 111 |
+
11,
|
| 112 |
+
11,
|
| 113 |
+
10
|
| 114 |
+
],
|
| 115 |
+
"partial_rotary_factor": 0.25,
|
| 116 |
+
"rope_theta": 10000000,
|
| 117 |
+
"type": "default"
|
| 118 |
+
},
|
| 119 |
+
"tie_word_embeddings": false,
|
| 120 |
+
"use_cache": true,
|
| 121 |
+
"vocab_size": 248320
|
| 122 |
+
},
|
| 123 |
+
"tie_word_embeddings": false,
|
| 124 |
+
"transformers_version": "4.57.1",
|
| 125 |
+
"video_token_id": 248057,
|
| 126 |
+
"vision_end_token_id": 248054,
|
| 127 |
+
"vision_start_token_id": 248053,
|
| 128 |
+
"quantization": {
|
| 129 |
+
"group_size": 64,
|
| 130 |
+
"bits": 4,
|
| 131 |
+
"mode": "affine",
|
| 132 |
+
"language_model.model.embed_tokens": {
|
| 133 |
+
"bits": 8,
|
| 134 |
+
"group_size": 64,
|
| 135 |
+
"mode": "affine"
|
| 136 |
+
},
|
| 137 |
+
"language_model.model.layers.0.linear_attn.in_proj_a": {
|
| 138 |
+
"bits": 5,
|
| 139 |
+
"group_size": 64,
|
| 140 |
+
"mode": "affine"
|
| 141 |
+
},
|
| 142 |
+
"language_model.model.layers.0.linear_attn.in_proj_b": {
|
| 143 |
+
"bits": 5,
|
| 144 |
+
"group_size": 64,
|
| 145 |
+
"mode": "affine"
|
| 146 |
+
},
|
| 147 |
+
"language_model.model.layers.0.linear_attn.in_proj_qkv": {
|
| 148 |
+
"bits": 5,
|
| 149 |
+
"group_size": 64,
|
| 150 |
+
"mode": "affine"
|
| 151 |
+
},
|
| 152 |
+
"language_model.model.layers.0.linear_attn.in_proj_z": {
|
| 153 |
+
"bits": 5,
|
| 154 |
+
"group_size": 64,
|
| 155 |
+
"mode": "affine"
|
| 156 |
+
},
|
| 157 |
+
"language_model.model.layers.0.linear_attn.out_proj": {
|
| 158 |
+
"bits": 5,
|
| 159 |
+
"group_size": 64,
|
| 160 |
+
"mode": "affine"
|
| 161 |
+
},
|
| 162 |
+
"language_model.model.layers.1.linear_attn.in_proj_a": {
|
| 163 |
+
"bits": 5,
|
| 164 |
+
"group_size": 64,
|
| 165 |
+
"mode": "affine"
|
| 166 |
+
},
|
| 167 |
+
"language_model.model.layers.1.linear_attn.in_proj_b": {
|
| 168 |
+
"bits": 5,
|
| 169 |
+
"group_size": 64,
|
| 170 |
+
"mode": "affine"
|
| 171 |
+
},
|
| 172 |
+
"language_model.model.layers.1.linear_attn.in_proj_qkv": {
|
| 173 |
+
"bits": 5,
|
| 174 |
+
"group_size": 64,
|
| 175 |
+
"mode": "affine"
|
| 176 |
+
},
|
| 177 |
+
"language_model.model.layers.1.linear_attn.in_proj_z": {
|
| 178 |
+
"bits": 5,
|
| 179 |
+
"group_size": 64,
|
| 180 |
+
"mode": "affine"
|
| 181 |
+
},
|
| 182 |
+
"language_model.model.layers.1.linear_attn.out_proj": {
|
| 183 |
+
"bits": 5,
|
| 184 |
+
"group_size": 64,
|
| 185 |
+
"mode": "affine"
|
| 186 |
+
},
|
| 187 |
+
"language_model.model.layers.2.linear_attn.in_proj_a": {
|
| 188 |
+
"bits": 5,
|
| 189 |
+
"group_size": 64,
|
| 190 |
+
"mode": "affine"
|
| 191 |
+
},
|
| 192 |
+
"language_model.model.layers.2.linear_attn.in_proj_b": {
|
| 193 |
+
"bits": 5,
|
| 194 |
+
"group_size": 64,
|
| 195 |
+
"mode": "affine"
|
| 196 |
+
},
|
| 197 |
+
"language_model.model.layers.2.linear_attn.in_proj_z": {
|
| 198 |
+
"bits": 5,
|
| 199 |
+
"group_size": 64,
|
| 200 |
+
"mode": "affine"
|
| 201 |
+
},
|
| 202 |
+
"language_model.model.layers.2.linear_attn.out_proj": {
|
| 203 |
+
"bits": 5,
|
| 204 |
+
"group_size": 64,
|
| 205 |
+
"mode": "affine"
|
| 206 |
+
},
|
| 207 |
+
"language_model.model.layers.3.self_attn.k_proj": {
|
| 208 |
+
"bits": 5,
|
| 209 |
+
"group_size": 64,
|
| 210 |
+
"mode": "affine"
|
| 211 |
+
},
|
| 212 |
+
"language_model.model.layers.10.linear_attn.in_proj_a": {
|
| 213 |
+
"bits": 5,
|
| 214 |
+
"group_size": 64,
|
| 215 |
+
"mode": "affine"
|
| 216 |
+
},
|
| 217 |
+
"language_model.model.layers.10.linear_attn.in_proj_b": {
|
| 218 |
+
"bits": 5,
|
| 219 |
+
"group_size": 64,
|
| 220 |
+
"mode": "affine"
|
| 221 |
+
},
|
| 222 |
+
"language_model.model.layers.10.linear_attn.out_proj": {
|
| 223 |
+
"bits": 5,
|
| 224 |
+
"group_size": 64,
|
| 225 |
+
"mode": "affine"
|
| 226 |
+
},
|
| 227 |
+
"language_model.model.layers.4.linear_attn.in_proj_a": {
|
| 228 |
+
"bits": 5,
|
| 229 |
+
"group_size": 64,
|
| 230 |
+
"mode": "affine"
|
| 231 |
+
},
|
| 232 |
+
"language_model.model.layers.4.linear_attn.in_proj_b": {
|
| 233 |
+
"bits": 5,
|
| 234 |
+
"group_size": 64,
|
| 235 |
+
"mode": "affine"
|
| 236 |
+
},
|
| 237 |
+
"language_model.model.layers.4.linear_attn.out_proj": {
|
| 238 |
+
"bits": 5,
|
| 239 |
+
"group_size": 64,
|
| 240 |
+
"mode": "affine"
|
| 241 |
+
},
|
| 242 |
+
"language_model.model.layers.5.linear_attn.in_proj_a": {
|
| 243 |
+
"bits": 5,
|
| 244 |
+
"group_size": 64,
|
| 245 |
+
"mode": "affine"
|
| 246 |
+
},
|
| 247 |
+
"language_model.model.layers.5.linear_attn.in_proj_b": {
|
| 248 |
+
"bits": 5,
|
| 249 |
+
"group_size": 64,
|
| 250 |
+
"mode": "affine"
|
| 251 |
+
},
|
| 252 |
+
"language_model.model.layers.5.linear_attn.out_proj": {
|
| 253 |
+
"bits": 5,
|
| 254 |
+
"group_size": 64,
|
| 255 |
+
"mode": "affine"
|
| 256 |
+
},
|
| 257 |
+
"language_model.model.layers.6.linear_attn.in_proj_a": {
|
| 258 |
+
"bits": 5,
|
| 259 |
+
"group_size": 64,
|
| 260 |
+
"mode": "affine"
|
| 261 |
+
},
|
| 262 |
+
"language_model.model.layers.6.linear_attn.in_proj_b": {
|
| 263 |
+
"bits": 5,
|
| 264 |
+
"group_size": 64,
|
| 265 |
+
"mode": "affine"
|
| 266 |
+
},
|
| 267 |
+
"language_model.model.layers.6.linear_attn.out_proj": {
|
| 268 |
+
"bits": 5,
|
| 269 |
+
"group_size": 64,
|
| 270 |
+
"mode": "affine"
|
| 271 |
+
},
|
| 272 |
+
"language_model.model.layers.8.linear_attn.out_proj": {
|
| 273 |
+
"bits": 5,
|
| 274 |
+
"group_size": 64,
|
| 275 |
+
"mode": "affine"
|
| 276 |
+
},
|
| 277 |
+
"language_model.model.layers.9.linear_attn.out_proj": {
|
| 278 |
+
"bits": 5,
|
| 279 |
+
"group_size": 64,
|
| 280 |
+
"mode": "affine"
|
| 281 |
+
},
|
| 282 |
+
"language_model.model.layers.12.linear_attn.out_proj": {
|
| 283 |
+
"bits": 5,
|
| 284 |
+
"group_size": 64,
|
| 285 |
+
"mode": "affine"
|
| 286 |
+
},
|
| 287 |
+
"language_model.model.layers.13.linear_attn.out_proj": {
|
| 288 |
+
"bits": 5,
|
| 289 |
+
"group_size": 64,
|
| 290 |
+
"mode": "affine"
|
| 291 |
+
},
|
| 292 |
+
"language_model.model.layers.14.linear_attn.out_proj": {
|
| 293 |
+
"bits": 5,
|
| 294 |
+
"group_size": 64,
|
| 295 |
+
"mode": "affine"
|
| 296 |
+
},
|
| 297 |
+
"language_model.model.layers.16.linear_attn.out_proj": {
|
| 298 |
+
"bits": 5,
|
| 299 |
+
"group_size": 64,
|
| 300 |
+
"mode": "affine"
|
| 301 |
+
},
|
| 302 |
+
"language_model.model.layers.17.linear_attn.out_proj": {
|
| 303 |
+
"bits": 5,
|
| 304 |
+
"group_size": 64,
|
| 305 |
+
"mode": "affine"
|
| 306 |
+
},
|
| 307 |
+
"language_model.model.layers.18.linear_attn.out_proj": {
|
| 308 |
+
"bits": 5,
|
| 309 |
+
"group_size": 64,
|
| 310 |
+
"mode": "affine"
|
| 311 |
+
},
|
| 312 |
+
"language_model.model.layers.20.linear_attn.out_proj": {
|
| 313 |
+
"bits": 5,
|
| 314 |
+
"group_size": 64,
|
| 315 |
+
"mode": "affine"
|
| 316 |
+
},
|
| 317 |
+
"language_model.model.layers.21.linear_attn.out_proj": {
|
| 318 |
+
"bits": 5,
|
| 319 |
+
"group_size": 64,
|
| 320 |
+
"mode": "affine"
|
| 321 |
+
},
|
| 322 |
+
"language_model.model.layers.22.linear_attn.out_proj": {
|
| 323 |
+
"bits": 5,
|
| 324 |
+
"group_size": 64,
|
| 325 |
+
"mode": "affine"
|
| 326 |
+
},
|
| 327 |
+
"language_model.model.layers.24.linear_attn.out_proj": {
|
| 328 |
+
"bits": 5,
|
| 329 |
+
"group_size": 64,
|
| 330 |
+
"mode": "affine"
|
| 331 |
+
},
|
| 332 |
+
"language_model.model.layers.25.linear_attn.out_proj": {
|
| 333 |
+
"bits": 5,
|
| 334 |
+
"group_size": 64,
|
| 335 |
+
"mode": "affine"
|
| 336 |
+
},
|
| 337 |
+
"language_model.model.layers.26.linear_attn.out_proj": {
|
| 338 |
+
"bits": 5,
|
| 339 |
+
"group_size": 64,
|
| 340 |
+
"mode": "affine"
|
| 341 |
+
},
|
| 342 |
+
"language_model.model.layers.28.linear_attn.out_proj": {
|
| 343 |
+
"bits": 5,
|
| 344 |
+
"group_size": 64,
|
| 345 |
+
"mode": "affine"
|
| 346 |
+
},
|
| 347 |
+
"language_model.model.layers.29.linear_attn.out_proj": {
|
| 348 |
+
"bits": 5,
|
| 349 |
+
"group_size": 64,
|
| 350 |
+
"mode": "affine"
|
| 351 |
+
},
|
| 352 |
+
"language_model.model.layers.30.linear_attn.out_proj": {
|
| 353 |
+
"bits": 5,
|
| 354 |
+
"group_size": 64,
|
| 355 |
+
"mode": "affine"
