init: lemer-lite v1 — text-only Q4 MLX, 2.47 GB, fits iPhone base
Browse filesStrip vision + audio from lemer-mlx-bf16 source, mlx_lm.convert flat Q4
(4.501 bits/weight). Architecture switched to Gemma4ForCausalLM. Same
LEK-aligned text reasoning as full lemer; multimodal towers removed for
sub-3GB ceiling targeting iPhone base / iPad / base Apple Silicon.
Trade: text only, flat Q4 not mixed-precision Q4. Best-effort tier.
- .gitattributes +1 -0
- LICENSE +287 -0
- README.md +62 -0
- chat_template.jinja +344 -0
- config.json +101 -0
- generation_config.json +14 -0
- model.safetensors +3 -0
- model.safetensors.index.json +1244 -0
- tokenizer.json +3 -0
- tokenizer_config.json +96 -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
|
LICENSE
ADDED
|
@@ -0,0 +1,287 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
EUROPEAN UNION PUBLIC LICENCE v. 1.2
|
| 2 |
+
EUPL © the European Union 2007, 2016
|
| 3 |
+
|
| 4 |
+
This European Union Public Licence (the ‘EUPL’) applies to the Work (as defined
|
| 5 |
+
below) which is provided under the terms of this Licence. Any use of the Work,
|
| 6 |
+
other than as authorised under this Licence is prohibited (to the extent such
|
| 7 |
+
use is covered by a right of the copyright holder of the Work).
|
| 8 |
+
|
| 9 |
+
The Work is provided under the terms of this Licence when the Licensor (as
|
| 10 |
+
defined below) has placed the following notice immediately following the
|
| 11 |
+
copyright notice for the Work:
|
| 12 |
+
|
| 13 |
+
Licensed under the EUPL
|
| 14 |
+
|
| 15 |
+
or has expressed by any other means his willingness to license under the EUPL.
|
| 16 |
+
|
| 17 |
+
1. Definitions
|
| 18 |
+
|
| 19 |
+
In this Licence, the following terms have the following meaning:
|
| 20 |
+
|
| 21 |
+
- ‘The Licence’: this Licence.
|
| 22 |
+
|
| 23 |
+
- ‘The Original Work’: the work or software distributed or communicated by the
|
| 24 |
+
Licensor under this Licence, available as Source Code and also as Executable
|
| 25 |
+
Code as the case may be.
|
| 26 |
+
|
| 27 |
+
- ‘Derivative Works’: the works or software that could be created by the
|
| 28 |
+
Licensee, based upon the Original Work or modifications thereof. This Licence
|
| 29 |
+
does not define the extent of modification or dependence on the Original Work
|
| 30 |
+
required in order to classify a work as a Derivative Work; this extent is
|
| 31 |
+
determined by copyright law applicable in the country mentioned in Article 15.
|
| 32 |
+
|
| 33 |
+
- ‘The Work’: the Original Work or its Derivative Works.
|
| 34 |
+
|
| 35 |
+
- ‘The Source Code’: the human-readable form of the Work which is the most
|
| 36 |
+
convenient for people to study and modify.
|
| 37 |
+
|
| 38 |
+
- ‘The Executable Code’: any code which has generally been compiled and which is
|
| 39 |
+
meant to be interpreted by a computer as a program.
|
| 40 |
+
|
| 41 |
+
- ‘The Licensor’: the natural or legal person that distributes or communicates
|
| 42 |
+
the Work under the Licence.
|
| 43 |
+
|
| 44 |
+
- ‘Contributor(s)’: any natural or legal person who modifies the Work under the
|
| 45 |
+
Licence, or otherwise contributes to the creation of a Derivative Work.
|
| 46 |
+
|
| 47 |
+
- ‘The Licensee’ or ‘You’: any natural or legal person who makes any usage of
|
| 48 |
+
the Work under the terms of the Licence.
|
| 49 |
+
|
| 50 |
+
- ‘Distribution’ or ‘Communication’: any act of selling, giving, lending,
|
| 51 |
+
renting, distributing, communicating, transmitting, or otherwise making
|
| 52 |
+
available, online or offline, copies of the Work or providing access to its
|
| 53 |
+
essential functionalities at the disposal of any other natural or legal
|
| 54 |
+
person.
|
| 55 |
+
|
| 56 |
+
2. Scope of the rights granted by the Licence
|
| 57 |
+
|
| 58 |
+
The Licensor hereby grants You a worldwide, royalty-free, non-exclusive,
|
| 59 |
+
sublicensable licence to do the following, for the duration of copyright vested
|
| 60 |
+
in the Original Work:
|
| 61 |
+
|
| 62 |
+
- use the Work in any circumstance and for all usage,
|
| 63 |
+
- reproduce the Work,
|
| 64 |
+
- modify the Work, and make Derivative Works based upon the Work,
|
| 65 |
+
- communicate to the public, including the right to make available or display
|
| 66 |
+
the Work or copies thereof to the public and perform publicly, as the case may
|
| 67 |
+
be, the Work,
|
| 68 |
+
- distribute the Work or copies thereof,
|
| 69 |
+
- lend and rent the Work or copies thereof,
|
| 70 |
+
- sublicense rights in the Work or copies thereof.
|
| 71 |
+
|
| 72 |
+
Those rights can be exercised on any media, supports and formats, whether now
|
| 73 |
+
known or later invented, as far as the applicable law permits so.
|
| 74 |
+
|
| 75 |
+
In the countries where moral rights apply, the Licensor waives his right to
|
| 76 |
+
exercise his moral right to the extent allowed by law in order to make effective
|
| 77 |
+
the licence of the economic rights here above listed.
|
| 78 |
+
|
| 79 |
+
The Licensor grants to the Licensee royalty-free, non-exclusive usage rights to
|
| 80 |
+
any patents held by the Licensor, to the extent necessary to make use of the
|
| 81 |
+
rights granted on the Work under this Licence.
|
| 82 |
+
|
| 83 |
+
3. Communication of the Source Code
|
| 84 |
+
|
| 85 |
+
The Licensor may provide the Work either in its Source Code form, or as
|
| 86 |
+
Executable Code. If the Work is provided as Executable Code, the Licensor
|
| 87 |
+
provides in addition a machine-readable copy of the Source Code of the Work
|
| 88 |
+
along with each copy of the Work that the Licensor distributes or indicates, in
|
| 89 |
+
a notice following the copyright notice attached to the Work, a repository where
|
| 90 |
+
the Source Code is easily and freely accessible for as long as the Licensor
|
| 91 |
+
continues to distribute or communicate the Work.
