Add files using upload-large-folder tool
Browse files- .gitattributes +4 -0
- LICENSE +201 -0
- LICENSE-NOTE.md +18 -0
- README.md +259 -0
- SHA256SUMS +25 -0
- config.json +79 -0
- julia_config.json +8 -0
- macos/fp32-s1024/julia1_fp32_s1024.aimodel/main.hash +2 -0
- macos/fp32-s1024/julia1_fp32_s1024.aimodel/main.mlirb +3 -0
- macos/fp32-s1024/julia1_fp32_s1024.aimodel/metadata.json +8 -0
- macos/fp32-s1024/metadata.json +81 -0
- macos/fp32-s1024/provenance/export-gate.json +0 -0
- macos/fp32-s1024/provenance/export-manifest.json +160 -0
- macos/fp32-s1024/provenance/runtime-gate.json +0 -0
- macos/fp32-s1024/reference.json +0 -0
- macos/fp32-s1024/tokenizer/tokenizer.json +3 -0
- macos/fp32-s1024/tokenizer/tokenizer_config.json +28 -0
- macos/fp32-s512/julia1_fp32_s512.aimodel/main.hash +1 -0
- macos/fp32-s512/julia1_fp32_s512.aimodel/main.mlirb +3 -0
- macos/fp32-s512/julia1_fp32_s512.aimodel/metadata.json +8 -0
- macos/fp32-s512/metadata.json +81 -0
- macos/fp32-s512/provenance/export-gate.json +0 -0
- macos/fp32-s512/provenance/export-manifest.json +160 -0
- macos/fp32-s512/provenance/runtime-gate.json +0 -0
- macos/fp32-s512/reference.json +0 -0
- macos/fp32-s512/tokenizer/tokenizer.json +3 -0
- macos/fp32-s512/tokenizer/tokenizer_config.json +28 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,7 @@ 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 |
+
macos/fp32-s1024/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
macos/fp32-s512/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
macos/fp32-s512/julia1_fp32_s512.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
macos/fp32-s1024/julia1_fp32_s1024.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
|
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Apache License
|
| 2 |
+
Version 2.0, January 2004
|
| 3 |
+
http://www.apache.org/licenses/
|
| 4 |
+
|
| 5 |
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
| 6 |
+
|
| 7 |
+
1. Definitions.
|
| 8 |
+
|
| 9 |
+
"License" shall mean the terms and conditions for use, reproduction,
|
| 10 |
+
and distribution as defined by Sections 1 through 9 of this document.
|
| 11 |
+
|
| 12 |
+
"Licensor" shall mean the copyright owner or entity authorized by
|
| 13 |
+
the copyright owner that is granting the License.
|
| 14 |
+
|
| 15 |
+
"Legal Entity" shall mean the union of the acting entity and all
|
| 16 |
+
other entities that control, are controlled by, or are under common
|
| 17 |
+
control with that entity. For the purposes of this definition,
|
| 18 |
+
"control" means (i) the power, direct or indirect, to cause the
|
| 19 |
+
direction or management of such entity, whether by contract or
|
| 20 |
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
| 21 |
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
| 22 |
+
|
| 23 |
+
"You" (or "Your") shall mean an individual or Legal Entity
|
| 24 |
+
exercising permissions granted by this License.
|
| 25 |
+
|
| 26 |
+
"Source" form shall mean the preferred form for making modifications,
|
| 27 |
+
including but not limited to software source code, documentation
|
| 28 |
+
source, and configuration files.
|
| 29 |
+
|
| 30 |
+
"Object" form shall mean any form resulting from mechanical
|
| 31 |
+
transformation or translation of a Source form, including but
|
| 32 |
+
not limited to compiled object code, generated documentation,
|
| 33 |
+
and conversions to other media types.
|
| 34 |
+
|
| 35 |
+
"Work" shall mean the work of authorship, whether in Source or
|
| 36 |
+
Object form, made available under the License, as indicated by a
|
| 37 |
+
copyright notice that is included in or attached to the work
|
| 38 |
+
(an example is provided in the Appendix below).
|
| 39 |
+
|
| 40 |
+
"Derivative Works" shall mean any work, whether in Source or Object
|
| 41 |
+
form, that is based on (or derived from) the Work and for which the
|
| 42 |
+
editorial revisions, annotations, elaborations, or other modifications
|
| 43 |
+
represent, as a whole, an original work of authorship. For the purposes
|
| 44 |
+
of this License, Derivative Works shall not include works that remain
|
| 45 |
+
separable from, or merely link (or bind by name) to the interfaces of,
|
| 46 |
+
the Work and Derivative Works thereof.
|
| 47 |
+
|
| 48 |
+
"Contribution" shall mean any work of authorship, including
|
| 49 |
+
the original version of the Work and any modifications or additions
|
| 50 |
+
to that Work or Derivative Works thereof, that is intentionally
|
| 51 |
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
| 52 |
+
or by an individual or Legal Entity authorized to submit on behalf of
|
| 53 |
+
the copyright owner. For the purposes of this definition, "submitted"
|
| 54 |
+
means any form of electronic, verbal, or written communication sent
|
| 55 |
+
to the Licensor or its representatives, including but not limited to
|
| 56 |
+
communication on electronic mailing lists, source code control systems,
|
| 57 |
+
and issue tracking systems that are managed by, or on behalf of, the
|
| 58 |
+
Licensor for the purpose of discussing and improving the Work, but
|
| 59 |
+
excluding communication that is conspicuously marked or otherwise
|
| 60 |
+
designated in writing by the copyright owner as "Not a Contribution."
|
| 61 |
+
|
| 62 |
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
| 63 |
+
on behalf of whom a Contribution has been received by Licensor and
|
| 64 |
+
subsequently incorporated within the Work.
|
| 65 |
+
|
| 66 |
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
| 67 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 68 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 69 |
+
copyright license to reproduce, prepare Derivative Works of,
|
| 70 |
+
publicly display, publicly perform, sublicense, and distribute the
|
| 71 |
+
Work and such Derivative Works in Source or Object form.
|
| 72 |
+
|
| 73 |
+
3. Grant of Patent License. Subject to the terms and conditions of
|
| 74 |
+
this License, each Contributor hereby grants to You a perpetual,
|
| 75 |
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
| 76 |
+
(except as stated in this section) patent license to make, have made,
|
| 77 |
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
| 78 |
+
where such license applies only to those patent claims licensable
|
| 79 |
+
by such Contributor that are necessarily infringed by their
|
| 80 |
+
Contribution(s) alone or by combination of their Contribution(s)
|
| 81 |
+
with the Work to which such Contribution(s) was submitted. If You
|
| 82 |
+
institute patent litigation against any entity (including a
|
| 83 |
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
| 84 |
+
or a Contribution incorporated within the Work constitutes direct
|
| 85 |
+
or contributory patent infringement, then any patent licenses
|
| 86 |
+
granted to You under this License for that Work shall terminate
|
| 87 |
+
as of the date such litigation is filed.
|
| 88 |
+
|
| 89 |
+
4. Redistribution. You may reproduce and distribute copies of the
|
| 90 |
+
Work or Derivative Works thereof in any medium, with or without
|
| 91 |
+
modifications, and in Source or Object form, provided that You
|
| 92 |
+
meet the following conditions:
|
| 93 |
+
|
| 94 |
+
(a) You must give any other recipients of the Work or
|
| 95 |
+
Derivative Works a copy of this License; and
|
| 96 |
+
|
| 97 |
+
(b) You must cause any modified files to carry prominent notices
|
| 98 |
+
stating that You changed the files; and
|
| 99 |
+
|
| 100 |
+
(c) You must retain, in the Source form of any Derivative Works
|
| 101 |
+
that You distribute, all copyright, patent, trademark, and
|
| 102 |
+
attribution notices from the Source form of the Work,
|
| 103 |
+
excluding those notices that do not pertain to any part of
|
| 104 |
+
the Derivative Works; and
|
| 105 |
+
|
| 106 |
+
(d) If the Work includes a "NOTICE" text file as part of its
|
| 107 |
+
distribution, then any Derivative Works that You distribute must
|
| 108 |
+
include a readable copy of the attribution notices contained
|
| 109 |
+
within such NOTICE file, excluding those notices that do not
|
| 110 |
+
pertain to any part of the Derivative Works, in at least one
|
| 111 |
+
of the following places: within a NOTICE text file distributed
|
| 112 |
+
as part of the Derivative Works; within the Source form or
|
| 113 |
+
documentation, if provided along with the Derivative Works; or,
|
| 114 |
+
within a display generated by the Derivative Works, if and
|
| 115 |
+
wherever such third-party notices normally appear. The contents
|
| 116 |
+
of the NOTICE file are for informational purposes only and
|
| 117 |
+
do not modify the License. You may add Your own attribution
|
| 118 |
+
notices within Derivative Works that You distribute, alongside
|
| 119 |
+
or as an addendum to the NOTICE text from the Work, provided
|
| 120 |
+
that such additional attribution notices cannot be construed
|
| 121 |
+
as modifying the License.
|
| 122 |
+
|
| 123 |
+
You may add Your own copyright statement to Your modifications and
|
| 124 |
+
may provide additional or different license terms and conditions
|
| 125 |
+
for use, reproduction, or distribution of Your modifications, or
|
| 126 |
+
for any such Derivative Works as a whole, provided Your use,
|
| 127 |
+
reproduction, and distribution of the Work otherwise complies with
|
| 128 |
+
the conditions stated in this License.