|
| 356 |
+
},
|
| 357 |
+
"language_model.model.layers.32.linear_attn.out_proj": {
|
| 358 |
+
"bits": 5,
|
| 359 |
+
"group_size": 64,
|
| 360 |
+
"mode": "affine"
|
| 361 |
+
},
|
| 362 |
+
"language_model.model.layers.33.linear_attn.out_proj": {
|
| 363 |
+
"bits": 5,
|
| 364 |
+
"group_size": 64,
|
| 365 |
+
"mode": "affine"
|
| 366 |
+
},
|
| 367 |
+
"language_model.model.layers.34.linear_attn.out_proj": {
|
| 368 |
+
"bits": 5,
|
| 369 |
+
"group_size": 64,
|
| 370 |
+
"mode": "affine"
|
| 371 |
+
},
|
| 372 |
+
"language_model.model.layers.36.linear_attn.out_proj": {
|
| 373 |
+
"bits": 5,
|
| 374 |
+
"group_size": 64,
|
| 375 |
+
"mode": "affine"
|
| 376 |
+
},
|
| 377 |
+
"language_model.model.layers.37.linear_attn.out_proj": {
|
| 378 |
+
"bits": 5,
|
| 379 |
+
"group_size": 64,
|
| 380 |
+
"mode": "affine"
|
| 381 |
+
},
|
| 382 |
+
"language_model.model.layers.38.linear_attn.out_proj": {
|
| 383 |
+
"bits": 5,
|
| 384 |
+
"group_size": 64,
|
| 385 |
+
"mode": "affine"
|
| 386 |
+
},
|
| 387 |
+
"language_model.model.layers.40.linear_attn.out_proj": {
|
| 388 |
+
"bits": 5,
|
| 389 |
+
"group_size": 64,
|
| 390 |
+
"mode": "affine"
|
| 391 |
+
},
|
| 392 |
+
"language_model.model.layers.41.linear_attn.out_proj": {
|
| 393 |
+
"bits": 5,
|
| 394 |
+
"group_size": 64,
|
| 395 |
+
"mode": "affine"
|
| 396 |
+
},
|
| 397 |
+
"language_model.model.layers.42.linear_attn.out_proj": {
|
| 398 |
+
"bits": 5,
|
| 399 |
+
"group_size": 64,
|
| 400 |
+
"mode": "affine"
|
| 401 |
+
},
|
| 402 |
+
"language_model.model.layers.44.linear_attn.out_proj": {
|
| 403 |
+
"bits": 5,
|
| 404 |
+
"group_size": 64,
|
| 405 |
+
"mode": "affine"
|
| 406 |
+
},
|
| 407 |
+
"language_model.model.layers.45.linear_attn.out_proj": {
|
| 408 |
+
"bits": 5,
|
| 409 |
+
"group_size": 64,
|
| 410 |
+
"mode": "affine"
|
| 411 |
+
},
|
| 412 |
+
"language_model.model.layers.46.linear_attn.out_proj": {
|
| 413 |
+
"bits": 5,
|
| 414 |
+
"group_size": 64,
|
| 415 |
+
"mode": "affine"
|
| 416 |
+
},
|
| 417 |
+
"language_model.model.layers.48.linear_attn.out_proj": {
|
| 418 |
+
"bits": 5,
|
| 419 |
+
"group_size": 64,
|
| 420 |
+
"mode": "affine"
|
| 421 |
+
},
|
| 422 |
+
"language_model.model.layers.49.linear_attn.out_proj": {
|
| 423 |
+
"bits": 5,
|
| 424 |
+
"group_size": 64,
|
| 425 |
+
"mode": "affine"
|
| 426 |
+
},
|
| 427 |
+
"language_model.model.layers.50.linear_attn.out_proj": {
|
| 428 |
+
"bits": 5,
|
| 429 |
+
"group_size": 64,
|
| 430 |
+
"mode": "affine"
|
| 431 |
+
},
|
| 432 |
+
"language_model.model.layers.52.linear_attn.out_proj": {
|
| 433 |
+
"bits": 5,
|
| 434 |
+
"group_size": 64,
|
| 435 |
+
"mode": "affine"
|
| 436 |
+
},
|
| 437 |
+
"language_model.model.layers.53.linear_attn.out_proj": {
|
| 438 |
+
"bits": 5,
|
| 439 |
+
"group_size": 64,
|
| 440 |
+
"mode": "affine"
|
| 441 |
+
},
|
| 442 |
+
"language_model.model.layers.54.linear_attn.out_proj": {
|
| 443 |
+
"bits": 5,
|
| 444 |
+
"group_size": 64,
|
| 445 |
+
"mode": "affine"
|
| 446 |
+
},
|
| 447 |
+
"language_model.model.layers.56.linear_attn.out_proj": {
|
| 448 |
+
"bits": 5,
|
| 449 |
+
"group_size": 64,
|
| 450 |
+
"mode": "affine"
|
| 451 |
+
},
|
| 452 |
+
"language_model.model.layers.57.linear_attn.out_proj": {
|
| 453 |
+
"bits": 5,
|
| 454 |
+
"group_size": 64,
|
| 455 |
+
"mode": "affine"
|
| 456 |
+
},
|
| 457 |
+
"language_model.model.layers.58.linear_attn.out_proj": {
|
| 458 |
+
"bits": 5,
|
| 459 |
+
"group_size": 64,
|
| 460 |
+
"mode": "affine"
|
| 461 |
+
},
|
| 462 |
+
"language_model.model.layers.60.linear_attn.out_proj": {
|
| 463 |
+
"bits": 5,
|
| 464 |
+
"group_size": 64,
|
| 465 |
+
"mode": "affine"
|
| 466 |
+
},
|
| 467 |
+
"language_model.model.layers.61.linear_attn.out_proj": {
|
| 468 |
+
"bits": 5,
|
| 469 |
+
"group_size": 64,
|
| 470 |
+
"mode": "affine"
|
| 471 |
+
},
|
| 472 |
+
"language_model.model.layers.62.linear_attn.out_proj": {
|
| 473 |
+
"bits": 5,
|
| 474 |
+
"group_size": 64,
|
| 475 |
+
"mode": "affine"
|
| 476 |
+
}
|
| 477 |
+
},
|
| 478 |
+
"quantization_config": {
|
| 479 |
+
"group_size": 64,
|
| 480 |
+
"bits": 4,
|
| 481 |
+
"mode": "affine",
|
| 482 |
+
"language_model.model.embed_tokens": {
|
| 483 |
+
"bits": 8,
|
| 484 |
+
"group_size": 64,
|
| 485 |
+
"mode": "affine"
|
| 486 |
+
},
|
| 487 |
+
"language_model.model.layers.0.linear_attn.in_proj_a": {
|
| 488 |
+
"bits": 5,
|
| 489 |
+
"group_size": 64,
|
| 490 |
+
"mode": "affine"
|
| 491 |
+
},
|
| 492 |
+
"language_model.model.layers.0.linear_attn.in_proj_b": {
|
| 493 |
+
"bits": 5,
|
| 494 |
+
"group_size": 64,
|
| 495 |
+
"mode": "affine"
|
| 496 |
+
},
|
| 497 |
+
"language_model.model.layers.0.linear_attn.in_proj_qkv": {
|
| 498 |
+
"bits": 5,
|
| 499 |
+
"group_size": 64,
|
| 500 |
+
"mode": "affine"
|
| 501 |
+
},
|
| 502 |
+
"language_model.model.layers.0.linear_attn.in_proj_z": {
|
| 503 |
+
"bits": 5,
|
| 504 |
+
"group_size": 64,
|
| 505 |
+
"mode": "affine"
|
| 506 |
+
},
|
| 507 |
+
"language_model.model.layers.0.linear_attn.out_proj": {
|
| 508 |
+
"bits": 5,
|
| 509 |
+
"group_size": 64,
|
| 510 |
+
"mode": "affine"
|
| 511 |
+
},
|
| 512 |
+
"language_model.model.layers.1.linear_attn.in_proj_a": {
|
| 513 |
+
"bits": 5,
|
| 514 |
+
"group_size": 64,
|
| 515 |
+
"mode": "affine"
|
| 516 |
+
},
|
| 517 |
+
"language_model.model.layers.1.linear_attn.in_proj_b": {
|
| 518 |
+
"bits": 5,
|
| 519 |
+
"group_size": 64,
|
| 520 |
+
"mode": "affine"
|
| 521 |
+
},
|
| 522 |
+
"language_model.model.layers.1.linear_attn.in_proj_qkv": {
|
| 523 |
+
"bits": 5,
|
| 524 |
+
"group_size": 64,
|
| 525 |
+
"mode": "affine"
|
| 526 |
+
},
|
| 527 |
+
"language_model.model.layers.1.linear_attn.in_proj_z": {
|
| 528 |
+
"bits": 5,
|
| 529 |
+
"group_size": 64,
|
| 530 |
+
"mode": "affine"
|
| 531 |
+
},
|
| 532 |
+
"language_model.model.layers.1.linear_attn.out_proj": {
|
| 533 |
+
"bits": 5,
|
| 534 |
+
"group_size": 64,
|
| 535 |
+
"mode": "affine"
|
| 536 |
+
},
|
| 537 |
+
"language_model.model.layers.2.linear_attn.in_proj_a": {
|
| 538 |
+
"bits": 5,
|
| 539 |
+
"group_size": 64,
|
| 540 |
+
"mode": "affine"
|
| 541 |
+
},
|
| 542 |
+
"language_model.model.layers.2.linear_attn.in_proj_b": {
|
| 543 |
+
"bits": 5,
|
| 544 |
+
"group_size": 64,
|
| 545 |
+
"mode": "affine"
|
| 546 |
+
},
|
| 547 |
+
"language_model.model.layers.2.linear_attn.in_proj_z": {
|
| 548 |
+
"bits": 5,
|
| 549 |
+
"group_size": 64,
|
| 550 |
+
"mode": "affine"
|
| 551 |
+
},
|
| 552 |
+
"language_model.model.layers.2.linear_attn.out_proj": {
|
| 553 |
+
"bits": 5,
|
| 554 |
+
"group_size": 64,
|
| 555 |
+
"mode": "affine"
|
| 556 |
+
},
|
| 557 |
+
"language_model.model.layers.3.self_attn.k_proj": {
|
| 558 |
+
"bits": 5,
|
| 559 |
+
"group_size": 64,
|
| 560 |
+
"mode": "affine"
|
| 561 |
+
},
|
| 562 |
+
"language_model.model.layers.10.linear_attn.in_proj_a": {
|
| 563 |
+
"bits": 5,
|
| 564 |
+
"group_size": 64,
|
| 565 |
+
"mode": "affine"
|
| 566 |
+
},
|
| 567 |
+
"language_model.model.layers.10.linear_attn.in_proj_b": {
|
| 568 |
+
"bits": 5,
|
| 569 |
+
"group_size": 64,
|
| 570 |
+
"mode": "affine"
|
| 571 |
+
},
|
| 572 |
+
"language_model.model.layers.10.linear_attn.out_proj": {
|
| 573 |
+
"bits": 5,
|
| 574 |
+
"group_size": 64,
|
| 575 |
+
"mode": "affine"
|
| 576 |
+
},
|
| 577 |
+
"language_model.model.layers.4.linear_attn.in_proj_a": {
|
| 578 |
+
"bits": 5,
|
| 579 |
+
"group_size": 64,
|
| 580 |
+
"mode": "affine"
|
| 581 |
+
},
|
| 582 |
+
"language_model.model.layers.4.linear_attn.in_proj_b": {
|
| 583 |
+
"bits": 5,
|
| 584 |
+
"group_size": 64,
|
| 585 |
+
"mode": "affine"
|
| 586 |
+
},
|
| 587 |
+
"language_model.model.layers.4.linear_attn.out_proj": {
|
| 588 |
+
"bits": 5,
|
| 589 |
+
"group_size": 64,
|
| 590 |
+
"mode": "affine"
|
| 591 |
+
},
|
| 592 |
+
"language_model.model.layers.5.linear_attn.in_proj_a": {
|
| 593 |
+
"bits": 5,
|
| 594 |
+
"group_size": 64,
|
| 595 |
+
"mode": "affine"
|
| 596 |
+
},
|
| 597 |
+
"language_model.model.layers.5.linear_attn.in_proj_b": {
|
| 598 |
+
"bits": 5,
|
| 599 |
+
"group_size": 64,
|
| 600 |