|
| 92 |
+
|
| 93 |
+
4. Limitations on copyright
|
| 94 |
+
|
| 95 |
+
Nothing in this Licence is intended to deprive the Licensee of the benefits from
|
| 96 |
+
any exception or limitation to the exclusive rights of the rights owners in the
|
| 97 |
+
Work, of the exhaustion of those rights or of other applicable limitations
|
| 98 |
+
thereto.
|
| 99 |
+
|
| 100 |
+
5. Obligations of the Licensee
|
| 101 |
+
|
| 102 |
+
The grant of the rights mentioned above is subject to some restrictions and
|
| 103 |
+
obligations imposed on the Licensee. Those obligations are the following:
|
| 104 |
+
|
| 105 |
+
Attribution right: The Licensee shall keep intact all copyright, patent or
|
| 106 |
+
trademarks notices and all notices that refer to the Licence and to the
|
| 107 |
+
disclaimer of warranties. The Licensee must include a copy of such notices and a
|
| 108 |
+
copy of the Licence with every copy of the Work he/she distributes or
|
| 109 |
+
communicates. The Licensee must cause any Derivative Work to carry prominent
|
| 110 |
+
notices stating that the Work has been modified and the date of modification.
|
| 111 |
+
|
| 112 |
+
Copyleft clause: If the Licensee distributes or communicates copies of the
|
| 113 |
+
Original Works or Derivative Works, this Distribution or Communication will be
|
| 114 |
+
done under the terms of this Licence or of a later version of this Licence
|
| 115 |
+
unless the Original Work is expressly distributed only under this version of the
|
| 116 |
+
Licence — for example by communicating ‘EUPL v. 1.2 only’. The Licensee
|
| 117 |
+
(becoming Licensor) cannot offer or impose any additional terms or conditions on
|
| 118 |
+
the Work or Derivative Work that alter or restrict the terms of the Licence.
|
| 119 |
+
|
| 120 |
+
Compatibility clause: If the Licensee Distributes or Communicates Derivative
|
| 121 |
+
Works or copies thereof based upon both the Work and another work licensed under
|
| 122 |
+
a Compatible Licence, this Distribution or Communication can be done under the
|
| 123 |
+
terms of this Compatible Licence. For the sake of this clause, ‘Compatible
|
| 124 |
+
Licence’ refers to the licences listed in the appendix attached to this Licence.
|
| 125 |
+
Should the Licensee's obligations under the Compatible Licence conflict with
|
| 126 |
+
his/her obligations under this Licence, the obligations of the Compatible
|
| 127 |
+
Licence shall prevail.
|
| 128 |
+
|
| 129 |
+
Provision of Source Code: When distributing or communicating copies of the Work,
|
| 130 |
+
the Licensee will provide a machine-readable copy of the Source Code or indicate
|
| 131 |
+
a repository where this Source will be easily and freely available for as long
|
| 132 |
+
as the Licensee continues to distribute or communicate the Work.
|
| 133 |
+
|
| 134 |
+
Legal Protection: This Licence does not grant permission to use the trade names,
|
| 135 |
+
trademarks, service marks, or names of the Licensor, except as required for
|
| 136 |
+
reasonable and customary use in describing the origin of the Work and
|
| 137 |
+
reproducing the content of the copyright notice.
|
| 138 |
+
|
| 139 |
+
6. Chain of Authorship
|
| 140 |
+
|
| 141 |
+
The original Licensor warrants that the copyright in the Original Work granted
|
| 142 |
+
hereunder is owned by him/her or licensed to him/her and that he/she has the
|
| 143 |
+
power and authority to grant the Licence.
|
| 144 |
+
|
| 145 |
+
Each Contributor warrants that the copyright in the modifications he/she brings
|
| 146 |
+
to the Work are owned by him/her or licensed to him/her and that he/she has the
|
| 147 |
+
power and authority to grant the Licence.
|
| 148 |
+
|
| 149 |
+
Each time You accept the Licence, the original Licensor and subsequent
|
| 150 |
+
Contributors grant You a licence to their contributions to the Work, under the
|
| 151 |
+
terms of this Licence.
|
| 152 |
+
|
| 153 |
+
7. Disclaimer of Warranty
|
| 154 |
+
|
| 155 |
+
The Work is a work in progress, which is continuously improved by numerous
|
| 156 |
+
Contributors. It is not a finished work and may therefore contain defects or
|
| 157 |
+
‘bugs’ inherent to this type of development.
|
| 158 |
+
|
| 159 |
+
For the above reason, the Work is provided under the Licence on an ‘as is’ basis
|
| 160 |
+
and without warranties of any kind concerning the Work, including without
|
| 161 |
+
limitation merchantability, fitness for a particular purpose, absence of defects
|
| 162 |
+
or errors, accuracy, non-infringement of intellectual property rights other than
|
| 163 |
+
copyright as stated in Article 6 of this Licence.
|
| 164 |
+
|
| 165 |
+
This disclaimer of warranty is an essential part of the Licence and a condition
|
| 166 |
+
for the grant of any rights to the Work.
|
| 167 |
+
|
| 168 |
+
8. Disclaimer of Liability
|
| 169 |
+
|
| 170 |
+
Except in the cases of wilful misconduct or damages directly caused to natural
|
| 171 |
+
persons, the Licensor will in no event be liable for any direct or indirect,
|
| 172 |
+
material or moral, damages of any kind, arising out of the Licence or of the use
|
| 173 |
+
of the Work, including without limitation, damages for loss of goodwill, work
|
| 174 |
+
stoppage, computer failure or malfunction, loss of data or any commercial
|
| 175 |
+
damage, even if the Licensor has been advised of the possibility of such damage.
|
| 176 |
+
However, the Licensor will be liable under statutory product liability laws as
|
| 177 |
+
far such laws apply to the Work.