|
| 129 |
+
|
| 130 |
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
| 131 |
+
any Contribution intentionally submitted for inclusion in the Work
|
| 132 |
+
by You to the Licensor shall be under the terms and conditions of
|
| 133 |
+
this License, without any additional terms or conditions.
|
| 134 |
+
Notwithstanding the above, nothing herein shall supersede or modify
|
| 135 |
+
the terms of any separate license agreement you may have executed
|
| 136 |
+
with Licensor regarding such Contributions.
|
| 137 |
+
|
| 138 |
+
6. Trademarks. This License does not grant permission to use the trade
|
| 139 |
+
names, trademarks, service marks, or product names of the Licensor,
|
| 140 |
+
except as required for reasonable and customary use in describing the
|
| 141 |
+
origin of the Work and reproducing the content of the NOTICE file.
|
| 142 |
+
|
| 143 |
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
| 144 |
+
agreed to in writing, Licensor provides the Work (and each
|
| 145 |
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
| 146 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
| 147 |
+
implied, including, without limitation, any warranties or conditions
|
| 148 |
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
| 149 |
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
| 150 |
+
appropriateness of using or redistributing the Work and assume any
|
| 151 |
+
risks associated with Your exercise of permissions under this License.
|
| 152 |
+
|
| 153 |
+
8. Limitation of Liability. In no event and under no legal theory,
|
| 154 |
+
whether in tort (including negligence), contract, or otherwise,
|
| 155 |
+
unless required by applicable law (such as deliberate and grossly
|
| 156 |
+
negligent acts) or agreed to in writing, shall any Contributor be
|
| 157 |
+
liable to You for damages, including any direct, indirect, special,
|
| 158 |
+
incidental, or consequential damages of any character arising as a
|
| 159 |
+
result of this License or out of the use or inability to use the
|
| 160 |
+
Work (including but not limited to damages for loss of goodwill,
|
| 161 |
+
work stoppage, computer failure or malfunction, or any and all
|
| 162 |
+
other commercial damages or losses), even if such Contributor
|
| 163 |
+
has been advised of the possibility of such damages.
|
| 164 |
+
|
| 165 |
+
9. Accepting Warranty or Additional Liability. While redistributing
|
| 166 |
+
the Work or Derivative Works thereof, You may choose to offer,
|
| 167 |
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
| 168 |
+
or other liability obligations and/or rights consistent with this
|
| 169 |
+
License. However, in accepting such obligations, You may act only
|
| 170 |
+
on Your own behalf and on Your sole responsibility, not on behalf
|
| 171 |
+
of any other Contributor, and only if You agree to indemnify,
|
| 172 |
+
defend, and hold each Contributor harmless for any liability
|
| 173 |
+
incurred by, or claims asserted against, such Contributor by reason
|
| 174 |
+
of your accepting any such warranty or additional liability.
|
| 175 |
+
|
| 176 |
+
END OF TERMS AND CONDITIONS
|
| 177 |
+
|
| 178 |
+
APPENDIX: How to apply the Apache License to your work.
|
| 179 |
+
|
| 180 |
+
To apply the Apache License to your work, attach the following
|
| 181 |
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
| 182 |
+
replaced with your own identifying information. (Don't include
|
| 183 |
+
the brackets!) The text should be enclosed in the appropriate
|
| 184 |
+
comment syntax for the file format. We also recommend that a
|
| 185 |
+
file or class name and description of purpose be included on the
|
| 186 |
+
same "printed page" as the copyright notice for easier
|
| 187 |
+
identification within third-party archives.
|
| 188 |
+
|
| 189 |
+
Copyright [yyyy] [name of copyright owner]
|
| 190 |
+
|
| 191 |
+
Licensed under the Apache License, Version 2.0 (the "License");
|
| 192 |
+
you may not use this file except in compliance with the License.
|
| 193 |
+
You may obtain a copy of the License at
|
| 194 |
+
|
| 195 |
+
http://www.apache.org/licenses/LICENSE-2.0
|
| 196 |
+
|
| 197 |
+
Unless required by applicable law or agreed to in writing, software
|
| 198 |
+
distributed under the License is distributed on an "AS IS" BASIS,
|
| 199 |
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 200 |
+
See the License for the specific language governing permissions and
|
| 201 |
+
limitations under the License.
|
LICENSE-NOTE.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# License and changes
|
| 2 |
+
|
| 3 |
+
Supersonic Labs declares Apache-2.0 for `SupersonicLabs/Julia-1` in the upstream model card at the pinned revision
|
| 4 |
+
`a85b127321d580d65176c89ced8273f305745d85` ("The model artifacts are licensed under Apache 2.0"); no standalone LICENSE or NOTICE file is
|
| 5 |
+
listed at that revision. The standard Apache-2.0 text is included as `LICENSE`. The upstream base encoder is
|
| 6 |
+
`jhu-clsp/mmBERT-small` (MIT).
|
| 7 |
+
|
| 8 |
+
Changes relative to the upstream checkpoint:
|
| 9 |
+
- re-authored as a static Core AI graph from the raw weights (no transformers or `julia` package code in the
|
| 10 |
+
graph), batch 1, one function `main` (encoder, type embedding, the two head layers and the scorer at every
|
| 11 |
+
position); the checkpoint's `act_head` and `temperature` buffer, which the upstream inference API does not
|
| 12 |
+
read, are not exported;
|
| 13 |
+
- `fp32` folders keep the weights as published (F32); `wfp16` folders store them in fp16 (rounded) and
|
| 14 |
+
compute in fp32;
|
| 15 |
+
- `tokenizer/` holds the checkpoint's `tokenizer.json` and `tokenizer_config.json`, unmodified;
|
| 16 |
+
`config.json` (the upstream `encoder/config.json`) and `julia_config.json` are the checkpoint's own files,
|
| 17 |
+
unmodified.
|
| 18 |
+
Source: `SupersonicLabs/Julia-1@a85b127321d580d65176c89ced8273f305745d85`.
|
README.md
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: coreai
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: SupersonicLabs/Julia-1
|
| 5 |
+
tags:
|
| 6 |
+
- coreai
|
| 7 |
+
- apple-silicon
|
| 8 |
+
- on-device
|
| 9 |
+
- modernbert
|
| 10 |
+
- decision-model
|
| 11 |
+
- text-classification
|
| 12 |
+
- multilingual
|
| 13 |
+
language:
|
| 14 |
+
- multilingual
|
| 15 |
+
pipeline_tag: text-classification
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
Core AI is Apple's on-device ML runtime in iOS 27 / macOS 27 and the successor to Core ML: PyTorch models are exported with Apple's `coreai-torch` (LLMs: `coreai.llm.export`) into `.aimodel` bundles that run on the GPU or the Neural Engine, e.g. Qwen3-8B 4-bit decodes at 94 tok/s on an M4 Max GPU, MLX 90 under the same protocol ([apple-silicon-llm-bench](https://github.com/john-rocky/apple-silicon-llm-bench), macOS 27 beta, 2026-06).
|
| 19 |
+
|
| 20 |
+
<!-- gen-cards:devicemark begin (managed by scripts/gen-cards + tools/devicemark_row.py — edit cards.json, not this block) -->
|
| 21 |
+
This model has no row on [DeviceMark](https://devicemark.github.io/), the on-device LLM leaderboard.
|
| 22 |
+
<!-- gen-cards:devicemark end -->
|
| 23 |
+
|
| 24 |
+
# Julia-1 — Core AI export
|
| 25 |
+
|
| 26 |
+
Zoo card, recipe and gate transcript: [coreai-model-zoo/models/julia-1](https://github.com/john-rocky/coreai-model-zoo/blob/main/models/julia-1/README.md).
|
| 27 |
+
|
| 28 |
+
[🤗 mlboydaisuke/Julia-1-CoreAI](https://huggingface.co/mlboydaisuke/Julia-1-CoreAI) · Apache-2.0 · source [SupersonicLabs/Julia-1](https://huggingface.co/SupersonicLabs/Julia-1/tree/a85b127321d580d65176c89ced8273f305745d85) (revision `a85b127`) · base jhu-clsp/mmBERT-small
|
| 29 |
+
|
| 30 |
+
This is Supersonic Labs' Julia-1, a 144M typed decision model, as a Core AI `.aimodel` converted with Apple's `coreai-torch`; on the GPU of an Apple M4 Max it takes 16.00 ms per decision at the 1,024-token window, tokenization not included (2026-09-30).
|
| 31 |
+
|
| 32 |
+
Give it a state (a message or a JSON record) and a question with 2 to 20 options you write: pick one (`choice`), place the state on an ordered rubric (`score`), or answer false or true (`noul`). It returns a probability for every option from one forward pass and generates no text.
|
| 33 |
+
|
| 34 |
+
## Graph contract
|
| 35 |
+
|
| 36 |
+
```
|
| 37 |
+
function "main"
|
| 38 |
+
input "input_ids" [1, S] int32 the row, right-padded with PAD 0
|
| 39 |
+
input "attention_mask" [1, S] int32 1 over real tokens, 0 over padding
|
| 40 |
+
input "qtype_onehot" [1, 3] fp32 choice / score / noul
|
| 41 |
+
output "token_logits" [1, S] fp32 the scorer at every position, read at the option markers
|
| 42 |
+
S = 512 or 1024, one bundle per window; batch 1; fp32 weights and compute
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
Inside `main` is the mmBERT-small encoder in the ModernBERT layout: 22 layers, hidden 384, 6 heads × 64,
|
| 46 |
+
GLU MLP 1152, global attention on layers 0, 3, …, 21 and a sliding window of inclusive radius 64 elsewhere,
|
| 47 |
+
RoPE θ 160,000, vocabulary 256,000. After it come the type embedding, two pre-norm transformer layers (384
|
| 48 |
+
wide, 6 heads, ReLU FFN 1536) and the scorer (LayerNorm → Linear → GELU → Linear to one logit).