+
"mode": "affine"
|
| 601 |
+
},
|
| 602 |
+
"language_model.model.layers.5.linear_attn.out_proj": {
|
| 603 |
+
"bits": 5,
|
| 604 |
+
"group_size": 64,
|
| 605 |
+
"mode": "affine"
|
| 606 |
+
},
|
| 607 |
+
"language_model.model.layers.6.linear_attn.in_proj_a": {
|
| 608 |
+
"bits": 5,
|
| 609 |
+
"group_size": 64,
|
| 610 |
+
"mode": "affine"
|
| 611 |
+
},
|
| 612 |
+
"language_model.model.layers.6.linear_attn.in_proj_b": {
|
| 613 |
+
"bits": 5,
|
| 614 |
+
"group_size": 64,
|
| 615 |
+
"mode": "affine"
|
| 616 |
+
},
|
| 617 |
+
"language_model.model.layers.6.linear_attn.out_proj": {
|
| 618 |
+
"bits": 5,
|
| 619 |
+
"group_size": 64,
|
| 620 |
+
"mode": "affine"
|
| 621 |
+
},
|
| 622 |
+
"language_model.model.layers.8.linear_attn.out_proj": {
|
| 623 |
+
"bits": 5,
|
| 624 |
+
"group_size": 64,
|
| 625 |
+
"mode": "affine"
|
| 626 |
+
},
|
| 627 |
+
"language_model.model.layers.9.linear_attn.out_proj": {
|
| 628 |
+
"bits": 5,
|
| 629 |
+
"group_size": 64,
|
| 630 |
+
"mode": "affine"
|
| 631 |
+
},
|
| 632 |
+
"language_model.model.layers.12.linear_attn.out_proj": {
|
| 633 |
+
"bits": 5,
|
| 634 |
+
"group_size": 64,
|
| 635 |
+
"mode": "affine"
|
| 636 |
+
},
|
| 637 |
+
"language_model.model.layers.13.linear_attn.out_proj": {
|
| 638 |
+
"bits": 5,
|
| 639 |
+
"group_size": 64,
|
| 640 |
+
"mode": "affine"
|
| 641 |
+
},
|
| 642 |
+
"language_model.model.layers.14.linear_attn.out_proj": {
|
| 643 |
+
"bits": 5,
|
| 644 |
+
"group_size": 64,
|
| 645 |
+
"mode": "affine"
|
| 646 |
+
},
|
| 647 |
+
"language_model.model.layers.16.linear_attn.out_proj": {
|
| 648 |
+
"bits": 5,
|
| 649 |
+
"group_size": 64,
|
| 650 |
+
"mode": "affine"
|
| 651 |
+
},
|
| 652 |
+
"language_model.model.layers.17.linear_attn.out_proj": {
|
| 653 |
+
"bits": 5,
|
| 654 |
+
"group_size": 64,
|
| 655 |
+
"mode": "affine"
|
| 656 |
+
},
|
| 657 |
+
"language_model.model.layers.18.linear_attn.out_proj": {
|
| 658 |
+
"bits": 5,
|
| 659 |
+
"group_size": 64,
|
| 660 |
+
"mode": "affine"
|
| 661 |
+
},
|
| 662 |
+
"language_model.model.layers.20.linear_attn.out_proj": {
|
| 663 |
+
"bits": 5,
|
| 664 |
+
"group_size": 64,
|
| 665 |
+
"mode": "affine"
|
| 666 |
+
},
|
| 667 |
+
"language_model.model.layers.21.linear_attn.out_proj": {
|
| 668 |
+
"bits": 5,
|
| 669 |
+
"group_size": 64,
|
| 670 |
+
"mode": "affine"
|
| 671 |
+
},
|
| 672 |
+
"language_model.model.layers.22.linear_attn.out_proj": {
|
| 673 |
+
"bits": 5,
|
| 674 |
+
"group_size": 64,
|
| 675 |
+
"mode": "affine"
|
| 676 |
+
},
|
| 677 |
+
"language_model.model.layers.24.linear_attn.out_proj": {
|
| 678 |
+
"bits": 5,
|
| 679 |
+
"group_size": 64,
|
| 680 |
+
"mode": "affine"
|
| 681 |
+
},
|
| 682 |
+
"language_model.model.layers.25.linear_attn.out_proj": {
|
| 683 |
+
"bits": 5,
|
| 684 |
+
"group_size": 64,
|
| 685 |
+
"mode": "affine"
|
| 686 |
+
},
|
| 687 |
+
"language_model.model.layers.26.linear_attn.out_proj": {
|
| 688 |
+
"bits": 5,
|
| 689 |
+
"group_size": 64,
|
| 690 |
+
"mode": "affine"
|
| 691 |
+
},
|
| 692 |
+
"language_model.model.layers.28.linear_attn.out_proj": {
|
| 693 |
+
"bits": 5,
|
| 694 |
+
"group_size": 64,
|
| 695 |
+
"mode": "affine"
|
| 696 |
+
},
|
| 697 |
+
"language_model.model.layers.29.linear_attn.out_proj": {
|
| 698 |
+
"bits": 5,
|
| 699 |
+
"group_size": 64,
|
| 700 |
+
"mode": "affine"
|
| 701 |
+
},
|
| 702 |
+
"language_model.model.layers.30.linear_attn.out_proj": {
|
| 703 |
+
"bits": 5,
|
| 704 |
+
"group_size": 64,
|
| 705 |
+
"mode": "affine"
|
| 706 |
+
},
|
| 707 |
+
"language_model.model.layers.32.linear_attn.out_proj": {
|
| 708 |
+
"bits": 5,
|
| 709 |
+
"group_size": 64,
|
| 710 |
+
"mode": "affine"
|
| 711 |
+
},
|
| 712 |
+
"language_model.model.layers.33.linear_attn.out_proj": {
|
| 713 |
+
"bits": 5,
|
| 714 |
+
"group_size": 64,
|
| 715 |
+
"mode": "affine"
|
| 716 |
+
},
|
| 717 |
+
"language_model.model.layers.34.linear_attn.out_proj": {
|
| 718 |
+
"bits": 5,
|
| 719 |
+
"group_size": 64,
|
| 720 |
+
"mode": "affine"
|
| 721 |
+
},
|
| 722 |
+
"language_model.model.layers.36.linear_attn.out_proj": {
|
| 723 |
+
"bits": 5,
|
| 724 |
+
"group_size": 64,
|
| 725 |
+
"mode": "affine"
|
| 726 |
+
},
|
| 727 |
+
"language_model.model.layers.37.linear_attn.out_proj": {
|
| 728 |
+
"bits": 5,
|
| 729 |
+
"group_size": 64,
|
| 730 |
+
"mode": "affine"
|
| 731 |
+
},
|
| 732 |
+
"language_model.model.layers.38.linear_attn.out_proj": {
|
| 733 |
+
"bits": 5,
|
| 734 |
+
"group_size": 64,
|
| 735 |
+
"mode": "affine"
|
| 736 |
+
},
|
| 737 |
+
"language_model.model.layers.40.linear_attn.out_proj": {
|
| 738 |
+
"bits": 5,
|
| 739 |
+
"group_size": 64,
|
| 740 |
+
"mode": "affine"
|
| 741 |
+
},
|
| 742 |
+
"language_model.model.layers.41.linear_attn.out_proj": {
|
| 743 |
+
"bits": 5,
|
| 744 |
+
"group_size": 64,
|
| 745 |
+
"mode": "affine"
|
| 746 |
+
},
|
| 747 |
+
"language_model.model.layers.42.linear_attn.out_proj": {
|
| 748 |
+
"bits": 5,
|
| 749 |
+
"group_size": 64,
|
| 750 |
+
"mode": "affine"
|
| 751 |
+
},
|
| 752 |
+
"language_model.model.layers.44.linear_attn.out_proj": {
|
| 753 |
+
"bits": 5,
|
| 754 |
+
"group_size": 64,
|
| 755 |
+
"mode": "affine"
|
| 756 |
+
},
|
| 757 |
+
"language_model.model.layers.45.linear_attn.out_proj": {
|
| 758 |
+
"bits": 5,
|
| 759 |
+
"group_size": 64,
|
| 760 |
+
"mode": "affine"
|
| 761 |
+
},
|
| 762 |
+
"language_model.model.layers.46.linear_attn.out_proj": {
|
| 763 |
+
"bits": 5,
|
| 764 |
+
"group_size": 64,
|
| 765 |
+
"mode": "affine"
|
| 766 |
+
},
|
| 767 |
+
"language_model.model.layers.48.linear_attn.out_proj": {
|
| 768 |
+
"bits": 5,
|
| 769 |
+
"group_size": 64,
|
| 770 |
+
"mode": "affine"
|
| 771 |
+
},
|
| 772 |
+
"language_model.model.layers.49.linear_attn.out_proj": {
|
| 773 |
+
"bits": 5,
|
| 774 |
+
"group_size": 64,
|
| 775 |
+
"mode": "affine"
|
| 776 |
+
},
|
| 777 |
+
"language_model.model.layers.50.linear_attn.out_proj": {
|
| 778 |
+
"bits": 5,
|
| 779 |
+
"group_size": 64,
|
| 780 |
+
"mode": "affine"
|
| 781 |
+
},
|
| 782 |
+
"language_model.model.layers.52.linear_attn.out_proj": {
|
| 783 |
+
"bits": 5,
|
| 784 |
+
"group_size": 64,
|
| 785 |
+
"mode": "affine"
|
| 786 |
+
},
|
| 787 |
+
"language_model.model.layers.53.linear_attn.out_proj": {
|
| 788 |
+
"bits": 5,
|
| 789 |
+
"group_size": 64,
|
| 790 |
+
"mode": "affine"
|
| 791 |
+
},
|
| 792 |
+
"language_model.model.layers.54.linear_attn.out_proj": {
|
| 793 |
+
"bits": 5,
|
| 794 |
+
"group_size": 64,
|
| 795 |
+
"mode": "affine"
|
| 796 |
+
},
|
| 797 |
+
"language_model.model.layers.56.linear_attn.out_proj": {
|
| 798 |
+
"bits": 5,
|
| 799 |
+
"group_size": 64,
|
| 800 |
+
"mode": "affine"
|
| 801 |
+
},
|
| 802 |
+
"language_model.model.layers.57.linear_attn.out_proj": {
|
| 803 |
+
"bits": 5,
|
| 804 |
+
"group_size": 64,
|
| 805 |
+
"mode": "affine"
|
| 806 |
+
},
|
| 807 |
+
"language_model.model.layers.58.linear_attn.out_proj": {
|
| 808 |
+
"bits": 5,
|
| 809 |
+
"group_size": 64,
|
| 810 |
+
"mode": "affine"
|
| 811 |
+
},
|
| 812 |
+
"language_model.model.layers.60.linear_attn.out_proj": {
|
| 813 |
+
"bits": 5,
|
| 814 |
+
"group_size": 64,
|
| 815 |
+
"mode": "affine"
|
| 816 |
+
},
|
| 817 |
+
"language_model.model.layers.61.linear_attn.out_proj": {
|
| 818 |
+
"bits": 5,
|
| 819 |
+
"group_size": 64,
|
| 820 |
+
"mode": "affine"
|
| 821 |
+
},
|
| 822 |
+
"language_model.model.layers.62.linear_attn.out_proj": {
|
| 823 |
+
"bits": 5,
|
| 824 |
+
"group_size": 64,
|
| 825 |
+
"mode": "affine"
|
| 826 |
+
}
|
| 827 |
+
}
|
| 828 |
+
}
|
docs/arc-challenge-10.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_id": "oq4e-smoke-s32",
|
| 3 |
+
"benchmark": "arc_challenge",
|
| 4 |
+
"sampling": "deterministic_thinking_off",
|
| 5 |
+
"total": 10,
|
| 6 |
+
"correct": 6,
|
| 7 |
+
"accuracy": 0.6,
|
| 8 |
+
"time_s": 39.548,
|
| 9 |
+
"peak_memory_gb": 15.415,
|
| 10 |
+
"question_results": [
|
| 11 |
+
{
|
| 12 |
+
"id": "Mercury_7043820",
|
| 13 |
+
"expected": "B",
|
| 14 |
+
"predicted": "A",
|
| 15 |
+
"correct": false,
|
| 16 |
+
"raw_response": "A."