|
| 178 |
+
|
| 179 |
+
9. Additional agreements
|
| 180 |
+
|
| 181 |
+
While distributing the Work, You may choose to conclude an additional agreement,
|
| 182 |
+
defining obligations or services consistent with this Licence. However, if
|
| 183 |
+
accepting obligations, You may act only on your own behalf and on your sole
|
| 184 |
+
responsibility, not on behalf of the original Licensor or any other Contributor,
|
| 185 |
+
and only if You agree to indemnify, defend, and hold each Contributor harmless
|
| 186 |
+
for any liability incurred by, or claims asserted against such Contributor by
|
| 187 |
+
the fact You have accepted any warranty or additional liability.
|
| 188 |
+
|
| 189 |
+
10. Acceptance of the Licence
|
| 190 |
+
|
| 191 |
+
The provisions of this Licence can be accepted by clicking on an icon ‘I agree’
|
| 192 |
+
placed under the bottom of a window displaying the text of this Licence or by
|
| 193 |
+
affirming consent in any other similar way, in accordance with the rules of
|
| 194 |
+
applicable law. Clicking on that icon indicates your clear and irrevocable
|
| 195 |
+
acceptance of this Licence and all of its terms and conditions.
|
| 196 |
+
|
| 197 |
+
Similarly, you irrevocably accept this Licence and all of its terms and
|
| 198 |
+
conditions by exercising any rights granted to You by Article 2 of this Licence,
|
| 199 |
+
such as the use of the Work, the creation by You of a Derivative Work or the
|
| 200 |
+
Distribution or Communication by You of the Work or copies thereof.
|
| 201 |
+
|
| 202 |
+
11. Information to the public
|
| 203 |
+
|
| 204 |
+
In case of any Distribution or Communication of the Work by means of electronic
|
| 205 |
+
communication by You (for example, by offering to download the Work from a
|
| 206 |
+
remote location) the distribution channel or media (for example, a website) must
|
| 207 |
+
at least provide to the public the information requested by the applicable law
|
| 208 |
+
regarding the Licensor, the Licence and the way it may be accessible, concluded,
|
| 209 |
+
stored and reproduced by the Licensee.
|
| 210 |
+
|
| 211 |
+
12. Termination of the Licence
|
| 212 |
+
|
| 213 |
+
The Licence and the rights granted hereunder will terminate automatically upon
|
| 214 |
+
any breach by the Licensee of the terms of the Licence.
|
| 215 |
+
|
| 216 |
+
Such a termination will not terminate the licences of any person who has
|
| 217 |
+
received the Work from the Licensee under the Licence, provided such persons
|
| 218 |
+
remain in full compliance with the Licence.
|
| 219 |
+
|
| 220 |
+
13. Miscellaneous
|
| 221 |
+
|
| 222 |
+
Without prejudice of Article 9 above, the Licence represents the complete
|
| 223 |
+
agreement between the Parties as to the Work.
|
| 224 |
+
|
| 225 |
+
If any provision of the Licence is invalid or unenforceable under applicable
|
| 226 |
+
law, this will not affect the validity or enforceability of the Licence as a
|
| 227 |
+
whole. Such provision will be construed or reformed so as necessary to make it
|
| 228 |
+
valid and enforceable.
|
| 229 |
+
|
| 230 |
+
The European Commission may publish other linguistic versions or new versions of
|
| 231 |
+
this Licence or updated versions of the Appendix, so far this is required and
|
| 232 |
+
reasonable, without reducing the scope of the rights granted by the Licence. New
|
| 233 |
+
versions of the Licence will be published with a unique version number.
|
| 234 |
+
|
| 235 |
+
All linguistic versions of this Licence, approved by the European Commission,
|
| 236 |
+
have identical value. Parties can take advantage of the linguistic version of
|
| 237 |
+
their choice.
|
| 238 |
+
|
| 239 |
+
14. Jurisdiction
|
| 240 |
+
|
| 241 |
+
Without prejudice to specific agreement between parties,
|
| 242 |
+
|
| 243 |
+
- any litigation resulting from the interpretation of this License, arising
|
| 244 |
+
between the European Union institutions, bodies, offices or agencies, as a
|
| 245 |
+
Licensor, and any Licensee, will be subject to the jurisdiction of the Court
|
| 246 |
+
of Justice of the European Union, as laid down in article 272 of the Treaty on
|
| 247 |
+
the Functioning of the European Union,
|
| 248 |
+
|
| 249 |
+
- any litigation arising between other parties and resulting from the
|
| 250 |
+
interpretation of this License, will be subject to the exclusive jurisdiction
|
| 251 |
+
of the competent court where the Licensor resides or conducts its primary
|
| 252 |
+
business.
|
| 253 |
+
|
| 254 |
+
15. Applicable Law
|
| 255 |
+
|
| 256 |
+
Without prejudice to specific agreement between parties,
|
| 257 |
+
|
| 258 |
+
- this Licence shall be governed by the law of the European Union Member State
|
| 259 |
+
where the Licensor has his seat, resides or has his registered office,
|
| 260 |
+
|
| 261 |
+
- this licence shall be governed by Belgian law if the Licensor has no seat,
|
| 262 |
+
residence or registered office inside a European Union Member State.
|
| 263 |
+
|
| 264 |
+
Appendix
|
| 265 |
+
|
| 266 |
+
‘Compatible Licences’ according to Article 5 EUPL are:
|
| 267 |
+
|
| 268 |
+
- GNU General Public License (GPL) v. 2, v. 3
|
| 269 |
+
- GNU Affero General Public License (AGPL) v. 3
|
| 270 |
+
- Open Software License (OSL) v. 2.1, v. 3.0
|
| 271 |
+
- Eclipse Public License (EPL) v. 1.0
|
| 272 |
+
- CeCILL v. 2.0, v. 2.1
|
| 273 |
+
- Mozilla Public Licence (MPL) v. 2
|
| 274 |
+
- GNU Lesser General Public Licence (LGPL) v. 2.1, v. 3
|
| 275 |
+
- Creative Commons Attribution-ShareAlike v. 3.0 Unported (CC BY-SA 3.0) for
|
| 276 |
+
works other than software
|
| 277 |
+
- European Union Public Licence (EUPL) v. 1.1, v. 1.2
|
| 278 |
+
- Québec Free and Open-Source Licence — Reciprocity (LiLiQ-R) or Strong
|
| 279 |
+
Reciprocity (LiLiQ-R+).