|
| 49 |
+
|
| 50 |
+
The checkpoint also holds an act head (Linear 388 → 256, GELU, Linear 256 → 2) and a temperature buffer of
|
| 51 |
+
[1, 1, 1]. Neither is in the graph, because the publisher's inference API reads neither: it calls
|
| 52 |
+
`forward(..., return_actions=False)`, uses no temperature, and `inference-policy.json` says `calibration: null`.
|
| 53 |
+
|
| 54 |
+
## Host recipe
|
| 55 |
+
|
| 56 |
+
The row and the readout are the publisher's (`julia/data.py` `sequence()`, `julia/typed.py`). `metadata.json`
|
| 57 |
+
in each folder records them with the window, the head budget and the token ids.
|
| 58 |
+
|
| 59 |
+
- Row: `[CLS 2] tok("{type} question: {instructions}") [SEP 1] ([MASK 4] tok(" " + option)[:48])… [SEP 1]
|
| 60 |
+
tok(state) [SEP 1]`. Each piece is tokenized alone, without special tokens, by the checkpoint's
|
| 61 |
+
`tokenizer.json`. A dict or list state becomes `json.dumps(state, ensure_ascii=False)`. An option's marker is
|
| 62 |
+
the position of its `[MASK]`.
|
| 63 |
+
- Options: the criteria descriptions as given. `choice` uses the mapping's values in order, and the answer is
|
| 64 |
+
the caller's id. `score` uses the rubric in order. `noul` uses `[criteria.false, criteria.true]`, or the
|
| 65 |
+
literal words `false` / `true` when the question has no criteria.
|
| 66 |
+
- Readout: the softmax of the raw marker logits at T = 1; no calibration exists. `choice` = the winning id,
|
| 67 |
+
`score` = the expected rubric index Σ i·p_i (not rounded), `noul` = p[true].
|
| 68 |
+
- Strict encoding: 2–20 options, each at most 48 tokens, and no literal `<mask>` in any text (the publisher's
|
| 69 |
+
non-strict builder turns it into a space). A question that would need any cut is refused, never truncated.
|
| 70 |
+
- Head budget (question plus options): 512 tokens at S = 1024, the publisher's protocol, and 256 at S = 512.
|
| 71 |
+
Every row that fits 512 gets the same ids with either budget (2,065 of 2,065). All 2,000 typed-decisions
|
| 72 |
+
test questions fit 1,024 tokens (the longest is 607); 1,965 fit 512.
|
| 73 |
+
|
| 74 |
+
The option text is where Julia differs from [laya-multilingual](https://github.com/john-rocky/coreai-model-zoo/blob/main/models/laya-multilingual/README.md), the same
|
| 75 |
+
design on mmBERT-base with the same graph inputs. laya hosts render `label: description`, `level i: …` and
|
| 76 |
+
`false: …` / `true: …`, so a laya host builds other rows for Julia and gets other answers.
|
| 77 |
+
|
| 78 |
+
## Measured (Mac)
|
| 79 |
+
|
| 80 |
+
Apple M4 Max, macOS 27.0 build 26A428, coreai-build 3600.83.1, coreai-core 1.0.0b2, 2026-09-30. Each bundle
|
| 81 |
+
ran every row of its window: at S = 1024 the 2,000 typed-decisions test questions, the publisher's 100 parity
|
| 82 |
+
requests and 20 window-filling rows; at S = 512 the 1,965 questions that fit, the same 100 and 35
|
| 83 |
+
window-filling rows. The GPU rows ran alone (the machine-wide GPU lock held, no other GPU job seen).
|
| 84 |
+
`cpu_only` is the parity option; its milliseconds were taken while other jobs used the CPU and are reference
|
| 85 |
+
values. A question's time covers the NumPy inputs, the graph and the marker gather, not the tokenization.
|
| 86 |
+
|
| 87 |
+
| Variant | S | Compute | Rows | Argmax | Max \|Δp\| | Marker max \|Δ\| | Repeat drift | Load | Warm median |
|
| 88 |
+
|---|---:|---|---:|---:|---:|---:|---:|---:|---:|
|
| 89 |
+
| fp32 | 1024 | GPU | 2,120 | 2,120/2,120 | 8.58e-5 | 5.71e-4 | 0 | 641 ms | 16.00 ms |
|
| 90 |
+
| fp32 | 512 | GPU | 2,100 | 2,100/2,100 | 7.97e-5 | 6.17e-4 | 0 | 702 ms | 8.28 ms |
|
| 91 |
+
| fp32 | 1024 | cpu_only | 2,120 | 2,120/2,120 | 5.91e-5 | 7.58e-4 | 0 | 648 ms | 109.7 ms |
|
| 92 |
+
| fp32 | 512 | cpu_only | 2,100 | 2,100/2,100 | 5.91e-5 | 7.58e-4 | 0 | 621 ms | 81.0 ms |
|
| 93 |
+
|
| 94 |
+
The GPU median at S = 1024 is over 60 warm questions (p10 15.89 ms, p90 16.16 ms); at S = 512, p10 is 8.20 ms
|
| 95 |
+
and p90 8.42 ms. The question right after load took 601 ms at S = 1024 and 118 ms at S = 512. Repeat drift is
|
| 96 |
+
the largest change in the marker logits when a row runs 3 times (212 rows at S = 1024).
|
| 97 |
+
|
| 98 |
+
On the typed-decisions test split, the bundle's own argmax (GPU, S = 1024) gives the same three totals as the
|
| 99 |
+
publisher's CPU FP32 run. The split is `LocalLLaMA/typed-decisions` at `c76749e` (400 cases, 2,000
|
| 100 |
+
questions); the publisher's run used torch 2.14.0, transformers 5.0.0, max_length 1024, head_length 512 and
|
| 101 |
+
strict encoding.
|
| 102 |
+
|
| 103 |
+
| | choice | score | noul |
|
| 104 |
+
|---|---:|---:|---:|
|
| 105 |
+
| Supersonic Labs, PyTorch CPU FP32 | 426/600 | 542/800 | 483/600 |
|
| 106 |
+
| this bundle, Mac GPU, S = 1024 | 426/600 | 542/800 | 483/600 |
|
| 107 |
+
|
| 108 |
+
From text to answer, the Python host (`julia_coreai.JuliaCoreAI`, the S = 1024 bundle, GPU) gives the
|
| 109 |
+
publisher's `engine.predict` answers on all 2,000 named questions: argmax 2,000/2,000, max |Δp| 8.58e-5,
|
| 110 |
+
score and noul values within 8.6e-5, 0 questions refused, and 426/542/483 when re-scored. The 2,000 questions
|
| 111 |
+
took 32.9 s, tokenization included.
|
| 112 |
+
|
| 113 |
+
The Swift host (`JuliaDecisions.swift` over the system CoreAI framework, built with Xcode 27.0 RC) was
|
| 114 |
+
checked on the 200 strict rows of the fixture below. Its row builder gives the publisher's ids and markers on
|
| 115 |
+
200/200 rows, and its answers through the bundle match the publisher's: argmax 200/200, max |Δp| 4.3e-5 on the
|
| 116 |
+
GPU and 3.3e-5 with cpu_only. That check read the publisher's token ids per text piece from a table, so a
|
| 117 |
+
Swift tokenizer is not part of it.
|
| 118 |
+
|
| 119 |
+
## Numerics gate
|
| 120 |
+
|
| 121 |
+
The oracle is the publisher's own `julia` package at the pinned revision (torch 2.14.0, transformers 5.0.0,
|
| 122 |
+
CPU fp32, 4 threads, one question per forward). On this Mac it reproduces 426/600, 542/800 and 483/600, and
|
| 123 |
+
its 2,000 answers are identical to those of the publisher's `scripts/reproduce_typed.py`, run unchanged here.
|
| 124 |
+
On the publisher's 100 WebGPU parity requests (`parity-cases.json` in `SupersonicLabs/Julia-1-ONNX` at
|
| 125 |
+
`82a2fad`) it matches the PyTorch logits the publisher recorded: argmax 100/100, max |Δ logit| 1.03e-4 (theirs
|
| 126 |
+
in padded batches of 4, ours one per forward).
|
| 127 |
+
|
| 128 |
+
Bars at every stage: the argmax equal to the oracle's on every row, max |Δp| ≤ 1e-3 over the options at
|
| 129 |
+
T = 1, and marker logits within 1e-3. The rows include near-ties: 58 typed questions have a top probability
|
| 130 |
+
below 0.6, 46 a top-two gap below 0.2 and 9 below 0.05 (the smallest 0.0098). The window-filling rows have no
|
| 131 |
+
padding: the 35 questions over 512 tokens, cut to exactly 512 by the publisher's non-strict builder (head
|
| 132 |
+
budget 256), and 20 synthetic states (consecutive test states in one JSON list) cut to exactly 1,024.
|
| 133 |
+
|
| 134 |
+
- Authoring: the graph re-authored in plain PyTorch from `model.safetensors` (no transformers or `julia` code,
|
| 135 |
+
all 170 tensors loaded strictly), run in the zoo venv with torch 2.9.0 on every row of each window.
|
| 136 |
+
S = 1024: argmax 2,120/2,120, max |Δp| 6.56e-5, marker 7.95e-4, typed totals 426/542/483. S = 512: argmax
|
| 137 |
+
2,100/2,100, max |Δp| 6.56e-5, marker 7.95e-4.