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"id": "MCAS_2003_5_33",
|
| 20 |
+
"expected": "C",
|
| 21 |
+
"predicted": "C",
|
| 22 |
+
"correct": true,
|
| 23 |
+
"raw_response": "C"
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"id": "Mercury_7219678",
|
| 27 |
+
"expected": "A",
|
| 28 |
+
"predicted": "B",
|
| 29 |
+
"correct": false,
|
| 30 |
+
"raw_response": "The question describes a scenario where a beach community's water supply (surface and groundwater) is decreasing. They decide to build a large-scale desalination plant to remove salt from bay water. The key reason for this decision is the **decrease in water resources**.\n\nLet's evaluate the options:\n\nA. **needed increased resources.** - This aligns with the problem statement: the water supply is decreasing, so they need more water resources. Desalination is a method to create fresh water resources from saltwater.\nB. **had access to advanced technology.** - While desalination uses technology, the *reason* for"
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"id": "AKDE&ED_2008_8_48",
|
| 34 |
+
"expected": "A",
|
| 35 |
+
"predicted": "A",
|
| 36 |
+
"correct": true,
|
| 37 |
+
"raw_response": "A"
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"id": "Mercury_7210455",
|
| 41 |
+
"expected": "C",
|
| 42 |
+
"predicted": "C",
|
| 43 |
+
"correct": true,
|
| 44 |
+
"raw_response": "C"
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"id": "Mercury_407517",
|
| 48 |
+
"expected": "C",
|
| 49 |
+
"predicted": "C",
|
| 50 |
+
"correct": true,
|
| 51 |
+
"raw_response": "C"
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"id": "TIMSS_2007_8_pg109",
|
| 55 |
+
"expected": "C",
|
| 56 |
+
"predicted": "C",
|
| 57 |
+
"correct": true,
|
| 58 |
+
"raw_response": "C"
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": "Mercury_SC_400134",
|
| 62 |
+
"expected": "D",
|
| 63 |
+
"predicted": "B",
|
| 64 |
+
"correct": false,
|
| 65 |
+
"raw_response": "B"
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"id": "Mercury_402501",
|
| 69 |
+
"expected": "B",
|
| 70 |
+
"predicted": "B",
|
| 71 |
+
"correct": true,
|
| 72 |
+
"raw_response": "B"
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"id": "Mercury_400084",
|
| 76 |
+
"expected": "D",
|
| 77 |
+
"predicted": "C",
|
| 78 |
+
"correct": false,
|
| 79 |
+
"raw_response": "To balance the chemical equation for the combustion of methane:\n\n$$ \\text{CH}_4 + \\Box \\text{O}_2 \\rightarrow 2\\text{CO}_2 + 4\\text{H}_2\\text{O} $$\n\nLet's count the atoms on each side:\n\n**Right Side (Products):**\n* Carbon (C): 2 atoms (from $2\\text{CO}_2$)\n* Hydrogen (H): 8 atoms (from $4\\text{H}_2\\text{O}$)\n* Oxygen (O): $(2"
|
| 80 |
+
}
|
| 81 |
+
]
|
| 82 |
+
}
|
docs/hellaswag-10.json
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_id": "oq4e-smoke-s32",
|
| 3 |
+
"benchmark": "hellaswag",
|
| 4 |
+
"sampling": "deterministic_thinking_off",
|
| 5 |
+
"total": 10,
|
| 6 |
+
"correct": 6,
|
| 7 |
+
"accuracy": 0.6,
|
| 8 |
+
"time_s": 71.689,
|
| 9 |
+
"peak_memory_gb": 15.696,
|
| 10 |
+
"question_results": [
|
| 11 |
+
{
|
| 12 |
+
"id": 28016,
|
| 13 |
+
"expected": "A",
|
| 14 |
+
"predicted": "A",
|
| 15 |
+
"correct": true,
|
| 16 |
+
"raw_response": "The context describes a scene of people watching a water polo game from the bleachers. The sentence ends with \"in the water\", which suggests the continuation should describe an action happening within the water during the game.\n\nLet's evaluate the options:\n\nA. \", two boys begin treading water and staying in the same place.\" - This is a plausible action in water polo (treading water is a fundamental skill). The comma suggests it continues the sentence structure.\nB. \"a woman stands on a rope over and over.\" - This is not a typical water polo action and doesn't fit the context of watching a game.\n",
|
| 17 |
+
"category": "Playing polo"
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"id": 5823,
|
| 21 |
+
"expected": "A",
|
| 22 |
+
"predicted": "A",
|
| 23 |
+
"correct": true,
|
| 24 |
+
"raw_response": "The most plausible continuation is **A**.\n\n**Reasoning:**\nThe context describes a casual, playful scene of boys on stilts on a sidewalk. Option A (\"continue talking as they bounce and walk\") is the most natural and common activity for a group of children playing together in such a setting. The other options introduce specific props or actions (wrapping paper, hoops, a wobbly bar and mat) that are not suggested by the context and are less likely to be the immediate next action without additional setup.\n\nAnswer: A",
|
| 25 |
+
"category": "Powerbocking"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"id": 9715,
|
| 29 |
+
"expected": "D",
|
| 30 |
+
"predicted": "D",
|
| 31 |
+
"correct": true,
|
| 32 |
+
"raw_response": "D",
|
| 33 |
+
"category": "Personal Care and Style"
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"id": 5867,
|
| 37 |
+
"expected": "D",
|
| 38 |
+
"predicted": "D",
|
| 39 |
+
"correct": true,
|
| 40 |
+
"raw_response": "D",
|
| 41 |
+
"category": "Health"
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"id": 3190,
|
| 45 |
+
"expected": "C",
|
| 46 |
+
"predicted": "C",
|
| 47 |
+
"correct": true,
|
| 48 |
+
"raw_response": "C",
|
| 49 |
+
"category": "Pets and Animals"
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 35259,
|
| 53 |
+
"expected": "C",
|
| 54 |
+
"predicted": "A",
|
| 55 |
+
"correct": false,
|
| 56 |
+
"raw_response": "C. instructs the boy on how to turn the mower and go around a small tree.",
|
| 57 |
+
"category": "Cutting the grass"
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"id": 25693,
|
| 61 |
+
"expected": "D",
|
| 62 |
+
"predicted": "D",
|
| 63 |
+
"correct": true,
|
| 64 |
+
"raw_response": "D",
|
| 65 |
+
"category": "Playing polo"
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"id": 42181,
|
| 69 |
+
"expected": "B",
|
| 70 |
+
"predicted": "A",
|
| 71 |
+
"correct": false,
|
| 72 |
+
"raw_response": "The context is a guide on \"How to be adventurous,\" specifically focusing on letting go of inhibitions (shyness, fear, etc.).\n\nLet's evaluate the options:\n\n* **A:** Suggests acting inappropriately to loosen others up. This is generally poor advice and doesn't directly address the internal feeling of inhibition mentioned in the context.\n* **B:** Directly addresses the goal (\"let go of what is holding you back\") by suggesting feeling safe. It also includes a logical next step (\"Ask yourself why you want to be adventurous\"). This fits the tone and structure of a self-help guide",
|
| 73 |
+
"category": "Health"
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"id": 21145,
|
| 77 |
+
"expected": "A",
|
| 78 |
+
"predicted": "B",
|
| 79 |
+
"correct": false,
|
| 80 |
+
"raw_response": "B. holds the spoon in his hands and lifts it up to show the proper position.",
|
| 81 |
+
"category": "Making a lemonade"
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"id": 47659,
|
| 85 |
+
"expected": "D",
|
| 86 |
+
"predicted": "A",
|
| 87 |
+
"correct": false,
|
| 88 |
+
"raw_response": "The context provides a step-by-step guide on how to recycle car seats. The last step mentioned is contacting a local car seat trade-in program. The most logical continuation would be to provide further instructions or alternative methods for recycling car seats.\n\nOption A suggests asking around and considering other automotive or recycling resources, which is a reasonable next step after mentioning trade-in programs. It also introduces a new title \"Recycle at a recycling center,\" which fits well with the theme of recycling.\n\nOption B talks about changing colors, which is irrelevant to recycling.\n\nOption C mentions mailing programs to a website, which doesn't make sense in this context",
|
| 89 |
+
"category": "Home and Garden"
|
| 90 |
+
}
|
| 91 |
+
]
|
| 92 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4849622d9f159a927df93d1c45b21ab7054c4c5a70dec850808fcbac383c1da9
|
| 3 |
+
size 5019168653
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e49ca0024c0d8e9c7c23f6a71ebef096515b36a7e97136399ebf47e258e16ecf
|
| 3 |
+
size 5001499651
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:080e92e3041fcedd253a582d42b107b06f283870d9131520f45bf240f00f5ba6
|
| 3 |
+
size 5038212407
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f7ec4edcbcd98313481810ed1b0c5c3aa88d6c5c60bb75bebef84ba48910b2a
|
| 3 |
+
size 924594886
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
oq_imatrix_report.json
ADDED
|
@@ -0,0 +1,591 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"enabled": true,
|
| 3 |
+
"cache_path": "IMATRIX_CACHE_S32.npz",
|