|
| 280 |
+
|
| 281 |
+
The European Commission may update this Appendix to later versions of the above
|
| 282 |
+
licences without producing a new version of the EUPL, as long as they provide
|
| 283 |
+
the rights granted in Article 2 of this Licence and protect the covered Source
|
| 284 |
+
Code from exclusive appropriation.
|
| 285 |
+
|
| 286 |
+
All other changes or additions to this Appendix require the production of a new
|
| 287 |
+
EUPL version.
|
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: eupl-1.2
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
+
library_name: mlx
|
| 5 |
+
base_model:
|
| 6 |
+
- lthn/lemer
|
| 7 |
+
base_model_relation: quantized
|
| 8 |
+
tags:
|
| 9 |
+
- gemma4
|
| 10 |
+
- lemma
|
| 11 |
+
- mlx
|
| 12 |
+
- 4bit
|
| 13 |
+
- apple-silicon
|
| 14 |
+
- on-device
|
| 15 |
+
- text-only
|
| 16 |
+
- lite
|
| 17 |
+
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
# Lemer-Lite — text-only, 2.5 GB, fits iPhone base
|
| 21 |
+
|
| 22 |
+
Stripped-down sibling of [`lthn/lemer`](https://huggingface.co/lthn/lemer) for devices that can't load the full multimodal build (≥3 GB ceiling).
|
| 23 |
+
|
| 24 |
+
| Variant | Size | Towers |
|
| 25 |
+
|---|---|---|
|
| 26 |
+
| [lthn/lemer](https://huggingface.co/lthn/lemer) | 4.06 GB | text + vision + audio |
|
| 27 |
+
| **lthn/lemer-lite** (you are here) | **2.47 GB** | text only |
|
| 28 |
+
|
| 29 |
+
## What it is
|
| 30 |
+
|
| 31 |
+
Same LEK-aligned Gemma 4 E2B base as [lemer](https://huggingface.co/lthn/lemer), with vision and audio towers stripped and the text path quantised flat 4-bit (4.501 bits/weight) instead of mixed-precision.
|
| 32 |
+
|
| 33 |
+
The Lethean Ethical Kernel (LEK) is fully present in the weights — the consent-based reasoning behaviour is identical to the full lemer.
|
| 34 |
+
|
| 35 |
+
## Trade-offs (the honest version)
|
| 36 |
+
|
| 37 |
+
This is a **best-effort tier** for users on smaller devices. The `-lite` prefix is a promise: we are packing this tight, results will vary, but you get to load and run the model.
|
| 38 |
+
|
| 39 |
+
- **Text only** — no image input, no audio input. If your use case needs eyes, run the full lemer on a Pro-class device.
|
| 40 |
+
- **Flat Q4** instead of mixed-precision Q4 — fluency is solid, rare-token recall slightly worse than the full lemer.
|
| 41 |
+
- **Same LEK alignment** — the ethical reasoning is in the text path, which is preserved.
|
| 42 |
+
|
| 43 |
+
## Targets
|
| 44 |
+
|
| 45 |
+
- iPhone base (≥3 GB free), iPad, base-spec Apple Silicon laptops.
|
| 46 |
+
- Anywhere the full 4 GB lemer would refuse to load.
|
| 47 |
+
|
| 48 |
+
## Loading
|
| 49 |
+
|
| 50 |
+
```python
|
| 51 |
+
from mlx_lm import load, generate
|
| 52 |
+
model, tokenizer = load("lthn/lemer-lite")
|
| 53 |
+
prompt = tokenizer.apply_chat_template(
|
| 54 |
+
[{"role": "user", "content": "Hello"}],
|
| 55 |
+
tokenize=False, add_generation_prompt=True,
|
| 56 |
+
)
|
| 57 |
+
print(generate(model, tokenizer, prompt=prompt, max_tokens=200))
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
## License
|
| 61 |
+
|
| 62 |
+
EUPL-1.2.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,344 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- macro format_parameters(properties, required) -%}
|
| 2 |
+
{%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
|
| 3 |
+
{%- set ns = namespace(found_first=false) -%}
|
| 4 |
+
{%- for key, value in properties | dictsort -%}
|
| 5 |
+
{%- set add_comma = false -%}
|
| 6 |
+
{%- if key not in standard_keys -%}
|
| 7 |
+
{%- if ns.found_first %},{% endif -%}
|
| 8 |
+
{%- set ns.found_first = true -%}
|
| 9 |
+
{{ key }}:{
|
| 10 |
+
{%- if value['description'] -%}
|
| 11 |
+
description:<|"|>{{ value['description'] }}<|"|>
|
| 12 |
+
{%- set add_comma = true -%}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- if value['type'] | upper == 'STRING' -%}
|
| 15 |
+
{%- if value['enum'] -%}
|
| 16 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 17 |
+
enum:{{ format_argument(value['enum']) }}
|
| 18 |
+
{%- endif -%}
|
| 19 |
+
{%- elif value['type'] | upper == 'ARRAY' -%}
|
| 20 |
+
{%- if value['items'] is mapping and value['items'] -%}
|
| 21 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 22 |
+
items:{
|
| 23 |
+
{%- set ns_items = namespace(found_first=false) -%}
|
| 24 |
+
{%- for item_key, item_value in value['items'] | dictsort -%}
|
| 25 |
+
{%- if item_value is not none -%}
|
| 26 |
+
{%- if ns_items.found_first %},{% endif -%}
|
| 27 |
+
{%- set ns_items.found_first = true -%}
|
| 28 |
+
{%- if item_key == 'properties' -%}
|
| 29 |
+
properties:{
|
| 30 |
+
{%- if item_value is mapping -%}
|
| 31 |
+
{{- format_parameters(item_value, value['items']['required'] | default([])) -}}
|
| 32 |
+
{%- endif -%}
|
| 33 |
+
}
|
| 34 |
+
{%- elif item_key == 'required' -%}
|
| 35 |
+
required:[
|
| 36 |
+
{%- for req_item in item_value -%}
|
| 37 |
+
<|"|>{{- req_item -}}<|"|>
|
| 38 |
+
{%- if not loop.last %},{% endif -%}
|
| 39 |