|
| 138 |
+
- Layer gate on the hidden states: absolute ≤ 1e-4 on the embeddings and layers 0–9 (max 4.8e-5 at S = 1024,
|
| 139 |
+
3.5e-5 at S = 512); relative ≤ 5e-4 from layer 10 through the head (max 2.07e-4 and 3.42e-4).
|
| 140 |
+
- Negative controls, caught at both windows (S = 1024 / 512): all-global attention 5.09 / 3.59 at layer 1;
|
| 141 |
+
all-local 3.72 / 4.20 at layer 0; radius 63 instead of 64, 1.29 / 1.45 at layer 1; padding ignored,
|
| 142 |
+
29.5 / 29.4 at layer 0; no type embedding, caught at the head input (marker logits moved by 0.81 at
|
| 143 |
+
S = 512). Random ids in every pad position leave every real position bit-identical (11 rows per window).
|
| 144 |
+
On the bundle, judging each row against another row's outputs fails on 1,724 of 2,120 pairs (S = 1024).
|
| 145 |
+
- Export: the `torch.export` graph after `coreai_torch` decomposition, gated before conversion on every 4th
|
| 146 |
+
row plus the layer-gate rows and every window-filling row. S = 1024: 552 rows, argmax 552/552, max |Δp|
|
| 147 |
+
5.81e-5. S = 512: 560 rows, argmax 560/560, max |Δp| 6.56e-5.
|
| 148 |
+
- Runtime: the table above.
|
| 149 |
+
- Host: the NumPy host (tokenizers 0.23.0rc0 on the checkpoint's `tokenizer.json`) rebuilds all 2,155 oracle
|
| 150 |
+
rows from text with identical ids and markers. It renders the 2,000 named questions the publisher's way and
|
| 151 |
+
reproduces the publisher's 2,000 answer dictionaries from the same logits (max difference 8.9e-16).
|
| 152 |
+
|
| 153 |
+
The relative bar is twice the publisher's own SDPA-vs-eager distance on this checkpoint (2.87e-4 at the final
|
| 154 |
+
norm, S = 1024), rounded down; laya's 2e-4, tried before it, failed at the final norm. Under the publisher's
|
| 155 |
+
torch 2.14.0 the graph equals the publisher's eager-attention path to 1.3e-7 relative at every hidden state
|
| 156 |
+
and 1.9e-6 on the marker logits (13 rows per window).
|
| 157 |
+
|
| 158 |
+
[`fixtures-julia-1.json`](https://github.com/john-rocky/coreai-model-zoo/blob/main/models/julia-1/fixtures-julia-1.json) in the zoo repository (543 KB) holds the 100 parity requests, every 20th typed question and
|
| 159 |
+
5 window-filling rows per window, each with the request, token ids, markers and the publisher's raw logits.
|
| 160 |
+
|
| 161 |
+
## Precision
|
| 162 |
+
|
| 163 |
+
fp32 ships: the checkpoint's F32 weights as published, computed in fp32. fp16 weight storage with fp32 compute
|
| 164 |
+
was measured at S = 1024 and fails the 1e-3 bar, so it does not ship. It keeps argmax 2,120/2,120 and the
|
| 165 |
+
typed totals 426/542/483, but max |Δp| is 0.0234 (over 1e-3 on 325 rows, over 1e-2 on 32); a score's expected
|
| 166 |
+
index moves by up to 0.029 and a noul's p[true] by up to 0.023.
|
| 167 |
+
|
| 168 |
+
Neural Engine: not used. With a Neural Engine preference the Mac returns the GPU's results bit for bit at the same speed (844 rows, 2026-09-30), and `coreai-build compile --preferred-compute neural-engine` produces no Neural Engine region for macOS (h16c) or the iPhone 18 Pro (h19p): the graph computes in fp32, which the Neural Engine does not take.
|
| 169 |
+
|
| 170 |
+
## Bundle
|
| 171 |
+
|
| 172 |
+
This repository holds one folder per window, each self-contained: the bundle,
|
| 173 |
+
`tokenizer/` (the checkpoint's files, unmodified), `metadata.json` (the decision contract), `reference.json`
|
| 174 |
+
(the window's rows with token ids, markers and the publisher's logits) and `provenance/` (the export manifest
|
| 175 |
+
and the export and runtime gate records).
|
| 176 |
+
|
| 177 |
+
| Folder | Platform | Format | Bundle | Bytes |
|
| 178 |
+
|---|---|---|---|---:|
|
| 179 |
+
| `macos/fp32-s1024/` | macOS 27 | JIT `.aimodel` | `julia1_fp32_s1024.aimodel` | 581,765,544 |
|
| 180 |
+
| `macos/fp32-s512/` | macOS 27 | JIT `.aimodel` | `julia1_fp32_s512.aimodel` | 578,357,637 |
|
| 181 |
+
|
| 182 |
+
The whole folders are 627,543,671 and 623,850,816 bytes.
|
| 183 |
+
|
| 184 |
+
Convert yourself: [`conversion/julia/`](https://github.com/john-rocky/coreai-model-zoo/blob/main/conversion/julia/README.md), the staged scripts in order;
|
| 185 |
+
[`recipe.toml`](https://github.com/john-rocky/coreai-model-zoo/blob/main/models/julia-1/recipe.toml) names the commands.
|
| 186 |
+
|
| 187 |
+
## Use it
|
| 188 |
+
|
| 189 |
+
Python, with `conversion/julia/julia_coreai.py` (the reference host; it needs `coreai-core`, `numpy` and
|
| 190 |
+
`tokenizers`):
|
| 191 |
+
|
| 192 |
+
```python
|
| 193 |
+
import sys
|
| 194 |
+
sys.path.insert(0, "conversion/julia") # the folder with julia_coreai.py and _julia_host.py
|
| 195 |
+
from julia_coreai import JuliaCoreAI
|
| 196 |
+
|
| 197 |
+
julia = JuliaCoreAI("Julia-1-CoreAI/macos/fp32-s1024") # a download of the HF repo; GPU by default
|
| 198 |
+
result = julia.predict(
|
| 199 |
+
state="I was charged twice for the same order.",
|
| 200 |
+
questions={
|
| 201 |
+
"team": {
|
| 202 |
+
"type": "choice",
|
| 203 |
+
"instructions": "Which team should handle this request?",
|
| 204 |
+
"criteria": {
|
| 205 |
+
"billing": "Billing and payment disputes",
|
| 206 |
+
"shipping": "Shipping and delivery",
|
| 207 |
+
"access": "Account access and login",
|
| 208 |
+
},
|
| 209 |
+
},
|
| 210 |
+
},
|
| 211 |
+
)
|
| 212 |
+
print(result["answers"]["team"]["choice"])
|
| 213 |
+
print(result["answers"]["team"]["probabilities"])
|
| 214 |
+
```
|
| 215 |
+
|
| 216 |
+
The call and the returned dictionary follow the publisher's `engine.predict(state=..., questions=...)`.
|
| 217 |
+
`JuliaCoreAI(folder, compute="cpu_only")` loads the parity option.
|
| 218 |
+
|
| 219 |
+
Swift, with `conversion/julia/swift/JuliaDecisions.swift` added to your target (the system CoreAI framework,
|
| 220 |
+
macOS 27). It needs a tokenizer for the folder's `tokenizer/tokenizer.json`, passed in as `encode:`; with
|
| 221 |
+
swift-transformers:
|
| 222 |
+
|
| 223 |
+
```swift
|
| 224 |
+
import CoreAI
|
| 225 |
+
import Tokenizers // swift-transformers
|
| 226 |
+
|
| 227 |
+
let folder = URL(filePath: "Julia-1-CoreAI/macos/fp32-s1024") // a download of the HF repo
|
| 228 |
+
let tokenizer = try await AutoTokenizer.from(modelFolder: folder.appendingPathComponent("tokenizer"))
|
| 229 |
+
let julia = try await JuliaDecisions(folder: folder, encode: { text in
|
| 230 |
+
tokenizer.encode(text: text, addSpecialTokens: false).map(Int32.init)
|
| 231 |
+
})
|
| 232 |
+
let answers = try await julia.predict(state: "I was charged twice for the same order.", questions: [
|
| 233 |
+
("team", .choice("Which team should handle this request?", [
|
| 234 |
+
("billing", "Billing and payment disputes"), ("shipping", "Shipping and delivery"),
|
| 235 |
+
("access", "Account access and login")])),
|
| 236 |
+
])
|
| 237 |
+
print(answers["team"]!.choice!)
|
| 238 |
+
```
|
| 239 |
+
|
| 240 |
+
`JuliaDecisions` loads the folder with `AIModel` itself; Julia-1 is not a CoreAIKit catalog model. A
|
| 241 |
+
structured state goes in as text, serialized the way Python's `json.dumps(state, ensure_ascii=False)` writes
|
| 242 |
+
it. The Swift check above did not run a tokenizer; `reference.json` and the fixture hold the ids a tokenizer
|
| 243 |
+
has to reproduce.
|
| 244 |
+
|
| 245 |
+
## Other runtimes
|
| 246 |
+
|
| 247 |
+
Not compared here: the publisher's ONNX export with a WebGPU adapter, `SupersonicLabs/Julia-1-ONNX`; MLX,
|
| 248 |
+
`zainmerchan/Julia-1-MLX`; GGUF, `andrelucas/Julia-1-GGUF`.