| 4 |
+
"cache_reused": false,
|
| 5 |
+
"entry_count": 496,
|
| 6 |
+
"calib_dataset": "oqe_code_multilingual",
|
| 7 |
+
"collection": {
|
| 8 |
+
"dataset": "oqe_code_multilingual",
|
| 9 |
+
"requested_samples": 32,
|
| 10 |
+
"seq_length": 512,
|
| 11 |
+
"adaptive": true,
|
| 12 |
+
"adaptive_step_samples": 32,
|
| 13 |
+
"adaptive_max_samples": 256,
|
| 14 |
+
"available_samples": 256,
|
| 15 |
+
"micro_batch_size": 17,
|
| 16 |
+
"micro_batches": 2,
|
| 17 |
+
"batch_plan": {
|
| 18 |
+
"micro_batch_size": 17,
|
| 19 |
+
"estimated_sample_bytes": 10485760,
|
| 20 |
+
"capture_budget_bytes": 179194593,
|
| 21 |
+
"hidden_size": 5120,
|
| 22 |
+
"num_experts": 0,
|
| 23 |
+
"top_k": 1
|
| 24 |
+
},
|
| 25 |
+
"processed_samples": 32,
|
| 26 |
+
"installed_modules": 497,
|
| 27 |
+
"capture_module_classes": {
|
| 28 |
+
"QuantizedLinear": 497
|
| 29 |
+
},
|
| 30 |
+
"switch_capture_modules": 0,
|
| 31 |
+
"requires_expert_counts": false,
|
| 32 |
+
"coverage_sufficient": true,
|
| 33 |
+
"collection_sufficient": true,
|
| 34 |
+
"coverage": {
|
| 35 |
+
"has_expert_counts": false,
|
| 36 |
+
"expert_modules": 0,
|
| 37 |
+
"total_experts": 0,
|
| 38 |
+
"active_experts": 0,
|
| 39 |
+
"zero_count_experts": 0,
|
| 40 |
+
"active_ratio": 1.0,
|
| 41 |
+
"min_count": 0,
|
| 42 |
+
"p05_count": 0.0,
|
| 43 |
+
"p10_count": 0.0,
|
| 44 |
+
"median_count": 0.0,
|
| 45 |
+
"max_count": 0,
|
| 46 |
+
"min_required_count": 16,
|
| 47 |
+
"required_percentile": 5
|
| 48 |
+
},
|
| 49 |
+
"rounds": [
|
| 50 |
+
{
|
| 51 |
+
"processed_samples": 32,
|
| 52 |
+
"coverage_sufficient": true,
|
| 53 |
+
"collection_sufficient": true,
|
| 54 |
+
"coverage": {
|
| 55 |
+
"has_expert_counts": false,
|
| 56 |
+
"expert_modules": 0,
|
| 57 |
+
"total_experts": 0,
|
| 58 |
+
"active_experts": 0,
|
| 59 |
+
"zero_count_experts": 0,
|
| 60 |
+
"active_ratio": 1.0,
|
| 61 |
+
"min_count": 0,
|
| 62 |
+
"p05_count": 0.0,
|
| 63 |
+
"p10_count": 0.0,
|
| 64 |
+
"median_count": 0.0,
|
| 65 |
+
"max_count": 0,
|
| 66 |
+
"min_required_count": 16,
|
| 67 |
+
"required_percentile": 5
|
| 68 |
+
}
|
| 69 |
+
}
|
| 70 |
+
]
|
| 71 |
+
},
|
| 72 |
+
"expert_coverage": {
|
| 73 |
+
"has_expert_counts": false,
|
| 74 |
+
"expert_modules": 0,
|
| 75 |
+
"total_experts": 0,
|
| 76 |
+
"active_experts": 0,
|
| 77 |
+
"zero_count_experts": 0,
|
| 78 |
+
"active_ratio": 1.0,
|
| 79 |
+
"min_count": 0,
|
| 80 |
+
"p05_count": 0.0,
|
| 81 |
+
"p10_count": 0.0,
|
| 82 |
+
"median_count": 0.0,
|
| 83 |
+
"max_count": 0,
|
| 84 |
+
"min_required_count": 16,
|
| 85 |
+
"required_percentile": 5
|
| 86 |
+
},
|
| 87 |
+
"applied": [
|
| 88 |
+
"language_model.model.layers.0.linear_attn.in_proj_a",
|
| 89 |
+
"language_model.model.layers.0.linear_attn.in_proj_b",
|
| 90 |
+
"language_model.model.layers.0.linear_attn.in_proj_qkv",
|
| 91 |
+
"language_model.model.layers.0.linear_attn.in_proj_z",
|
| 92 |
+
"language_model.model.layers.0.linear_attn.out_proj",
|
| 93 |
+
"language_model.model.layers.0.mlp.down_proj",
|
| 94 |
+
"language_model.model.layers.0.mlp.gate_proj",
|
| 95 |
+
"language_model.model.layers.0.mlp.up_proj",
|
| 96 |
+
"language_model.model.layers.1.linear_attn.in_proj_a",
|
| 97 |
+
"language_model.model.layers.1.linear_attn.in_proj_b",
|
| 98 |
+
"language_model.model.layers.1.linear_attn.in_proj_qkv",
|
| 99 |
+
"language_model.model.layers.1.linear_attn.in_proj_z",
|
| 100 |
+
"language_model.model.layers.1.linear_attn.out_proj",
|
| 101 |
+
"language_model.model.layers.1.mlp.down_proj",
|
| 102 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
| 103 |
+
"language_model.model.layers.1.mlp.up_proj",
|
| 104 |
+
"language_model.model.layers.10.linear_attn.in_proj_a",
|
| 105 |
+
"language_model.model.layers.10.linear_attn.in_proj_b",
|
| 106 |
+
"language_model.model.layers.10.linear_attn.in_proj_qkv",
|
| 107 |
+
"language_model.model.layers.10.linear_attn.in_proj_z",
|
| 108 |
+
"language_model.model.layers.10.linear_attn.out_proj",
|
| 109 |
+
"language_model.model.layers.10.mlp.down_proj",
|
| 110 |
+
"language_model.model.layers.10.mlp.gate_proj",
|
| 111 |
+
"language_model.model.layers.10.mlp.up_proj",
|
| 112 |
+
"language_model.model.layers.11.mlp.down_proj",
|
| 113 |
+
"language_model.model.layers.11.mlp.gate_proj",
|
| 114 |
+
"language_model.model.layers.11.mlp.up_proj",
|
| 115 |
+
"language_model.model.layers.11.self_attn.k_proj",
|
| 116 |
+
"language_model.model.layers.11.self_attn.o_proj",
|
| 117 |
+
"language_model.model.layers.11.self_attn.q_proj",
|
| 118 |
+
"language_model.model.layers.11.self_attn.v_proj",
|
| 119 |
+
"language_model.model.layers.12.linear_attn.in_proj_a",
|
| 120 |
+
"language_model.model.layers.12.linear_attn.in_proj_b",
|
| 121 |
+
"language_model.model.layers.12.linear_attn.in_proj_qkv",
|
| 122 |
+
"language_model.model.layers.12.linear_attn.in_proj_z",
|
| 123 |
+
"language_model.model.layers.12.linear_attn.out_proj",
|
| 124 |
+
"language_model.model.layers.12.mlp.down_proj",
|
| 125 |
+
"language_model.model.layers.12.mlp.gate_proj",
|
| 126 |
+
"language_model.model.layers.12.mlp.up_proj",
|
| 127 |
+
"language_model.model.layers.13.linear_attn.in_proj_a",
|
| 128 |
+
"language_model.model.layers.13.linear_attn.in_proj_b",
|
| 129 |
+
"language_model.model.layers.13.linear_attn.in_proj_qkv",
|
| 130 |
+
"language_model.model.layers.13.linear_attn.in_proj_z",
|
| 131 |
+
"language_model.model.layers.13.linear_attn.out_proj",
|
| 132 |
+
"language_model.model.layers.13.mlp.down_proj",
|
| 133 |
+
"language_model.model.layers.13.mlp.gate_proj",
|
| 134 |
+
"language_model.model.layers.13.mlp.up_proj",
|
| 135 |
+
"language_model.model.layers.14.linear_attn.in_proj_a",
|
| 136 |
+
"language_model.model.layers.14.linear_attn.in_proj_b",
|
| 137 |
+
"language_model.model.layers.14.linear_attn.in_proj_qkv",
|
| 138 |
+
"language_model.model.layers.14.linear_attn.in_proj_z",
|
| 139 |
+
"language_model.model.layers.14.linear_attn.out_proj",
|
| 140 |
+
"language_model.model.layers.14.mlp.down_proj",
|
| 141 |
+
"language_model.model.layers.14.mlp.gate_proj",
|
| 142 |
+
"language_model.model.layers.14.mlp.up_proj",
|
| 143 |
+
"language_model.model.layers.15.mlp.down_proj",
|
| 144 |
+
"language_model.model.layers.15.mlp.gate_proj",
|
| 145 |
+
"language_model.model.layers.15.mlp.up_proj",
|
| 146 |
+
"language_model.model.layers.15.self_attn.k_proj",
|
| 147 |
+
"language_model.model.layers.15.self_attn.o_proj",
|
| 148 |
+
"language_model.model.layers.15.self_attn.q_proj",
|
| 149 |
+
"language_model.model.layers.15.self_attn.v_proj",
|
| 150 |
+
"language_model.model.layers.16.linear_attn.in_proj_a",
|
| 151 |
+
"language_model.model.layers.16.linear_attn.in_proj_b",
|
| 152 |
+
"language_model.model.layers.16.linear_attn.in_proj_qkv",
|
| 153 |
+
"language_model.model.layers.16.linear_attn.in_proj_z",
|
| 154 |
+
"language_model.model.layers.16.linear_attn.out_proj",
|
| 155 |
+
"language_model.model.layers.16.mlp.down_proj",
|
| 156 |
+
"language_model.model.layers.16.mlp.gate_proj",
|
| 157 |
+
"language_model.model.layers.16.mlp.up_proj",
|
| 158 |
+
"language_model.model.layers.17.linear_attn.in_proj_a",
|
| 159 |
+
"language_model.model.layers.17.linear_attn.in_proj_b",
|
| 160 |
+
"language_model.model.layers.17.linear_attn.in_proj_qkv",
|
| 161 |
+
"language_model.model.layers.17.linear_attn.in_proj_z",
|
| 162 |
+
"language_model.model.layers.17.linear_attn.out_proj",
|
| 163 |
+
"language_model.model.layers.17.mlp.down_proj",
|
| 164 |
+
"language_model.model.layers.17.mlp.gate_proj",
|
| 165 |
+
"language_model.model.layers.17.mlp.up_proj",
|
| 166 |
+
"language_model.model.layers.18.linear_attn.in_proj_a",
|
| 167 |
+
"language_model.model.layers.18.linear_attn.in_proj_b",
|
| 168 |
+
"language_model.model.layers.18.linear_attn.in_proj_qkv",
|
| 169 |
+
"language_model.model.layers.18.linear_attn.in_proj_z",
|
| 170 |
+
"language_model.model.layers.18.linear_attn.out_proj",
|
| 171 |
+
"language_model.model.layers.18.mlp.down_proj",
|
| 172 |
+
"language_model.model.layers.18.mlp.gate_proj",
|
| 173 |
+
"language_model.model.layers.18.mlp.up_proj",
|
| 174 |
+
"language_model.model.layers.19.mlp.down_proj",
|
| 175 |
+
"language_model.model.layers.19.mlp.gate_proj",
|
| 176 |
+
"language_model.model.layers.19.mlp.up_proj",
|
| 177 |
+
"language_model.model.layers.19.self_attn.k_proj",
|
| 178 |
+
"language_model.model.layers.19.self_attn.o_proj",
|
| 179 |
+
"language_model.model.layers.19.self_attn.q_proj",
|
| 180 |
+
"language_model.model.layers.19.self_attn.v_proj",
|
| 181 |
+
"language_model.model.layers.2.linear_attn.in_proj_a",
|
| 182 |
+
"language_model.model.layers.2.linear_attn.in_proj_b",