+
{%- endfor -%}
|
| 40 |
+
]
|
| 41 |
+
{%- elif item_key == 'type' -%}
|
| 42 |
+
{%- if item_value is string -%}
|
| 43 |
+
type:{{ format_argument(item_value | upper) }}
|
| 44 |
+
{%- else -%}
|
| 45 |
+
type:{{ format_argument(item_value | map('upper') | list) }}
|
| 46 |
+
{%- endif -%}
|
| 47 |
+
{%- else -%}
|
| 48 |
+
{{ item_key }}:{{ format_argument(item_value) }}
|
| 49 |
+
{%- endif -%}
|
| 50 |
+
{%- endif -%}
|
| 51 |
+
{%- endfor -%}
|
| 52 |
+
}
|
| 53 |
+
{%- endif -%}
|
| 54 |
+
{%- endif -%}
|
| 55 |
+
{%- if value['nullable'] %}
|
| 56 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 57 |
+
nullable:true
|
| 58 |
+
{%- endif -%}
|
| 59 |
+
{%- if value['type'] | upper == 'OBJECT' -%}
|
| 60 |
+
{%- if value['properties'] is defined and value['properties'] is mapping -%}
|
| 61 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 62 |
+
properties:{
|
| 63 |
+
{{- format_parameters(value['properties'], value['required'] | default([])) -}}
|
| 64 |
+
}
|
| 65 |
+
{%- elif value is mapping -%}
|
| 66 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 67 |
+
properties:{
|
| 68 |
+
{{- format_parameters(value, value['required'] | default([])) -}}
|
| 69 |
+
}
|
| 70 |
+
{%- endif -%}
|
| 71 |
+
{%- if value['required'] -%}
|
| 72 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 73 |
+
required:[
|
| 74 |
+
{%- for item in value['required'] | default([]) -%}
|
| 75 |
+
<|"|>{{- item -}}<|"|>
|
| 76 |
+
{%- if not loop.last %},{% endif -%}
|
| 77 |
+
{%- endfor -%}
|
| 78 |
+
]
|
| 79 |
+
{%- endif -%}
|
| 80 |
+
{%- endif -%}
|
| 81 |
+
{%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
|
| 82 |
+
type:<|"|>{{ value['type'] | upper }}<|"|>}
|
| 83 |
+
{%- endif -%}
|
| 84 |
+
{%- endfor -%}
|
| 85 |
+
{%- endmacro -%}
|
| 86 |
+
{%- macro format_function_declaration(tool_data) -%}
|
| 87 |
+
declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
|
| 88 |
+
{%- set params = tool_data['function']['parameters'] -%}
|
| 89 |
+
{%- if params -%}
|
| 90 |
+
,parameters:{
|
| 91 |
+
{%- if params['properties'] -%}
|
| 92 |
+
properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
|
| 93 |
+
{%- endif -%}
|
| 94 |
+
{%- if params['required'] -%}
|
| 95 |
+
required:[
|
| 96 |
+
{%- for item in params['required'] -%}
|
| 97 |
+
<|"|>{{- item -}}<|"|>
|
| 98 |
+
{{- ',' if not loop.last -}}
|
| 99 |
+
{%- endfor -%}
|
| 100 |
+
],
|
| 101 |
+
{%- endif -%}
|
| 102 |
+
{%- if params['type'] -%}
|
| 103 |
+
type:<|"|>{{- params['type'] | upper -}}<|"|>}
|
| 104 |
+
{%- endif -%}
|
| 105 |
+
{%- endif -%}
|
| 106 |
+
{%- if 'response' in tool_data['function'] -%}
|
| 107 |
+
{%- set response_declaration = tool_data['function']['response'] -%}
|
| 108 |
+
,response:{
|
| 109 |
+
{%- if response_declaration['description'] -%}
|
| 110 |
+
description:<|"|>{{- response_declaration['description'] -}}<|"|>,
|
| 111 |
+
{%- endif -%}
|
| 112 |
+
{%- if response_declaration['type'] | upper == 'OBJECT' -%}
|
| 113 |
+
type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
|
| 114 |
+
{%- endif -%}
|
| 115 |
+
{%- endif -%}
|
| 116 |
+
}
|
| 117 |
+
{%- endmacro -%}
|
| 118 |
+
{%- macro format_argument(argument, escape_keys=True) -%}
|
| 119 |
+
{%- if argument is string -%}
|
| 120 |
+
{{- '<|"|>' + argument + '<|"|>' -}}
|
| 121 |
+
{%- elif argument is boolean -%}
|
| 122 |
+
{{- 'true' if argument else 'false' -}}
|
| 123 |
+
{%- elif argument is mapping -%}
|
| 124 |
+
{{- '{' -}}
|
| 125 |
+
{%- set ns = namespace(found_first=false) -%}
|
| 126 |
+
{%- for key, value in argument | dictsort -%}
|
| 127 |
+
{%- if ns.found_first %},{% endif -%}
|
| 128 |
+
{%- set ns.found_first = true -%}
|
| 129 |
+
{%- if escape_keys -%}
|
| 130 |
+
{{- '<|"|>' + key + '<|"|>' -}}
|
| 131 |
+
{%- else -%}
|
| 132 |
+
{{- key -}}
|
| 133 |
+
{%- endif -%}
|
| 134 |
+
:{{- format_argument(value, escape_keys=escape_keys) -}}
|
| 135 |
+
{%- endfor -%}
|
| 136 |
+
{{- '}' -}}
|
| 137 |
+
{%- elif argument is sequence -%}
|
| 138 |
+
{{- '[' -}}
|
| 139 |
+
{%- for item in argument -%}
|
| 140 |
+
{{- format_argument(item, escape_keys=escape_keys) -}}
|
| 141 |
+
{%- if not loop.last %},{% endif -%}
|
| 142 |
+
{%- endfor -%}
|
| 143 |
+
{{- ']' -}}
|
| 144 |
+
{%- else -%}
|
| 145 |
+
{{- argument -}}
|
| 146 |
+
{%- endif -%}
|
| 147 |
+
{%- endmacro -%}
|
| 148 |
+
{%- macro strip_thinking(text) -%}
|
| 149 |
+
{%- set ns = namespace(result='') -%}
|
| 150 |
+
{%- for part in text.split('<channel|>') -%}
|
| 151 |
+
{%- if '<|channel>' in part -%}
|
| 152 |
+
{%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
|
| 153 |
+
{%- else -%}
|
| 154 |
+
{%- set ns.result = ns.result + part -%}
|
| 155 |
+
{%- endif -%}
|
| 156 |
+
{%- endfor -%}
|
| 157 |
+
{{- ns.result | trim -}}
|
| 158 |
+
{%- endmacro -%}
|
| 159 |
+
|
| 160 |
+
{%- macro format_tool_response_block(tool_name, response) -%}
|
| 161 |
+
{{- '<|tool_response>' -}}
|
| 162 |
+
{%- if response is mapping -%}
|
| 163 |
+
{{- 'response:' + tool_name + '{' -}}
|
| 164 |