|
| 249 |
+
|
| 250 |
+
## License and limits
|
| 251 |
+
|
| 252 |
+
Apache-2.0, from the upstream card: its metadata declares it, and its README says "The model artifacts are
|
| 253 |
+
licensed under Apache 2.0." The upstream repository has no LICENSE file. The base, jhu-clsp/mmBERT-small, is
|
| 254 |
+
MIT. Julia-1 and its weights are the work of Supersonic Labs; these bundles carry the weights in fp32 as
|
| 255 |
+
published. The fixture's requests come from `LocalLLaMA/typed-decisions` and the Julia-1-ONNX
|
| 256 |
+
`parity-cases.json`, both Apache-2.0.
|
| 257 |
+
|
| 258 |
+
Not tested: iPhone (not measured), other Macs and OS builds, batched shapes, windows other than 512 and 1024,
|
| 259 |
+
the publisher's other benchmarks (not re-run here), and the publisher's `Router` for more than 20 options.
|
SHA256SUMS
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4 LICENSE
|
| 2 |
+
4670f123942007bc60b1525ab2ab726a37ebd020178cf0312a23df636b97de47 LICENSE-NOTE.md
|
| 3 |
+
ba01823bd1e64d927602b063fa7d2bda8b84d58cee6ee7d650a226dc7810d1f6 README.md
|
| 4 |
+
c79cda42d42ddf777218254845ce92fb25a10dc35874be40d06abd707894523d config.json
|
| 5 |
+
b9b881646beeac5414eaa78b39d3fe89ff8a2c062731ad718432620f9aee6bf7 julia_config.json
|
| 6 |
+
4e1ee201ce359a55aed90422bea275e200a7331d995cc6c4d4728f4bcb5e4b1a macos/fp32-s1024/julia1_fp32_s1024.aimodel/main.hash
|
| 7 |
+
ad29d6800776a1077cb50e0afa7ffe786c51db11bf61514a1577212075a540e8 macos/fp32-s1024/julia1_fp32_s1024.aimodel/main.mlirb
|
| 8 |
+
a3dda1a55670ebf047213938eee9dfabae83e19e0e022de905b91279c8772da5 macos/fp32-s1024/julia1_fp32_s1024.aimodel/metadata.json
|
| 9 |
+
debbcac4fb5873788c78bf6e2f35e4bc6b791d55a6014bcda182c78c7b5a0048 macos/fp32-s1024/metadata.json
|
| 10 |
+
37978d7abf233adfaf81214d2485625bd9608079890594fcbcedc0bfccbf6ec4 macos/fp32-s1024/provenance/export-gate.json
|
| 11 |
+
f2beeb90ccddb5705ca706c0adf7b7cdbfdd2eeda2f0fc37fa4bfdca28f127f7 macos/fp32-s1024/provenance/export-manifest.json
|
| 12 |
+
de82f57d9b1b6afc59b347bd2f44f6a3e662f5c3b5e7c24d7a91e51e51712494 macos/fp32-s1024/provenance/runtime-gate.json
|
| 13 |
+
1fbd7e516ac8b0828efd508d4251f12aa5d461d12fd6dc7bb5b1d4a1222e3445 macos/fp32-s1024/reference.json
|
| 14 |
+
609d8f4c067cd3950f88594c5a802616cea245823836ef5848ee4fc40aab5b6f macos/fp32-s1024/tokenizer/tokenizer.json
|
| 15 |
+
6b069e57db0ce0794c22547725275f22618809c4ef4249307337e651a0dfef8c macos/fp32-s1024/tokenizer/tokenizer_config.json
|
| 16 |
+
e6493cb1f5cabeaa395d558628485d906f3216a0f612b52891cfd334ba3ce732 macos/fp32-s512/julia1_fp32_s512.aimodel/main.hash
|
| 17 |
+
f9287684c9e2d01fb38a7776aa0f5397c733f8f7d390b6cabe36cfb45d3c81d4 macos/fp32-s512/julia1_fp32_s512.aimodel/main.mlirb
|
| 18 |
+
e9ee198e153c93d1d4678df8751cab8f3f9811e69a329c9fdea4cef19bd64366 macos/fp32-s512/julia1_fp32_s512.aimodel/metadata.json
|
| 19 |
+
800bb514522ecdaafef95650348df7ae23234e98f77fb90ffb4f0a706ade2d47 macos/fp32-s512/metadata.json
|
| 20 |
+
77300fdd1c131f336943228fe11839fe37eb36969654fd2d38e05bd090eccad4 macos/fp32-s512/provenance/export-gate.json
|
| 21 |
+
c310db109e6bc20b8437a1fe46e68c456527f0f210b93422e114d07f62c5fbf5 macos/fp32-s512/provenance/export-manifest.json
|
| 22 |
+
075799cc5b19bb79cf0f9008629652290df091bd0513c671f5a8da818cb6de02 macos/fp32-s512/provenance/runtime-gate.json
|
| 23 |
+
65a2ed0f8435d5998e12461cb07a78a8917b381e00c88b5e31a6d4026992b725 macos/fp32-s512/reference.json
|
| 24 |
+
609d8f4c067cd3950f88594c5a802616cea245823836ef5848ee4fc40aab5b6f macos/fp32-s512/tokenizer/tokenizer.json
|
| 25 |
+
6b069e57db0ce0794c22547725275f22618809c4ef4249307337e651a0dfef8c macos/fp32-s512/tokenizer/tokenizer_config.json
|
config.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 1,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "float32",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 1,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 384,
|
| 22 |
+
"initializer_cutoff_factor": 2.0,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 1152,
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"layer_types": [
|
| 27 |
+
"full_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"full_attention"
|
| 49 |
+
],
|
| 50 |
+
"local_attention": 128,
|
| 51 |
+
"mask_token_id": 4,
|
| 52 |
+
"max_position_embeddings": 8192,
|
| 53 |
+
"mlp_bias": false,
|
| 54 |
+
"mlp_dropout": 0.0,
|
| 55 |
+
"model_type": "modernbert",
|
| 56 |
+
"norm_bias": false,
|
| 57 |
+
"norm_eps": 1e-05,
|
| 58 |
+
"num_attention_heads": 6,
|
| 59 |
+
"num_hidden_layers": 22,
|
| 60 |
+
"pad_token_id": 0,
|
| 61 |
+
"position_embedding_type": "sans_pos",
|
| 62 |
+
"repad_logits_with_grad": false,
|
| 63 |
+
"rope_parameters": {
|
| 64 |
+
"full_attention": {
|
| 65 |
+
"rope_theta": 160000,
|
| 66 |
+
"rope_type": "default"
|
| 67 |
+
},
|
| 68 |
+
"sliding_attention": {
|
| 69 |
+
"rope_theta": 160000,
|
| 70 |
+
"rope_type": "default"
|
| 71 |
+
}
|
| 72 |
+
},
|
| 73 |
+
"sep_token_id": 1,
|
| 74 |
+
"sparse_pred_ignore_index": -100,
|
| 75 |
+
"sparse_prediction": true,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"transformers_version": "5.0.0",
|
| 78 |
+
"vocab_size": 256000
|
| 79 |
+
}
|
julia_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"format_version": 1,
|
| 3 |
+
"architecture": "JuliaDecisionModel",
|
| 4 |
+
"weight_dtype": "float32",
|
| 5 |
+
"head_layers": 2,
|
| 6 |
+
"n_act": 2,
|
| 7 |
+
"dropout": 0.1
|
| 8 |
+
}
|
macos/fp32-s1024/julia1_fp32_s1024.aimodel/main.hash
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
�)րv�|�
|
| 2 |
+
��xlQ��aQJw! u�@�
|
macos/fp32-s1024/julia1_fp32_s1024.aimodel/main.mlirb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad29d6800776a1077cb50e0afa7ffe786c51db11bf61514a1577212075a540e8
|
| 3 |
+
size 581765120
|
macos/fp32-s1024/julia1_fp32_s1024.aimodel/metadata.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"author" : "mlboydaisuke (coreai-model-zoo); weights Supersonic Labs (Julia-1)",
|
| 3 |
+
"assetVersion" : "2.0",
|
| 4 |
+
"description" : "Julia-1 decision encoder (mmBERT-small + typed head); fp32; S=1024; function main; source SupersonicLabs\/Julia-1@a85b127321d580d65176c89ced8273f305745d85",
|
| 5 |
+
"producer" : "coreai-core 1.0.0b2",
|
| 6 |
+
"license" : "Apache-2.0",
|
| 7 |
+
"creationDate" : "20260930T004313Z"
|
| 8 |
+
}
|
macos/fp32-s1024/metadata.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata_version": "0.2",
|
| 3 |
+
"kind": "encoder",
|
| 4 |
+
"decision": {
|
| 5 |
+
"head": "encoder",
|
| 6 |
+
"layout": "julia",
|
| 7 |
+
"window": 1024,
|
| 8 |
+
"head_max_len": 512,
|
| 9 |
+
"option_text_tokens": 48,
|
| 10 |
+
"strict_encoding": true,
|
| 11 |
+
"cls_token_id": 2,
|
| 12 |
+
"sep_token_id": 1,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"mask_token_id": 4,