|
| 183 |
+
"language_model.model.layers.2.linear_attn.in_proj_qkv",
|
| 184 |
+
"language_model.model.layers.2.linear_attn.in_proj_z",
|
| 185 |
+
"language_model.model.layers.2.linear_attn.out_proj",
|
| 186 |
+
"language_model.model.layers.2.mlp.down_proj",
|
| 187 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
| 188 |
+
"language_model.model.layers.2.mlp.up_proj",
|
| 189 |
+
"language_model.model.layers.20.linear_attn.in_proj_a",
|
| 190 |
+
"language_model.model.layers.20.linear_attn.in_proj_b",
|
| 191 |
+
"language_model.model.layers.20.linear_attn.in_proj_qkv",
|
| 192 |
+
"language_model.model.layers.20.linear_attn.in_proj_z",
|
| 193 |
+
"language_model.model.layers.20.linear_attn.out_proj",
|
| 194 |
+
"language_model.model.layers.20.mlp.down_proj",
|
| 195 |
+
"language_model.model.layers.20.mlp.gate_proj",
|
| 196 |
+
"language_model.model.layers.20.mlp.up_proj",
|
| 197 |
+
"language_model.model.layers.21.linear_attn.in_proj_a",
|
| 198 |
+
"language_model.model.layers.21.linear_attn.in_proj_b",
|
| 199 |
+
"language_model.model.layers.21.linear_attn.in_proj_qkv",
|
| 200 |
+
"language_model.model.layers.21.linear_attn.in_proj_z",
|
| 201 |
+
"language_model.model.layers.21.linear_attn.out_proj",
|
| 202 |
+
"language_model.model.layers.21.mlp.down_proj",
|
| 203 |
+
"language_model.model.layers.21.mlp.gate_proj",
|
| 204 |
+
"language_model.model.layers.21.mlp.up_proj",
|
| 205 |
+
"language_model.model.layers.22.linear_attn.in_proj_a",
|
| 206 |
+
"language_model.model.layers.22.linear_attn.in_proj_b",
|
| 207 |
+
"language_model.model.layers.22.linear_attn.in_proj_qkv",
|
| 208 |
+
"language_model.model.layers.22.linear_attn.in_proj_z",
|
| 209 |
+
"language_model.model.layers.22.linear_attn.out_proj",
|
| 210 |
+
"language_model.model.layers.22.mlp.down_proj",
|
| 211 |
+
"language_model.model.layers.22.mlp.gate_proj",
|
| 212 |
+
"language_model.model.layers.22.mlp.up_proj",
|
| 213 |
+
"language_model.model.layers.23.mlp.down_proj",
|
| 214 |
+
"language_model.model.layers.23.mlp.gate_proj",
|
| 215 |
+
"language_model.model.layers.23.mlp.up_proj",
|
| 216 |
+
"language_model.model.layers.23.self_attn.k_proj",
|
| 217 |
+
"language_model.model.layers.23.self_attn.o_proj",
|
| 218 |
+
"language_model.model.layers.23.self_attn.q_proj",
|
| 219 |
+
"language_model.model.layers.23.self_attn.v_proj",
|
| 220 |
+
"language_model.model.layers.24.linear_attn.in_proj_a",
|
| 221 |
+
"language_model.model.layers.24.linear_attn.in_proj_b",
|
| 222 |
+
"language_model.model.layers.24.linear_attn.in_proj_qkv",
|
| 223 |
+
"language_model.model.layers.24.linear_attn.in_proj_z",
|
| 224 |
+
"language_model.model.layers.24.linear_attn.out_proj",
|
| 225 |
+
"language_model.model.layers.24.mlp.down_proj",
|
| 226 |
+
"language_model.model.layers.24.mlp.gate_proj",
|
| 227 |
+
"language_model.model.layers.24.mlp.up_proj",
|
| 228 |
+
"language_model.model.layers.25.linear_attn.in_proj_a",
|
| 229 |
+
"language_model.model.layers.25.linear_attn.in_proj_b",
|
| 230 |
+
"language_model.model.layers.25.linear_attn.in_proj_qkv",
|
| 231 |
+
"language_model.model.layers.25.linear_attn.in_proj_z",
|
| 232 |
+
"language_model.model.layers.25.linear_attn.out_proj",
|
| 233 |
+
"language_model.model.layers.25.mlp.down_proj",
|
| 234 |
+
"language_model.model.layers.25.mlp.gate_proj",
|
| 235 |
+
"language_model.model.layers.25.mlp.up_proj",
|
| 236 |
+
"language_model.model.layers.26.linear_attn.in_proj_a",
|
| 237 |
+
"language_model.model.layers.26.linear_attn.in_proj_b",
|
| 238 |
+
"language_model.model.layers.26.linear_attn.in_proj_qkv",
|
| 239 |
+
"language_model.model.layers.26.linear_attn.in_proj_z",
|
| 240 |
+
"language_model.model.layers.26.linear_attn.out_proj",
|
| 241 |
+
"language_model.model.layers.26.mlp.down_proj",
|
| 242 |
+
"language_model.model.layers.26.mlp.gate_proj",
|
| 243 |
+
"language_model.model.layers.26.mlp.up_proj",
|
| 244 |
+
"language_model.model.layers.27.mlp.down_proj",
|
| 245 |
+
"language_model.model.layers.27.mlp.gate_proj",
|
| 246 |
+
"language_model.model.layers.27.mlp.up_proj",
|
| 247 |
+
"language_model.model.layers.27.self_attn.k_proj",
|
| 248 |
+
"language_model.model.layers.27.self_attn.o_proj",
|
| 249 |
+
"language_model.model.layers.27.self_attn.q_proj",
|
| 250 |
+
"language_model.model.layers.27.self_attn.v_proj",
|
| 251 |
+
"language_model.model.layers.28.linear_attn.in_proj_a",
|
| 252 |
+
"language_model.model.layers.28.linear_attn.in_proj_b",
|
| 253 |
+
"language_model.model.layers.28.linear_attn.in_proj_qkv",
|
| 254 |
+
"language_model.model.layers.28.linear_attn.in_proj_z",
|
| 255 |
+
"language_model.model.layers.28.linear_attn.out_proj",
|
| 256 |
+
"language_model.model.layers.28.mlp.down_proj",
|
| 257 |
+
"language_model.model.layers.28.mlp.gate_proj",
|
| 258 |
+
"language_model.model.layers.28.mlp.up_proj",
|
| 259 |
+
"language_model.model.layers.29.linear_attn.in_proj_a",
|
| 260 |
+
"language_model.model.layers.29.linear_attn.in_proj_b",
|
| 261 |
+
"language_model.model.layers.29.linear_attn.in_proj_qkv",
|
| 262 |
+
"language_model.model.layers.29.linear_attn.in_proj_z",
|
| 263 |
+
"language_model.model.layers.29.linear_attn.out_proj",
|
| 264 |
+
"language_model.model.layers.29.mlp.down_proj",
|
| 265 |
+
"language_model.model.layers.29.mlp.gate_proj",
|
| 266 |
+
"language_model.model.layers.29.mlp.up_proj",
|
| 267 |
+
"language_model.model.layers.3.mlp.down_proj",
|
| 268 |
+
"language_model.model.layers.3.mlp.gate_proj",
|
| 269 |
+
"language_model.model.layers.3.mlp.up_proj",
|
| 270 |
+
"language_model.model.layers.3.self_attn.k_proj",
|
| 271 |
+
"language_model.model.layers.3.self_attn.o_proj",
|
| 272 |
+
"language_model.model.layers.3.self_attn.q_proj",
|
| 273 |
+
"language_model.model.layers.3.self_attn.v_proj",
|
| 274 |
+
"language_model.model.layers.30.linear_attn.in_proj_a",
|
| 275 |
+
"language_model.model.layers.30.linear_attn.in_proj_b",
|
| 276 |
+
"language_model.model.layers.30.linear_attn.in_proj_qkv",
|
| 277 |
+
"language_model.model.layers.30.linear_attn.in_proj_z",
|
| 278 |
+
"language_model.model.layers.30.linear_attn.out_proj",
|
| 279 |
+
"language_model.model.layers.30.mlp.down_proj",
|
| 280 |
+
"language_model.model.layers.30.mlp.gate_proj",
|
| 281 |
+
"language_model.model.layers.30.mlp.up_proj",
|
| 282 |
+
"language_model.model.layers.31.mlp.down_proj",
|
| 283 |
+
"language_model.model.layers.31.mlp.gate_proj",
|
| 284 |
+
"language_model.model.layers.31.mlp.up_proj",
|
| 285 |
+
"language_model.model.layers.31.self_attn.k_proj",
|
| 286 |
+
"language_model.model.layers.31.self_attn.o_proj",
|
| 287 |
+
"language_model.model.layers.31.self_attn.q_proj",
|
| 288 |
+
"language_model.model.layers.31.self_attn.v_proj",
|
| 289 |
+
"language_model.model.layers.32.linear_attn.in_proj_a",
|
| 290 |
+
"language_model.model.layers.32.linear_attn.in_proj_b",
|
| 291 |
+
"language_model.model.layers.32.linear_attn.in_proj_qkv",
|
| 292 |
+
"language_model.model.layers.32.linear_attn.in_proj_z",
|
| 293 |
+
"language_model.model.layers.32.linear_attn.out_proj",
|
| 294 |
+
"language_model.model.layers.32.mlp.down_proj",
|
| 295 |
+
"language_model.model.layers.32.mlp.gate_proj",
|
| 296 |
+
"language_model.model.layers.32.mlp.up_proj",
|
| 297 |
+
"language_model.model.layers.33.linear_attn.in_proj_a",
|
| 298 |
+
"language_model.model.layers.33.linear_attn.in_proj_b",
|
| 299 |
+
"language_model.model.layers.33.linear_attn.in_proj_qkv",
|
| 300 |
+
"language_model.model.layers.33.linear_attn.in_proj_z",
|
| 301 |
+
"language_model.model.layers.33.linear_attn.out_proj",
|
| 302 |
+
"language_model.model.layers.33.mlp.down_proj",
|
| 303 |
+
"language_model.model.layers.33.mlp.gate_proj",
|
| 304 |
+
"language_model.model.layers.33.mlp.up_proj",
|
| 305 |
+
"language_model.model.layers.34.linear_attn.in_proj_a",
|
| 306 |
+
"language_model.model.layers.34.linear_attn.in_proj_b",
|
| 307 |
+
"language_model.model.layers.34.linear_attn.in_proj_qkv",
|
| 308 |
+
"language_model.model.layers.34.linear_attn.in_proj_z",
|
| 309 |
+
"language_model.model.layers.34.linear_attn.out_proj",
|
| 310 |
+
"language_model.model.layers.34.mlp.down_proj",
|
| 311 |
+
"language_model.model.layers.34.mlp.gate_proj",
|
| 312 |
+
"language_model.model.layers.34.mlp.up_proj",
|
| 313 |
+
"language_model.model.layers.35.mlp.down_proj",
|
| 314 |
+
"language_model.model.layers.35.mlp.gate_proj",
|
| 315 |
+
"language_model.model.layers.35.mlp.up_proj",
|
| 316 |
+
"language_model.model.layers.35.self_attn.k_proj",
|
| 317 |
+
"language_model.model.layers.35.self_attn.o_proj",
|
| 318 |
+
"language_model.model.layers.35.self_attn.q_proj",
|
| 319 |
+