+
{%- for key, value in response | dictsort -%}
|
| 165 |
+
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
| 166 |
+
{%- if not loop.last %},{% endif -%}
|
| 167 |
+
{%- endfor -%}
|
| 168 |
+
{{- '}' -}}
|
| 169 |
+
{%- else -%}
|
| 170 |
+
{{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
|
| 171 |
+
{%- endif -%}
|
| 172 |
+
{{- '<tool_response|>' -}}
|
| 173 |
+
{%- endmacro -%}
|
| 174 |
+
|
| 175 |
+
{%- set ns = namespace(prev_message_type=None) -%}
|
| 176 |
+
{%- set loop_messages = messages -%}
|
| 177 |
+
{{- bos_token -}}
|
| 178 |
+
{#- Handle System/Tool Definitions Block -#}
|
| 179 |
+
{%- if (enable_thinking is defined and enable_thinking) or tools or messages[0]['role'] in ['system', 'developer'] -%}
|
| 180 |
+
{{- '<|turn>system\n' -}}
|
| 181 |
+
|
| 182 |
+
{#- Inject Thinking token at the very top of the FIRST system turn -#}
|
| 183 |
+
{%- if enable_thinking is defined and enable_thinking -%}
|
| 184 |
+
{{- '<|think|>\n' -}}
|
| 185 |
+
{%- set ns.prev_message_type = 'think' -%}
|
| 186 |
+
{%- endif -%}
|
| 187 |
+
|
| 188 |
+
{%- if messages[0]['role'] in ['system', 'developer'] -%}
|
| 189 |
+
{{- messages[0]['content'] | trim -}}
|
| 190 |
+
{%- set loop_messages = messages[1:] -%}
|
| 191 |
+
{%- endif -%}
|
| 192 |
+
|
| 193 |
+
{%- if tools -%}
|
| 194 |
+
{%- for tool in tools %}
|
| 195 |
+
{{- '<|tool>' -}}
|
| 196 |
+
{{- format_function_declaration(tool) | trim -}}
|
| 197 |
+
{{- '<tool|>' -}}
|
| 198 |
+
{%- endfor %}
|
| 199 |
+
{%- set ns.prev_message_type = 'tool' -%}
|
| 200 |
+
{%- endif -%}
|
| 201 |
+
|
| 202 |
+
{{- '<turn|>\n' -}}
|
| 203 |
+
{%- endif %}
|
| 204 |
+
|
| 205 |
+
{#- Pre-scan: find last user message index for reasoning guard -#}
|
| 206 |
+
{%- set ns_turn = namespace(last_user_idx=-1) -%}
|
| 207 |
+
{%- for i in range(loop_messages | length) -%}
|
| 208 |
+
{%- if loop_messages[i]['role'] == 'user' -%}
|
| 209 |
+
{%- set ns_turn.last_user_idx = i -%}
|
| 210 |
+
{%- endif -%}
|
| 211 |
+
{%- endfor -%}
|
| 212 |
+
|
| 213 |
+
{#- Loop through messages -#}
|
| 214 |
+
{%- for message in loop_messages -%}
|
| 215 |
+
{%- if message['role'] != 'tool' -%}
|
| 216 |
+
{%- set ns.prev_message_type = None -%}
|
| 217 |
+
{%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
|
| 218 |
+
{#- Detect continuation: suppress duplicate <|turn>model when previous non-tool message was also assistant -#}
|
| 219 |
+
{%- set prev_nt = namespace(role=None, found=false) -%}
|
| 220 |
+
{%- if loop.index0 > 0 -%}
|
| 221 |
+
{%- for j in range(loop.index0 - 1, -1, -1) -%}
|
| 222 |
+
{%- if not prev_nt.found -%}
|
| 223 |
+
{%- if loop_messages[j]['role'] != 'tool' -%}
|
| 224 |
+
{%- set prev_nt.role = loop_messages[j]['role'] -%}
|
| 225 |
+
{%- set prev_nt.found = true -%}
|
| 226 |
+
{%- endif -%}
|
| 227 |
+
{%- endif -%}
|
| 228 |
+
{%- endfor -%}
|
| 229 |
+
{%- endif -%}
|
| 230 |
+
{%- set continue_same_model_turn = (role == 'model' and prev_nt.role == 'assistant') -%}
|
| 231 |
+
{%- if not continue_same_model_turn -%}
|
| 232 |
+
{{- '<|turn>' + role + '\n' }}
|
| 233 |
+
{%- endif -%}
|
| 234 |
+
|
| 235 |
+
{#- Render reasoning/reasoning_content as thinking channel -#}
|
| 236 |
+
{%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
|
| 237 |
+
{%- if thinking_text and loop.index0 > ns_turn.last_user_idx and message.get('tool_calls') -%}
|
| 238 |
+
{{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
|
| 239 |
+
{%- endif -%}
|
| 240 |
+
|
| 241 |
+
{%- if message['tool_calls'] -%}
|
| 242 |
+
{%- for tool_call in message['tool_calls'] -%}
|
| 243 |
+
{%- set function = tool_call['function'] -%}
|
| 244 |
+
{{- '<|tool_call>call:' + function['name'] + '{' -}}
|
| 245 |
+
{%- if function['arguments'] is mapping -%}
|
| 246 |
+
{%- set ns_args = namespace(found_first=false) -%}
|
| 247 |
+
{%- for key, value in function['arguments'] | dictsort -%}
|
| 248 |
+
{%- if ns_args.found_first %},{% endif -%}
|
| 249 |
+
{%- set ns_args.found_first = true -%}
|
| 250 |
+
{{- key -}}:{{- format_argument(value, escape_keys=False) -}}
|
| 251 |
+
{%- endfor -%}
|
| 252 |
+
{%- elif function['arguments'] is string -%}
|
| 253 |
+
{{- function['arguments'] -}}
|
| 254 |
+
{%- endif -%}
|
| 255 |
+
{{- '}<tool_call|>' -}}
|
| 256 |
+
{%- endfor -%}
|
| 257 |
+
{%- set ns.prev_message_type = 'tool_call' -%}
|
| 258 |
+
{%- endif -%}
|
| 259 |
+
|
| 260 |
+
{%- set ns_tr_out = namespace(flag=false) -%}
|
| 261 |
+
{%- if message.get('tool_responses') -%}
|
| 262 |
+
{#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
|
| 263 |
+
{%- for tool_response in message['tool_responses'] -%}
|
| 264 |
+
{{- format_tool_response_block(tool_response['name'] | default('unknown'), tool_response['response']) -}}
|
| 265 |
+
{%- set ns_tr_out.flag = true -%}
|
| 266 |
+
{%- set ns.prev_message_type = 'tool_response' -%}
|
| 267 |
+
{%- endfor -%}
|
| 268 |
+
{%- elif message.get('tool_calls') -%}
|
| 269 |
+
{#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
|
| 270 |
+