|
| 15 |
+
"functions": {
|
| 16 |
+
"main": "main"
|
| 17 |
+
},
|
| 18 |
+
"inputs": {
|
| 19 |
+
"input_ids": {
|
| 20 |
+
"dtype": "int32",
|
| 21 |
+
"shape": [
|
| 22 |
+
1,
|
| 23 |
+
1024
|
| 24 |
+
],
|
| 25 |
+
"padding": "right, PAD 0"
|
| 26 |
+
},
|
| 27 |
+
"attention_mask": {
|
| 28 |
+
"dtype": "int32",
|
| 29 |
+
"shape": [
|
| 30 |
+
1,
|
| 31 |
+
1024
|
| 32 |
+
],
|
| 33 |
+
"values": "1 real token, 0 padding"
|
| 34 |
+
},
|
| 35 |
+
"qtype_onehot": {
|
| 36 |
+
"dtype": "float32",
|
| 37 |
+
"shape": [
|
| 38 |
+
1,
|
| 39 |
+
3
|
| 40 |
+
],
|
| 41 |
+
"order": [
|
| 42 |
+
"choice",
|
| 43 |
+
"score",
|
| 44 |
+
"noul"
|
| 45 |
+
]
|
| 46 |
+
}
|
| 47 |
+
},
|
| 48 |
+
"outputs": {
|
| 49 |
+
"token_logits": {
|
| 50 |
+
"dtype": "float32",
|
| 51 |
+
"shape": [
|
| 52 |
+
1,
|
| 53 |
+
1024
|
| 54 |
+
],
|
| 55 |
+
"read": "at the option marker positions"
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"options": "the descriptions as given: choice = the criteria mapping's values in order (answer = its id), score = the rubric in order, noul = [criteria.false, criteria.true] or the literal ['false', 'true'] when a noul question has no criteria",
|
| 59 |
+
"sequence": "[CLS 2] tok('{type} question: {instructions}') [SEP 1] ([MASK 4] tok(' ' + option)[:48])... [SEP 1] tok(state) [SEP 1]; state = json.dumps(state, ensure_ascii=False) when not text; strict: a row that does not fit, or text holding the literal '<mask>', is refused, never cut or rewritten (the publisher's non-strict builder turns '<mask>' into ' ')",
|
| 60 |
+
"readout": "softmax of the raw marker logits (T = 1); choice = argmax id, score = sum(i * p_i), noul = p[true]",
|
| 61 |
+
"source_temperature": [
|
| 62 |
+
1.0,
|
| 63 |
+
1.0,
|
| 64 |
+
1.0
|
| 65 |
+
],
|
| 66 |
+
"calibration": null,
|
| 67 |
+
"precision": "fp32"
|
| 68 |
+
},
|
| 69 |
+
"source": {
|
| 70 |
+
"hf_model_id": "SupersonicLabs/Julia-1",
|
| 71 |
+
"hf_revision": "a85b127321d580d65176c89ced8273f305745d85"
|
| 72 |
+
},
|
| 73 |
+
"assets": {
|
| 74 |
+
"main": "julia1_fp32_s1024.aimodel"
|
| 75 |
+
},
|
| 76 |
+
"language": {
|
| 77 |
+
"tokenizer": "SupersonicLabs/Julia-1/tokenizer",
|
| 78 |
+
"vocab_size": 256000,
|
| 79 |
+
"max_context_length": 1024
|
| 80 |
+
}
|
| 81 |
+
}
|
macos/fp32-s1024/provenance/export-gate.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
macos/fp32-s1024/provenance/export-manifest.json
ADDED
|
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"status": "PASS",
|
| 3 |
+
"measure_only": false,
|
| 4 |
+
"model": "SupersonicLabs/Julia-1",
|
| 5 |
+
"model_sha": "a85b127321d580d65176c89ced8273f305745d85",
|
| 6 |
+
"bundle": "julia1_fp32_s1024.aimodel",
|
| 7 |
+
"intended_runtime": "macos",
|
| 8 |
+
"format": "JIT .aimodel (portable; one function main)",
|
| 9 |
+
"aot": false,
|
| 10 |
+
"precision": "fp32",
|
| 11 |
+
"window": 1024,
|
| 12 |
+
"inputs": {
|
| 13 |
+
"input_ids": {
|
| 14 |
+
"dtype": "int32",
|
| 15 |
+
"shape": [
|
| 16 |
+
1,
|
| 17 |
+
1024
|
| 18 |
+
],
|
| 19 |
+
"padding": "right, PAD 0"
|
| 20 |
+
},
|
| 21 |
+
"attention_mask": {
|
| 22 |
+
"dtype": "int32",
|
| 23 |
+
"shape": [
|
| 24 |
+
1,
|
| 25 |
+
1024
|
| 26 |
+
],
|
| 27 |
+
"values": "1 real token, 0 padding"
|
| 28 |
+
},
|
| 29 |
+
"qtype_onehot": {
|
| 30 |
+
"dtype": "float32",
|
| 31 |
+
"shape": [
|
| 32 |
+
1,
|
| 33 |
+
3
|
| 34 |
+
],
|
| 35 |
+
"order": [
|
| 36 |
+
"choice",
|
| 37 |
+
"score",
|
| 38 |
+
"noul"
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"outputs": {
|
| 43 |
+
"token_logits": {
|
| 44 |
+
"dtype": "float32",
|
| 45 |
+
"shape": [
|
| 46 |
+
1,
|
| 47 |
+
1024
|
| 48 |
+
],
|
| 49 |
+
"read": "at the option marker positions"
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"files": [
|
| 53 |
+
{
|
| 54 |
+
"path": "main.hash",
|
| 55 |
+
"bytes": 32,
|
| 56 |
+
"sha256": "4e1ee201ce359a55aed90422bea275e200a7331d995cc6c4d4728f4bcb5e4b1a"
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"path": "main.mlirb",
|
| 60 |
+
"bytes": 581765120,
|
| 61 |
+
"sha256": "ad29d6800776a1077cb50e0afa7ffe786c51db11bf61514a1577212075a540e8"
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"path": "metadata.json",
|
| 65 |
+
"bytes": 392,
|
| 66 |
+
"sha256": "a3dda1a55670ebf047213938eee9dfabae83e19e0e022de905b91279c8772da5"
|
| 67 |
+
}
|
| 68 |
+
],
|
| 69 |
+
"op_counts": {
|
| 70 |
+
"builtin.module": 1,
|
| 71 |
+
"coreai.cast": 1,
|
| 72 |
+
"coreai.concat": 44,
|
| 73 |
+
"coreai.constant": 195,
|
| 74 |
+
"coreai.decomposable.broadcasting_add": 130,
|
| 75 |
+
"coreai.decomposable.broadcasting_batch_matmul": 147,
|
| 76 |
+
"coreai.decomposable.broadcasting_mul": 182,
|
| 77 |
+
"coreai.decomposable.broadcasting_sub": 2,
|
| 78 |
+
"coreai.gather_nd": 1,
|
| 79 |
+
"coreai.gelu": 23,
|
| 80 |
+
"coreai.graph": 2,
|
| 81 |
+
"coreai.invoke": 50,
|
| 82 |
+
"coreai.output": 2,
|
| 83 |
+
"coreai.reduce_mean": 2,
|
| 84 |
+
"coreai.relu": 2,
|
| 85 |
+
"coreai.reshape": 122,
|
| 86 |
+
"coreai.rsqrt": 1,
|
| 87 |
+
"coreai.slice": 72,
|
| 88 |
+
"coreai.softmax": 24,
|
| 89 |
+
"coreai.split": 66,
|
| 90 |
+
"coreai.transpose": 215
|
| 91 |
+
},
|
| 92 |
+
"seconds": {
|
| 93 |
+
"torch_export": 2.504598124884069,
|
| 94 |
+
"convert_total": 0.9458033749833703,
|
| 95 |
+
"optimize": 0.03253654204308987,
|
| 96 |
+
"save": 0.46211579092778265,
|
| 97 |
+
"total": 145.6902863329742
|
| 98 |
+
},
|
| 99 |
+
"torch_export_gate": {
|
| 100 |
+
"status": "PASS",
|
| 101 |
+
"record": "provenance/export-gate.json",
|
| 102 |
+
"rows_stride": 4,
|
| 103 |
+
"rows_in_window": 2120,
|
| 104 |
+
"rows": 552,
|
| 105 |
+
"argmax_identical": 552,
|
| 106 |
+
"max_probability_error": 5.805650219314895e-05,
|
| 107 |
+
"max_marker_abs_error": 0.0002903938293457031,
|
| 108 |
+
"typed_accuracy": {
|
| 109 |
+
"choice": {
|
| 110 |
+
"count": 151,
|
| 111 |
+
"correct": 103
|
| 112 |
+
},
|
| 113 |
+
"score": {
|
| 114 |
+
"count": 202,
|
| 115 |
+
"correct": 138
|
| 116 |
+
},
|
| 117 |
+
"noul": {
|
| 118 |
+
"count": 153,
|
| 119 |
+
"correct": 121
|
| 120 |
+
}
|
| 121 |
+
}
|
| 122 |
+
},
|
| 123 |
+
"authoring_records": [
|
| 124 |
+
"/Users/majimadaisuke/code/coreai/_julia1/julia-1/results/authoring_fp32_s1024.json"
|
| 125 |
+
],
|
| 126 |
+
"runtime_gate": "NOT RUN — gate_julia_runtime.py <this folder> --compute cpu_only|gpu",
|
| 127 |
+
"environment": {
|
| 128 |
+
"date": "2026-09-30T09:43:14+09:00",
|
| 129 |
+
"machine": "Apple M4 Max",
|
| 130 |
+
"macos_version": "27.0",
|
| 131 |
+
"macos_build": "26A428",
|
| 132 |
+
"coreai_build": "coreai-build 3600.83.1",
|
| 133 |
+
"python": "3.11.13",
|
| 134 |
+
"packages": {
|
| 135 |
+
"torch": "2.9.0",
|
| 136 |
+
"coreai-torch": "0.4.1",