"language_model.model.layers.35.self_attn.v_proj",
|
| 320 |
+
"language_model.model.layers.36.linear_attn.in_proj_a",
|
| 321 |
+
"language_model.model.layers.36.linear_attn.in_proj_b",
|
| 322 |
+
"language_model.model.layers.36.linear_attn.in_proj_qkv",
|
| 323 |
+
"language_model.model.layers.36.linear_attn.in_proj_z",
|
| 324 |
+
"language_model.model.layers.36.linear_attn.out_proj",
|
| 325 |
+
"language_model.model.layers.36.mlp.down_proj",
|
| 326 |
+
"language_model.model.layers.36.mlp.gate_proj",
|
| 327 |
+
"language_model.model.layers.36.mlp.up_proj",
|
| 328 |
+
"language_model.model.layers.37.linear_attn.in_proj_a",
|
| 329 |
+
"language_model.model.layers.37.linear_attn.in_proj_b",
|
| 330 |
+
"language_model.model.layers.37.linear_attn.in_proj_qkv",
|
| 331 |
+
"language_model.model.layers.37.linear_attn.in_proj_z",
|
| 332 |
+
"language_model.model.layers.37.linear_attn.out_proj",
|
| 333 |
+
"language_model.model.layers.37.mlp.down_proj",
|
| 334 |
+
"language_model.model.layers.37.mlp.gate_proj",
|
| 335 |
+
"language_model.model.layers.37.mlp.up_proj",
|
| 336 |
+
"language_model.model.layers.38.linear_attn.in_proj_a",
|
| 337 |
+
"language_model.model.layers.38.linear_attn.in_proj_b",
|
| 338 |
+
"language_model.model.layers.38.linear_attn.in_proj_qkv",
|
| 339 |
+
"language_model.model.layers.38.linear_attn.in_proj_z",
|
| 340 |
+
"language_model.model.layers.38.linear_attn.out_proj",
|
| 341 |
+
"language_model.model.layers.38.mlp.down_proj",
|
| 342 |
+
"language_model.model.layers.38.mlp.gate_proj",
|
| 343 |
+
"language_model.model.layers.38.mlp.up_proj",
|
| 344 |
+
"language_model.model.layers.39.mlp.down_proj",
|
| 345 |
+
"language_model.model.layers.39.mlp.gate_proj",
|
| 346 |
+
"language_model.model.layers.39.mlp.up_proj",
|
| 347 |
+
"language_model.model.layers.39.self_attn.k_proj",
|
| 348 |
+
"language_model.model.layers.39.self_attn.o_proj",
|
| 349 |
+
"language_model.model.layers.39.self_attn.q_proj",
|
| 350 |
+
"language_model.model.layers.39.self_attn.v_proj",
|
| 351 |
+
"language_model.model.layers.4.linear_attn.in_proj_a",
|
| 352 |
+
"language_model.model.layers.4.linear_attn.in_proj_b",
|
| 353 |
+
"language_model.model.layers.4.linear_attn.in_proj_qkv",
|
| 354 |
+
"language_model.model.layers.4.linear_attn.in_proj_z",
|
| 355 |
+
"language_model.model.layers.4.linear_attn.out_proj",
|
| 356 |
+
"language_model.model.layers.4.mlp.down_proj",
|
| 357 |
+
"language_model.model.layers.4.mlp.gate_proj",
|
| 358 |
+
"language_model.model.layers.4.mlp.up_proj",
|
| 359 |
+
"language_model.model.layers.40.linear_attn.in_proj_a",
|
| 360 |
+
"language_model.model.layers.40.linear_attn.in_proj_b",
|
| 361 |
+
"language_model.model.layers.40.linear_attn.in_proj_qkv",
|
| 362 |
+
"language_model.model.layers.40.linear_attn.in_proj_z",
|
| 363 |
+
"language_model.model.layers.40.linear_attn.out_proj",
|
| 364 |
+
"language_model.model.layers.40.mlp.down_proj",
|
| 365 |
+
"language_model.model.layers.40.mlp.gate_proj",
|
| 366 |
+
"language_model.model.layers.40.mlp.up_proj",
|
| 367 |
+
"language_model.model.layers.41.linear_attn.in_proj_a",
|
| 368 |
+
"language_model.model.layers.41.linear_attn.in_proj_b",
|
| 369 |
+
"language_model.model.layers.41.linear_attn.in_proj_qkv",
|
| 370 |
+
"language_model.model.layers.41.linear_attn.in_proj_z",
|
| 371 |
+
"language_model.model.layers.41.linear_attn.out_proj",
|
| 372 |
+
"language_model.model.layers.41.mlp.down_proj",
|
| 373 |
+
"language_model.model.layers.41.mlp.gate_proj",
|
| 374 |
+
"language_model.model.layers.41.mlp.up_proj",
|
| 375 |
+
"language_model.model.layers.42.linear_attn.in_proj_a",
|
| 376 |
+
"language_model.model.layers.42.linear_attn.in_proj_b",
|
| 377 |
+
"language_model.model.layers.42.linear_attn.in_proj_qkv",
|
| 378 |
+
"language_model.model.layers.42.linear_attn.in_proj_z",
|
| 379 |
+
"language_model.model.layers.42.linear_attn.out_proj",
|
| 380 |
+
"language_model.model.layers.42.mlp.down_proj",
|
| 381 |
+
"language_model.model.layers.42.mlp.gate_proj",
|
| 382 |
+
"language_model.model.layers.42.mlp.up_proj",
|
| 383 |
+
"language_model.model.layers.43.mlp.down_proj",
|
| 384 |
+
"language_model.model.layers.43.mlp.gate_proj",
|
| 385 |
+
"language_model.model.layers.43.mlp.up_proj",
|
| 386 |
+
"language_model.model.layers.43.self_attn.k_proj",
|
| 387 |
+
"language_model.model.layers.43.self_attn.o_proj",
|
| 388 |
+
"language_model.model.layers.43.self_attn.q_proj",
|
| 389 |
+
"language_model.model.layers.43.self_attn.v_proj",
|
| 390 |
+
"language_model.model.layers.44.linear_attn.in_proj_a",
|
| 391 |
+
"language_model.model.layers.44.linear_attn.in_proj_b",
|
| 392 |
+
"language_model.model.layers.44.linear_attn.in_proj_qkv",
|
| 393 |
+
"language_model.model.layers.44.linear_attn.in_proj_z",
|
| 394 |
+
"language_model.model.layers.44.linear_attn.out_proj",
|
| 395 |
+
"language_model.model.layers.44.mlp.down_proj",
|
| 396 |
+
"language_model.model.layers.44.mlp.gate_proj",
|
| 397 |
+
"language_model.model.layers.44.mlp.up_proj",
|
| 398 |
+
"language_model.model.layers.45.linear_attn.in_proj_a",
|
| 399 |
+
"language_model.model.layers.45.linear_attn.in_proj_b",
|
| 400 |
+
"language_model.model.layers.45.linear_attn.in_proj_qkv",
|
| 401 |
+
"language_model.model.layers.45.linear_attn.in_proj_z",
|
| 402 |
+
"language_model.model.layers.45.linear_attn.out_proj",
|
| 403 |
+
"language_model.model.layers.45.mlp.down_proj",
|
| 404 |
+
"language_model.model.layers.45.mlp.gate_proj",
|
| 405 |
+
"language_model.model.layers.45.mlp.up_proj",
|
| 406 |
+
"language_model.model.layers.46.linear_attn.in_proj_a",
|
| 407 |
+
"language_model.model.layers.46.linear_attn.in_proj_b",
|
| 408 |
+
"language_model.model.layers.46.linear_attn.in_proj_qkv",
|
| 409 |
+
"language_model.model.layers.46.linear_attn.in_proj_z",
|
| 410 |
+
"language_model.model.layers.46.linear_attn.out_proj",
|
| 411 |
+
"language_model.model.layers.46.mlp.down_proj",
|
| 412 |
+
"language_model.model.layers.46.mlp.gate_proj",
|
| 413 |
+
"language_model.model.layers.46.mlp.up_proj",
|
| 414 |
+
"language_model.model.layers.47.mlp.down_proj",
|
| 415 |
+
"language_model.model.layers.47.mlp.gate_proj",
|
| 416 |
+
"language_model.model.layers.47.mlp.up_proj",
|
| 417 |
+
"language_model.model.layers.47.self_attn.k_proj",
|
| 418 |
+
"language_model.model.layers.47.self_attn.o_proj",
|
| 419 |
+
"language_model.model.layers.47.self_attn.q_proj",
|
| 420 |
+
"language_model.model.layers.47.self_attn.v_proj",
|
| 421 |
+
"language_model.model.layers.48.linear_attn.in_proj_a",
|
| 422 |
+
"language_model.model.layers.48.linear_attn.in_proj_b",
|
| 423 |
+
"language_model.model.layers.48.linear_attn.in_proj_qkv",
|
| 424 |
+
"language_model.model.layers.48.linear_attn.in_proj_z",
|
| 425 |
+
"language_model.model.layers.48.linear_attn.out_proj",
|
| 426 |
+
"language_model.model.layers.48.mlp.down_proj",
|
| 427 |
+
"language_model.model.layers.48.mlp.gate_proj",
|
| 428 |
+
"language_model.model.layers.48.mlp.up_proj",
|
| 429 |
+
"language_model.model.layers.49.linear_attn.in_proj_a",
|
| 430 |
+
"language_model.model.layers.49.linear_attn.in_proj_b",
|
| 431 |
+
"language_model.model.layers.49.linear_attn.in_proj_qkv",
|
| 432 |
+
"language_model.model.layers.49.linear_attn.in_proj_z",
|
| 433 |
+
"language_model.model.layers.49.linear_attn.out_proj",
|
| 434 |
+
"language_model.model.layers.49.mlp.down_proj",
|
| 435 |
+
"language_model.model.layers.49.mlp.gate_proj",
|
| 436 |
+
"language_model.model.layers.49.mlp.up_proj",
|
| 437 |
+
"language_model.model.layers.5.linear_attn.in_proj_a",
|
| 438 |
+
"language_model.model.layers.5.linear_attn.in_proj_b",
|
| 439 |
+
"language_model.model.layers.5.linear_attn.in_proj_qkv",
|
| 440 |
+
"language_model.model.layers.5.linear_attn.in_proj_z",
|
| 441 |
+
"language_model.model.layers.5.linear_attn.out_proj",
|
| 442 |
+
"language_model.model.layers.5.mlp.down_proj",
|
| 443 |
+
"language_model.model.layers.5.mlp.gate_proj",
|
| 444 |
+
"language_model.model.layers.5.mlp.up_proj",
|
| 445 |
+
"language_model.model.layers.50.linear_attn.in_proj_a",
|
| 446 |
+
"language_model.model.layers.50.linear_attn.in_proj_b",
|
| 447 |
+
"language_model.model.layers.50.linear_attn.in_proj_qkv",
|
| 448 |
+
"language_model.model.layers.50.linear_attn.in_proj_z",
|
| 449 |
+
"language_model.model.layers.50.linear_attn.out_proj",
|
| 450 |
+
"language_model.model.layers.50.mlp.down_proj",
|
| 451 |
+
"language_model.model.layers.50.mlp.gate_proj",
|
| 452 |
+
"language_model.model.layers.50.mlp.up_proj",
|
| 453 |
+
"language_model.model.layers.51.mlp.down_proj",
|
| 454 |
+
"language_model.model.layers.51.mlp.gate_proj",