{%- set ns_tool_scan = namespace(stopped=false) -%}
|
| 271 |
+
{%- for k in range(loop.index0 + 1, loop_messages | length) -%}
|
| 272 |
+
{%- if ns_tool_scan.stopped -%}
|
| 273 |
+
{%- elif loop_messages[k]['role'] != 'tool' -%}
|
| 274 |
+
{%- set ns_tool_scan.stopped = true -%}
|
| 275 |
+
{%- else -%}
|
| 276 |
+
{%- set follow = loop_messages[k] -%}
|
| 277 |
+
{#- Resolve tool_call_id to function name -#}
|
| 278 |
+
{%- set ns_tname = namespace(name=follow.get('name') | default('unknown')) -%}
|
| 279 |
+
{%- for tc in message['tool_calls'] -%}
|
| 280 |
+
{%- if tc.get('id') == follow.get('tool_call_id') -%}
|
| 281 |
+
{%- set ns_tname.name = tc['function']['name'] -%}
|
| 282 |
+
{%- endif -%}
|
| 283 |
+
{%- endfor -%}
|
| 284 |
+
{#- Handle content as string or content-parts array -#}
|
| 285 |
+
{%- set tool_body = follow.get('content') -%}
|
| 286 |
+
{%- if tool_body is string -%}
|
| 287 |
+
{{- format_tool_response_block(ns_tname.name, tool_body) -}}
|
| 288 |
+
{%- elif tool_body is sequence and tool_body is not string -%}
|
| 289 |
+
{%- set ns_txt = namespace(s='') -%}
|
| 290 |
+
{%- for part in tool_body -%}
|
| 291 |
+
{%- if part.get('type') == 'text' -%}
|
| 292 |
+
{%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
|
| 293 |
+
{%- endif -%}
|
| 294 |
+
{%- endfor -%}
|
| 295 |
+
{{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
|
| 296 |
+
{%- else -%}
|
| 297 |
+
{{- format_tool_response_block(ns_tname.name, tool_body) -}}
|
| 298 |
+
{%- endif -%}
|
| 299 |
+
{%- set ns_tr_out.flag = true -%}
|
| 300 |
+
{%- set ns.prev_message_type = 'tool_response' -%}
|
| 301 |
+
{%- endif -%}
|
| 302 |
+
{%- endfor -%}
|
| 303 |
+
{%- endif -%}
|
| 304 |
+
|
| 305 |
+
{%- if message['content'] is string -%}
|
| 306 |
+
{%- if role == 'model' -%}
|
| 307 |
+
{{- strip_thinking(message['content']) -}}
|
| 308 |
+
{%- else -%}
|
| 309 |
+
{{- message['content'] | trim -}}
|
| 310 |
+
{%- endif -%}
|
| 311 |
+
{%- elif message['content'] is sequence -%}
|
| 312 |
+
{%- for item in message['content'] -%}
|
| 313 |
+
{%- if item['type'] == 'text' -%}
|
| 314 |
+
{%- if role == 'model' -%}
|
| 315 |
+
{{- strip_thinking(item['text']) -}}
|
| 316 |
+
{%- else -%}
|
| 317 |
+
{{- item['text'] | trim -}}
|
| 318 |
+
{%- endif -%}
|
| 319 |
+
{%- elif item['type'] == 'image' -%}
|
| 320 |
+
{{- '<|image|>' -}}
|
| 321 |
+
{%- set ns.prev_message_type = 'image' -%}
|
| 322 |
+
{%- elif item['type'] == 'audio' -%}
|
| 323 |
+
{{- '<|audio|>' -}}
|
| 324 |
+
{%- set ns.prev_message_type = 'audio' -%}
|
| 325 |
+
{%- elif item['type'] == 'video' -%}
|
| 326 |
+
{{- '<|video|>' -}}
|
| 327 |
+
{%- set ns.prev_message_type = 'video' -%}
|
| 328 |
+
{%- endif -%}
|
| 329 |
+
{%- endfor -%}
|
| 330 |
+
{%- endif -%}
|
| 331 |
+
|
| 332 |
+
{%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
|
| 333 |
+
{{- '<|tool_response>' -}}
|
| 334 |
+
{%- elif not (ns_tr_out.flag and not message.get('content')) -%}
|
| 335 |
+
{{- '<turn|>\n' -}}
|
| 336 |
+
{%- endif -%}
|
| 337 |
+
{%- endif -%}
|
| 338 |
+
{%- endfor -%}
|
| 339 |
+
|
| 340 |
+
{%- if add_generation_prompt -%}
|
| 341 |
+
{%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
|
| 342 |
+
{{- '<|turn>model\n' -}}
|
| 343 |
+
{%- endif -%}
|
| 344 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma4ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_k_eq_v": false,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"enable_moe_block": false,
|
| 11 |
+
"eos_token_id": [
|
| 12 |
+
1,
|
| 13 |
+
106,
|
| 14 |
+
50
|
| 15 |
+
],
|
| 16 |
+
"expert_intermediate_size": null,
|
| 17 |
+
"final_logit_softcapping": 30.0,
|
| 18 |
+
"global_head_dim": 512,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 21 |
+
"hidden_size": 1536,
|
| 22 |
+
"hidden_size_per_layer_input": 256,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 6144,
|
| 25 |
+
"layer_types": [
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"full_attention"
|
| 61 |
+
],
|
| 62 |
+
"max_position_embeddings": 131072,
|
| 63 |
+
"model_type": "gemma4_text",
|
| 64 |
+
"num_attention_heads": 8,
|
| 65 |
+
"num_experts": null,
|
| 66 |
+
"num_global_key_value_heads": null,
|
| 67 |
+
"num_hidden_layers": 35,
|
| 68 |
+
"num_key_value_heads": 1,
|
| 69 |
+
"num_kv_shared_layers": 20,
|
| 70 |
+
"pad_token_id": 0,
|
| 71 |
+
"quantization": {
|
| 72 |
+
"group_size": 64,
|
| 73 |
+
"bits": 4,
|
| 74 |
+
"mode": "affine"
|
| 75 |
+
},
|
| 76 |
+
"quantization_config": {
|
| 77 |
+
"group_size": 64,
|
| 78 |
+
"bits": 4,
|
| 79 |
+
"mode": "affine"
|
| 80 |
+
},
|
| 81 |
+
"rms_norm_eps": 1e-06,
|
| 82 |
+
"rope_parameters": {
|
| 83 |
+
"full_attention": {
|
| 84 |
+
"partial_rotary_factor": 0.25,
|
| 85 |
+
"rope_theta": 1000000.0,
|
| 86 |
+
"rope_type": "proportional"
|
| 87 |
+
},
|
| 88 |
+
"sliding_attention": {
|
| 89 |
+
"rope_theta": 10000.0,
|
| 90 |
+
"rope_type": "default"
|
| 91 |
+
}
|
| 92 |
+
},
|
| 93 |
+
"sliding_window": 512,
|
| 94 |
+
"tie_word_embeddings": true,
|
| 95 |
+
"top_k_experts": null,