|
| 137 |
+
"coreai-core": "1.0.0b2",
|
| 138 |
+
"numpy": "2.3.5",
|
| 139 |
+
"safetensors": "0.7.0"
|
| 140 |
+
},
|
| 141 |
+
"argv": [
|
| 142 |
+
"conversion/julia/export_julia.py",
|
| 143 |
+
"--window",
|
| 144 |
+
"1024",
|
| 145 |
+
"--dtype",
|
| 146 |
+
"fp32",
|
| 147 |
+
"--rows-stride",
|
| 148 |
+
"4"
|
| 149 |
+
]
|
| 150 |
+
},
|
| 151 |
+
"input_hashes": {
|
| 152 |
+
"/Users/majimadaisuke/code/coreai/_julia1/julia-1/results/authoring_fp32_s1024.json": "4d27cd1702f639bc1e275e7108937fa74c01ffda6709ab873eddcb5977b76d80",
|
| 153 |
+
"/Users/majimadaisuke/code/coreai/_julia1/julia-1/oracle/rows.json": "c805348599fb0a87688246f0a290bb293e6f967c5fe938686d23fa8b3ea1377a",
|
| 154 |
+
"/Users/majimadaisuke/code/coreai/coreai-models-community-julia1-wt/conversion/julia/export_julia.py": "606dc911e2c092e8ee94affc28a52796bb7254909e9f1a2474f8a60ab6f27726",
|
| 155 |
+
"/Users/majimadaisuke/code/coreai/coreai-models-community-julia1-wt/conversion/julia/_julia_model.py": "616f219c230e2b36c40ef0939e8402ec42ed8fae7ce81f0c1b79de91b75b4cfe",
|
| 156 |
+
"/Users/majimadaisuke/code/coreai/coreai-models-community-julia1-wt/conversion/julia/_julia_host.py": "c77e391110b6295efdbad6ecb148b36cda06c6678183fa2e4dd1fd24ad967786",
|
| 157 |
+
"/Users/majimadaisuke/code/coreai/coreai-models-community-julia1-wt/conversion/julia/_gate_metrics.py": "8425201abe9aa7d232d67f95ca8b34a37a33d26835c3540eddcad9606e258de2"
|
| 158 |
+
},
|
| 159 |
+
"bytes": 581765544
|
| 160 |
+
}
|
macos/fp32-s1024/provenance/runtime-gate.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
macos/fp32-s1024/reference.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
macos/fp32-s1024/tokenizer/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:609d8f4c067cd3950f88594c5a802616cea245823836ef5848ee4fc40aab5b6f
|
| 3 |
+
size 34363188
|
macos/fp32-s1024/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<bos>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"cls_token": "<bos>",
|
| 6 |
+
"eos_token": "<eos>",
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<start_of_turn>",
|
| 9 |
+
"<end_of_turn>"
|
| 10 |
+
],
|
| 11 |
+
"is_local": true,
|
| 12 |
+
"mask_token": "<mask>",
|
| 13 |
+
"max_length": 512,
|
| 14 |
+
"model_input_names": [
|
| 15 |
+
"input_ids",
|
| 16 |
+
"attention_mask"
|
| 17 |
+
],
|
| 18 |
+
"model_max_length": 8192,
|
| 19 |
+
"pad_token": "<pad>",
|
| 20 |
+
"padding_side": "right",
|
| 21 |
+
"sep_token": "<eos>",
|
| 22 |
+
"spaces_between_special_tokens": false,
|
| 23 |
+
"stride": 0,
|
| 24 |
+
"tokenizer_class": "TokenizersBackend",
|
| 25 |
+
"truncation_side": "right",
|
| 26 |
+
"truncation_strategy": "longest_first",
|
| 27 |
+
"unk_token": "<unk>"
|
| 28 |
+
}
|
macos/fp32-s512/julia1_fp32_s512.aimodel/main.hash
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
�(v������wv�S��3��Ӑ�ʾ6ϴ]<��
|
macos/fp32-s512/julia1_fp32_s512.aimodel/main.mlirb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9287684c9e2d01fb38a7776aa0f5397c733f8f7d390b6cabe36cfb45d3c81d4
|
| 3 |
+
size 578357214
|
macos/fp32-s512/julia1_fp32_s512.aimodel/metadata.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"creationDate" : "20260930T004000Z",
|
| 3 |
+
"description" : "Julia-1 decision encoder (mmBERT-small + typed head); fp32; S=512; function main; source SupersonicLabs\/Julia-1@a85b127321d580d65176c89ced8273f305745d85",
|
| 4 |
+
"producer" : "coreai-core 1.0.0b2",
|
| 5 |
+
"assetVersion" : "2.0",
|
| 6 |
+
"license" : "Apache-2.0",
|
| 7 |
+
"author" : "mlboydaisuke (coreai-model-zoo); weights Supersonic Labs (Julia-1)"
|
| 8 |
+
}
|
macos/fp32-s512/metadata.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata_version": "0.2",
|
| 3 |
+
"kind": "encoder",
|
| 4 |
+
"decision": {
|
| 5 |
+
"head": "encoder",
|
| 6 |
+
"layout": "julia",
|
| 7 |
+
"window": 512,
|
| 8 |
+
"head_max_len": 256,
|
| 9 |
+
"option_text_tokens": 48,
|
| 10 |
+
"strict_encoding": true,
|
| 11 |
+
"cls_token_id": 2,
|
| 12 |
+
"sep_token_id": 1,
|
| 13 |
+
"pad_token_id": 0,
|
| 14 |
+
"mask_token_id": 4,
|
| 15 |
+
"functions": {
|
| 16 |
+
"main": "main"
|
| 17 |
+
},
|
| 18 |
+
"inputs": {
|
| 19 |
+
"input_ids": {
|
| 20 |
+
"dtype": "int32",
|
| 21 |
+
"shape": [
|
| 22 |
+
1,
|
| 23 |
+
512
|
| 24 |
+
],
|
| 25 |
+
"padding": "right, PAD 0"
|
| 26 |
+
},
|
| 27 |
+
"attention_mask": {
|
| 28 |
+
"dtype": "int32",
|
| 29 |
+
"shape": [
|
| 30 |
+
1,
|
| 31 |
+
512
|
| 32 |
+
],
|
| 33 |
+
"values": "1 real token, 0 padding"
|
| 34 |
+
},
|
| 35 |
+
"qtype_onehot": {
|
| 36 |
+
"dtype": "float32",
|
| 37 |
+
"shape": [
|
| 38 |
+
1,
|
| 39 |
+
3
|
| 40 |
+
],
|
| 41 |
+
"order": [
|
| 42 |
+
"choice",
|
| 43 |
+
"score",
|
| 44 |
+
"noul"
|
| 45 |
+
]
|
| 46 |
+
}
|
| 47 |
+
},
|
| 48 |
+
"outputs": {
|
| 49 |
+
"token_logits": {
|
| 50 |
+
"dtype": "float32",
|
| 51 |
+
"shape": [
|
| 52 |
+
1,
|
| 53 |
+
512
|
| 54 |
+
],
|
| 55 |
+
"read": "at the option marker positions"
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"options": "the descriptions as given: choice = the criteria mapping's values in order (answer = its id), score = the rubric in order, noul = [criteria.false, criteria.true] or the literal ['false', 'true'] when a noul question has no criteria",
|
| 59 |
+
"sequence": "[CLS 2] tok('{type} question: {instructions}') [SEP 1] ([MASK 4] tok(' ' + option)[:48])... [SEP 1] tok(state) [SEP 1]; state = json.dumps(state, ensure_ascii=False) when not text; strict: a row that does not fit, or text holding the literal '<mask>', is refused, never cut or rewritten (the publisher's non-strict builder turns '<mask>' into ' ')",
|
| 60 |
+
"readout": "softmax of the raw marker logits (T = 1); choice = argmax id, score = sum(i * p_i), noul = p[true]",
|
| 61 |
+
"source_temperature": [
|
| 62 |
+
1.0,
|
| 63 |
+
1.0,
|
| 64 |
+
1.0
|
| 65 |
+
],
|
| 66 |
+
"calibration": null,
|
| 67 |
+
"precision": "fp32"
|
| 68 |
+
},
|
| 69 |
+
"source": {
|
| 70 |
+
"hf_model_id": "SupersonicLabs/Julia-1",
|
| 71 |
+
"hf_revision": "a85b127321d580d65176c89ced8273f305745d85"
|
| 72 |
+
},
|
| 73 |
+
"assets": {
|
| 74 |
+
"main": "julia1_fp32_s512.aimodel"
|
| 75 |
+
},
|
| 76 |
+
"language": {
|
| 77 |
+
"tokenizer": "SupersonicLabs/Julia-1/tokenizer",
|
| 78 |
+
"vocab_size": 256000,
|
| 79 |
+
"max_context_length": 512
|
| 80 |
+
}
|
| 81 |
+
}
|
macos/fp32-s512/provenance/export-gate.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
macos/fp32-s512/provenance/export-manifest.json
ADDED
|
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"status": "PASS",
|
| 3 |
+
"measure_only": false,
|
| 4 |
+
"model": "SupersonicLabs/Julia-1",
|
| 5 |
+
"model_sha": "a85b127321d580d65176c89ced8273f305745d85",
|
| 6 |
+
"bundle": "julia1_fp32_s512.aimodel",
|
| 7 |