|
| 455 |
+
"language_model.model.layers.51.mlp.up_proj",
|
| 456 |
+
"language_model.model.layers.51.self_attn.k_proj",
|
| 457 |
+
"language_model.model.layers.51.self_attn.o_proj",
|
| 458 |
+
"language_model.model.layers.51.self_attn.q_proj",
|
| 459 |
+
"language_model.model.layers.51.self_attn.v_proj",
|
| 460 |
+
"language_model.model.layers.52.linear_attn.in_proj_a",
|
| 461 |
+
"language_model.model.layers.52.linear_attn.in_proj_b",
|
| 462 |
+
"language_model.model.layers.52.linear_attn.in_proj_qkv",
|
| 463 |
+
"language_model.model.layers.52.linear_attn.in_proj_z",
|
| 464 |
+
"language_model.model.layers.52.linear_attn.out_proj",
|
| 465 |
+
"language_model.model.layers.52.mlp.down_proj",
|
| 466 |
+
"language_model.model.layers.52.mlp.gate_proj",
|
| 467 |
+
"language_model.model.layers.52.mlp.up_proj",
|
| 468 |
+
"language_model.model.layers.53.linear_attn.in_proj_a",
|
| 469 |
+
"language_model.model.layers.53.linear_attn.in_proj_b",
|
| 470 |
+
"language_model.model.layers.53.linear_attn.in_proj_qkv",
|
| 471 |
+
"language_model.model.layers.53.linear_attn.in_proj_z",
|
| 472 |
+
"language_model.model.layers.53.linear_attn.out_proj",
|
| 473 |
+
"language_model.model.layers.53.mlp.down_proj",
|
| 474 |
+
"language_model.model.layers.53.mlp.gate_proj",
|
| 475 |
+
"language_model.model.layers.53.mlp.up_proj",
|
| 476 |
+
"language_model.model.layers.54.linear_attn.in_proj_a",
|
| 477 |
+
"language_model.model.layers.54.linear_attn.in_proj_b",
|
| 478 |
+
"language_model.model.layers.54.linear_attn.in_proj_qkv",
|
| 479 |
+
"language_model.model.layers.54.linear_attn.in_proj_z",
|
| 480 |
+
"language_model.model.layers.54.linear_attn.out_proj",
|
| 481 |
+
"language_model.model.layers.54.mlp.down_proj",
|
| 482 |
+
"language_model.model.layers.54.mlp.gate_proj",
|
| 483 |
+
"language_model.model.layers.54.mlp.up_proj",
|
| 484 |
+
"language_model.model.layers.55.mlp.down_proj",
|
| 485 |
+
"language_model.model.layers.55.mlp.gate_proj",
|
| 486 |
+
"language_model.model.layers.55.mlp.up_proj",
|
| 487 |
+
"language_model.model.layers.55.self_attn.k_proj",
|
| 488 |
+
"language_model.model.layers.55.self_attn.o_proj",
|
| 489 |
+
"language_model.model.layers.55.self_attn.q_proj",
|
| 490 |
+
"language_model.model.layers.55.self_attn.v_proj",
|
| 491 |
+
"language_model.model.layers.56.linear_attn.in_proj_a",
|
| 492 |
+
"language_model.model.layers.56.linear_attn.in_proj_b",
|
| 493 |
+
"language_model.model.layers.56.linear_attn.in_proj_qkv",
|
| 494 |
+
"language_model.model.layers.56.linear_attn.in_proj_z",
|
| 495 |
+
"language_model.model.layers.56.linear_attn.out_proj",
|
| 496 |
+
"language_model.model.layers.56.mlp.down_proj",
|
| 497 |
+
"language_model.model.layers.56.mlp.gate_proj",
|
| 498 |
+
"language_model.model.layers.56.mlp.up_proj",
|
| 499 |
+
"language_model.model.layers.57.linear_attn.in_proj_a",
|
| 500 |
+
"language_model.model.layers.57.linear_attn.in_proj_b",
|
| 501 |
+
"language_model.model.layers.57.linear_attn.in_proj_qkv",
|
| 502 |
+
"language_model.model.layers.57.linear_attn.in_proj_z",
|
| 503 |
+
"language_model.model.layers.57.linear_attn.out_proj",
|
| 504 |
+
"language_model.model.layers.57.mlp.down_proj",
|
| 505 |
+
"language_model.model.layers.57.mlp.gate_proj",
|
| 506 |
+
"language_model.model.layers.57.mlp.up_proj",
|
| 507 |
+
"language_model.model.layers.58.linear_attn.in_proj_a",
|
| 508 |
+
"language_model.model.layers.58.linear_attn.in_proj_b",
|
| 509 |
+
"language_model.model.layers.58.linear_attn.in_proj_qkv",
|
| 510 |
+
"language_model.model.layers.58.linear_attn.in_proj_z",
|
| 511 |
+
"language_model.model.layers.58.linear_attn.out_proj",
|
| 512 |
+
"language_model.model.layers.58.mlp.down_proj",
|
| 513 |
+
"language_model.model.layers.58.mlp.gate_proj",
|
| 514 |
+
"language_model.model.layers.58.mlp.up_proj",
|
| 515 |
+
"language_model.model.layers.59.mlp.down_proj",
|
| 516 |
+
"language_model.model.layers.59.mlp.gate_proj",
|
| 517 |
+
"language_model.model.layers.59.mlp.up_proj",
|
| 518 |
+
"language_model.model.layers.59.self_attn.k_proj",
|
| 519 |
+
"language_model.model.layers.59.self_attn.o_proj",
|
| 520 |
+
"language_model.model.layers.59.self_attn.q_proj",
|
| 521 |
+
"language_model.model.layers.59.self_attn.v_proj",
|
| 522 |
+
"language_model.model.layers.6.linear_attn.in_proj_a",
|
| 523 |
+
"language_model.model.layers.6.linear_attn.in_proj_b",
|
| 524 |
+
"language_model.model.layers.6.linear_attn.in_proj_qkv",
|
| 525 |
+
"language_model.model.layers.6.linear_attn.in_proj_z",
|
| 526 |
+
"language_model.model.layers.6.linear_attn.out_proj",
|
| 527 |
+
"language_model.model.layers.6.mlp.down_proj",
|
| 528 |
+
"language_model.model.layers.6.mlp.gate_proj",
|
| 529 |
+
"language_model.model.layers.6.mlp.up_proj",
|
| 530 |
+
"language_model.model.layers.60.linear_attn.in_proj_a",
|
| 531 |
+
"language_model.model.layers.60.linear_attn.in_proj_b",
|
| 532 |
+
"language_model.model.layers.60.linear_attn.in_proj_qkv",
|
| 533 |
+
"language_model.model.layers.60.linear_attn.in_proj_z",
|
| 534 |
+
"language_model.model.layers.60.linear_attn.out_proj",
|
| 535 |
+
"language_model.model.layers.60.mlp.down_proj",
|
| 536 |
+
"language_model.model.layers.60.mlp.gate_proj",
|
| 537 |
+
"language_model.model.layers.60.mlp.up_proj",
|
| 538 |
+
"language_model.model.layers.61.linear_attn.in_proj_a",
|
| 539 |
+
"language_model.model.layers.61.linear_attn.in_proj_b",
|
| 540 |
+
"language_model.model.layers.61.linear_attn.in_proj_qkv",
|
| 541 |
+
"language_model.model.layers.61.linear_attn.in_proj_z",
|
| 542 |
+
"language_model.model.layers.61.linear_attn.out_proj",
|
| 543 |
+
"language_model.model.layers.61.mlp.down_proj",
|
| 544 |
+
"language_model.model.layers.61.mlp.gate_proj",
|
| 545 |
+
"language_model.model.layers.61.mlp.up_proj",
|
| 546 |
+
"language_model.model.layers.62.linear_attn.in_proj_a",
|
| 547 |
+
"language_model.model.layers.62.linear_attn.in_proj_b",
|
| 548 |
+
"language_model.model.layers.62.linear_attn.in_proj_qkv",
|
| 549 |
+
"language_model.model.layers.62.linear_attn.in_proj_z",
|
| 550 |
+
"language_model.model.layers.62.linear_attn.out_proj",
|
| 551 |
+
"language_model.model.layers.62.mlp.down_proj",
|
| 552 |
+
"language_model.model.layers.62.mlp.gate_proj",
|
| 553 |
+
"language_model.model.layers.62.mlp.up_proj",
|
| 554 |
+
"language_model.model.layers.63.mlp.down_proj",
|
| 555 |
+
"language_model.model.layers.63.mlp.gate_proj",
|
| 556 |
+
"language_model.model.layers.63.mlp.up_proj",
|
| 557 |
+
"language_model.model.layers.63.self_attn.k_proj",
|
| 558 |
+
"language_model.model.layers.63.self_attn.o_proj",
|
| 559 |
+
"language_model.model.layers.63.self_attn.q_proj",
|
| 560 |
+
"language_model.model.layers.63.self_attn.v_proj",
|
| 561 |
+
"language_model.model.layers.7.mlp.down_proj",
|
| 562 |
+
"language_model.model.layers.7.mlp.gate_proj",
|
| 563 |
+
"language_model.model.layers.7.mlp.up_proj",
|
| 564 |
+
"language_model.model.layers.7.self_attn.k_proj",
|
| 565 |
+
"language_model.model.layers.7.self_attn.o_proj",
|
| 566 |
+
"language_model.model.layers.7.self_attn.q_proj",
|
| 567 |
+
"language_model.model.layers.7.self_attn.v_proj",
|
| 568 |
+
"language_model.model.layers.8.linear_attn.in_proj_a",
|
| 569 |
+
"language_model.model.layers.8.linear_attn.in_proj_b",
|
| 570 |
+
"language_model.model.layers.8.linear_attn.in_proj_qkv",
|
| 571 |
+
"language_model.model.layers.8.linear_attn.in_proj_z",
|
| 572 |
+
"language_model.model.layers.8.linear_attn.out_proj",
|
| 573 |
+
"language_model.model.layers.8.mlp.down_proj",
|
| 574 |
+
"language_model.model.layers.8.mlp.gate_proj",
|
| 575 |
+
"language_model.model.layers.8.mlp.up_proj",
|
| 576 |
+
"language_model.model.layers.9.linear_attn.in_proj_a",
|
| 577 |
+
"language_model.model.layers.9.linear_attn.in_proj_b",
|
| 578 |
+
"language_model.model.layers.9.linear_attn.in_proj_qkv",
|
| 579 |
+
"language_model.model.layers.9.linear_attn.in_proj_z",
|
| 580 |
+
"language_model.model.layers.9.linear_attn.out_proj",
|
| 581 |
+
"language_model.model.layers.9.mlp.down_proj",
|
| 582 |
+
"language_model.model.layers.9.mlp.gate_proj",
|
| 583 |
+
"language_model.model.layers.9.mlp.up_proj"
|
| 584 |
+
],
|
| 585 |
+
"missing": [
|
| 586 |
+
"language_model.lm_head",
|
| 587 |
+
"language_model.model.embed_tokens"
|
| 588 |
+
],
|
| 589 |
+
"mismatched": [],
|
| 590 |
+
"zero_count_experts": 0
|
| 591 |
+
}
|
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 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 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 |
+
"tool_parser_type": "qwen3_coder",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|