+
"intended_runtime": "macos",
|
| 8 |
+
"format": "JIT .aimodel (portable; one function main)",
|
| 9 |
+
"aot": false,
|
| 10 |
+
"precision": "fp32",
|
| 11 |
+
"window": 512,
|
| 12 |
+
"inputs": {
|
| 13 |
+
"input_ids": {
|
| 14 |
+
"dtype": "int32",
|
| 15 |
+
"shape": [
|
| 16 |
+
1,
|
| 17 |
+
512
|
| 18 |
+
],
|
| 19 |
+
"padding": "right, PAD 0"
|
| 20 |
+
},
|
| 21 |
+
"attention_mask": {
|
| 22 |
+
"dtype": "int32",
|
| 23 |
+
"shape": [
|
| 24 |
+
1,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"values": "1 real token, 0 padding"
|
| 28 |
+
},
|
| 29 |
+
"qtype_onehot": {
|
| 30 |
+
"dtype": "float32",
|
| 31 |
+
"shape": [
|
| 32 |
+
1,
|
| 33 |
+
3
|
| 34 |
+
],
|
| 35 |
+
"order": [
|
| 36 |
+
"choice",
|
| 37 |
+
"score",
|
| 38 |
+
"noul"
|
| 39 |
+
]
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"outputs": {
|
| 43 |
+
"token_logits": {
|
| 44 |
+
"dtype": "float32",
|
| 45 |
+
"shape": [
|
| 46 |
+
1,
|
| 47 |
+
512
|
| 48 |
+
],
|
| 49 |
+
"read": "at the option marker positions"
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"files": [
|
| 53 |
+
{
|
| 54 |
+
"path": "main.hash",
|
| 55 |
+
"bytes": 32,
|
| 56 |
+
"sha256": "e6493cb1f5cabeaa395d558628485d906f3216a0f612b52891cfd334ba3ce732"
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"path": "main.mlirb",
|
| 60 |
+
"bytes": 578357214,
|
| 61 |
+
"sha256": "f9287684c9e2d01fb38a7776aa0f5397c733f8f7d390b6cabe36cfb45d3c81d4"
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"path": "metadata.json",
|
| 65 |
+
"bytes": 391,
|
| 66 |
+
"sha256": "e9ee198e153c93d1d4678df8751cab8f3f9811e69a329c9fdea4cef19bd64366"
|
| 67 |
+
}
|
| 68 |
+
],
|
| 69 |
+
"op_counts": {
|
| 70 |
+
"builtin.module": 1,
|
| 71 |
+
"coreai.cast": 1,
|
| 72 |
+
"coreai.concat": 44,
|
| 73 |
+
"coreai.constant": 195,
|
| 74 |
+
"coreai.decomposable.broadcasting_add": 130,
|
| 75 |
+
"coreai.decomposable.broadcasting_batch_matmul": 147,
|
| 76 |
+
"coreai.decomposable.broadcasting_mul": 182,
|
| 77 |
+
"coreai.decomposable.broadcasting_sub": 2,
|
| 78 |
+
"coreai.gather_nd": 1,
|
| 79 |
+
"coreai.gelu": 23,
|
| 80 |
+
"coreai.graph": 2,
|
| 81 |
+
"coreai.invoke": 50,
|
| 82 |
+
"coreai.output": 2,
|
| 83 |
+
"coreai.reduce_mean": 2,
|
| 84 |
+
"coreai.relu": 2,
|
| 85 |
+
"coreai.reshape": 122,
|
| 86 |
+
"coreai.rsqrt": 1,
|
| 87 |
+
"coreai.slice": 72,
|
| 88 |
+
"coreai.softmax": 24,
|
| 89 |
+
"coreai.split": 66,
|
| 90 |
+
"coreai.transpose": 215
|
| 91 |
+
},
|
| 92 |
+
"seconds": {
|
| 93 |
+
"torch_export": 2.718504459131509,
|
| 94 |
+
"convert_total": 0.987051707925275,
|
| 95 |
+
"optimize": 0.05586250009946525,
|
| 96 |
+
"save": 0.4756990000605583,
|
| 97 |
+
"total": 53.41586508299224
|
| 98 |
+
},
|
| 99 |
+
"torch_export_gate": {
|
| 100 |
+
"status": "PASS",
|
| 101 |
+
"record": "provenance/export-gate.json",
|
| 102 |
+
"rows_stride": 4,
|
| 103 |
+
"rows_in_window": 2100,
|
| 104 |
+
"rows": 560,
|
| 105 |
+
"argmax_identical": 560,
|
| 106 |
+
"max_probability_error": 6.561606290444999e-05,
|
| 107 |
+
"max_marker_abs_error": 0.0003275871276855469,
|
| 108 |
+
"typed_accuracy": {
|
| 109 |
+
"choice": {
|
| 110 |
+
"count": 149,
|
| 111 |
+
"correct": 102
|
| 112 |
+
},
|
| 113 |
+
"score": {
|
| 114 |
+
"count": 198,
|
| 115 |
+
"correct": 135
|
| 116 |
+
},
|
| 117 |
+
"noul": {
|
| 118 |
+
"count": 150,
|
| 119 |
+
"correct": 128
|
| 120 |
+
}
|
| 121 |
+
}
|
| 122 |
+
},
|
| 123 |
+
"authoring_records": [
|
| 124 |
+
"/Users/majimadaisuke/code/coreai/_julia1/julia-1/results/authoring_fp32_s512.json"
|
| 125 |
+
],
|
| 126 |
+
"runtime_gate": "NOT RUN — gate_julia_runtime.py <this folder> --compute cpu_only|gpu",
|
| 127 |
+
"environment": {
|
| 128 |
+
"date": "2026-09-30T09:40:00+09:00",
|
| 129 |
+
"machine": "Apple M4 Max",
|
| 130 |
+
"macos_version": "27.0",
|
| 131 |
+
"macos_build": "26A428",
|
| 132 |
+
"coreai_build": "coreai-build 3600.83.1",
|
| 133 |
+
"python": "3.11.13",
|
| 134 |
+
"packages": {
|
| 135 |
+
"torch": "2.9.0",
|
| 136 |
+
"coreai-torch": "0.4.1",
|
| 137 |
+
"coreai-core": "1.0.0b2",
|
| 138 |
+
"numpy": "2.3.5",
|
| 139 |
+
"safetensors": "0.7.0"
|
| 140 |
+
},
|
| 141 |
+
"argv": [
|
| 142 |
+
"conversion/julia/export_julia.py",
|
| 143 |
+
"--window",
|
| 144 |
+
"512",
|
| 145 |
+
"--dtype",
|
| 146 |
+
"fp32",
|
| 147 |
+
"--rows-stride",
|
| 148 |
+
"4"
|
| 149 |
+
]
|
| 150 |
+
},
|
| 151 |
+
"input_hashes": {
|
| 152 |
+
"/Users/majimadaisuke/code/coreai/_julia1/julia-1/results/authoring_fp32_s512.json": "69bc0befb1922e7e93cb9937a9f6ee2386b5e090bae7435dd3a65904b66c5039",
|
| 153 |
+
"/Users/majimadaisuke/code/coreai/_julia1/julia-1/oracle/rows.json": "c805348599fb0a87688246f0a290bb293e6f967c5fe938686d23fa8b3ea1377a",
|
| 154 |
+
"/Users/majimadaisuke/code/coreai/coreai-models-community-julia1-wt/conversion/julia/export_julia.py": "606dc911e2c092e8ee94affc28a52796bb7254909e9f1a2474f8a60ab6f27726",
|
| 155 |
+
"/Users/majimadaisuke/code/coreai/coreai-models-community-julia1-wt/conversion/julia/_julia_model.py": "616f219c230e2b36c40ef0939e8402ec42ed8fae7ce81f0c1b79de91b75b4cfe",
|
| 156 |
+
"/Users/majimadaisuke/code/coreai/coreai-models-community-julia1-wt/conversion/julia/_julia_host.py": "c77e391110b6295efdbad6ecb148b36cda06c6678183fa2e4dd1fd24ad967786",
|
| 157 |
+
"/Users/majimadaisuke/code/coreai/coreai-models-community-julia1-wt/conversion/julia/_gate_metrics.py": "8425201abe9aa7d232d67f95ca8b34a37a33d26835c3540eddcad9606e258de2"
|
| 158 |
+
},
|
| 159 |
+
"bytes": 578357637
|
| 160 |
+
}
|
macos/fp32-s512/provenance/runtime-gate.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
macos/fp32-s512/reference.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
macos/fp32-s512/tokenizer/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:609d8f4c067cd3950f88594c5a802616cea245823836ef5848ee4fc40aab5b6f
|
| 3 |
+
size 34363188
|
macos/fp32-s512/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<bos>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"cls_token": "<bos>",
|
| 6 |
+
"eos_token": "<eos>",
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<start_of_turn>",
|
| 9 |
+
"<end_of_turn>"
|
| 10 |
+
],
|
| 11 |
+
"is_local": true,
|
| 12 |
+
"mask_token": "<mask>",
|
| 13 |
+
"max_length": 512,
|
| 14 |
+
"model_input_names": [
|
| 15 |
+
"input_ids",
|
| 16 |
+
"attention_mask"
|
| 17 |
+
],
|
| 18 |
+
"model_max_length": 8192,
|
| 19 |
+
"pad_token": "<pad>",
|
| 20 |
+
"padding_side": "right",
|
| 21 |
+
"sep_token": "<eos>",
|
| 22 |
+
"spaces_between_special_tokens": false,
|
| 23 |
+
"stride": 0,
|
| 24 |
+
"tokenizer_class": "TokenizersBackend",
|
| 25 |
+
"truncation_side": "right",
|
| 26 |
+
"truncation_strategy": "longest_first",
|
| 27 |
+
"unk_token": "<unk>"
|
| 28 |
+
}
|