|
| 96 |
+
"use_bidirectional_attention": null,
|
| 97 |
+
"use_cache": true,
|
| 98 |
+
"use_double_wide_mlp": true,
|
| 99 |
+
"vocab_size": 262144,
|
| 100 |
+
"vocab_size_per_layer_input": 262144
|
| 101 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 2,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1,
|
| 6 |
+
106,
|
| 7 |
+
50
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"temperature": 1.0,
|
| 11 |
+
"top_k": 64,
|
| 12 |
+
"top_p": 0.95,
|
| 13 |
+
"transformers_version": "5.5.0.dev0"
|
| 14 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efc334d160e31af92b39700084f21bf82c242e5bded16a2141db4ae017e48124
|
| 3 |
+
size 2614750951
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 2614610502,
|
| 4 |
+
"total_parameters": 4647449856
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.embed_tokens.biases": "model.safetensors",
|
| 8 |
+
"model.embed_tokens.scales": "model.safetensors",
|
| 9 |
+
"model.embed_tokens.weight": "model.safetensors",
|
| 10 |
+
"model.embed_tokens_per_layer.biases": "model.safetensors",
|
| 11 |
+
"model.embed_tokens_per_layer.scales": "model.safetensors",
|
| 12 |
+
"model.embed_tokens_per_layer.weight": "model.safetensors",
|
| 13 |
+
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 14 |
+
"model.layers.0.layer_scalar": "model.safetensors",
|
| 15 |
+
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
| 16 |
+
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
| 17 |
+
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 18 |
+
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
| 19 |
+
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
| 20 |
+
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 21 |
+
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
| 22 |
+
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
| 23 |
+
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 24 |
+
"model.layers.0.per_layer_input_gate.biases": "model.safetensors",
|
| 25 |
+
"model.layers.0.per_layer_input_gate.scales": "model.safetensors",
|
| 26 |
+
"model.layers.0.per_layer_input_gate.weight": "model.safetensors",
|
| 27 |
+
"model.layers.0.per_layer_projection.biases": "model.safetensors",
|
| 28 |
+
"model.layers.0.per_layer_projection.scales": "model.safetensors",
|
| 29 |
+
"model.layers.0.per_layer_projection.weight": "model.safetensors",
|
| 30 |
+
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 31 |
+
"model.layers.0.post_feedforward_layernorm.weight": "model.safetensors",
|
| 32 |
+
"model.layers.0.post_per_layer_input_norm.weight": "model.safetensors",
|
| 33 |
+
"model.layers.0.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 34 |
+
"model.layers.0.self_attn.k_norm.weight": "model.safetensors",
|
| 35 |
+
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
| 36 |
+
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 37 |
+
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 38 |
+
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
| 39 |
+
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
| 40 |
+
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 41 |
+
"model.layers.0.self_attn.q_norm.weight": "model.safetensors",
|
| 42 |
+
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
| 43 |
+
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 44 |
+
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 45 |
+
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
| 46 |
+
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 47 |
+
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 48 |
+
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 49 |
+
"model.layers.1.layer_scalar": "model.safetensors",
|
| 50 |
+
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
| 51 |
+
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
| 52 |
+
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 53 |
+
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
| 54 |
+
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
| 55 |
+
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 56 |
+
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
| 57 |
+
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
| 58 |
+
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 59 |
+
"model.layers.1.per_layer_input_gate.biases": "model.safetensors",
|
| 60 |
+
"model.layers.1.per_layer_input_gate.scales": "model.safetensors",
|
| 61 |
+
"model.layers.1.per_layer_input_gate.weight": "model.safetensors",
|
| 62 |
+
"model.layers.1.per_layer_projection.biases": "model.safetensors",
|
| 63 |
+
"model.layers.1.per_layer_projection.scales": "model.safetensors",
|
| 64 |
+
"model.layers.1.per_layer_projection.weight": "model.safetensors",
|
| 65 |
+
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 66 |
+
"model.layers.1.post_feedforward_layernorm.weight": "model.safetensors",
|
| 67 |
+
"model.layers.1.post_per_layer_input_norm.weight": "model.safetensors",
|
| 68 |
+
"model.layers.1.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 69 |
+
"model.layers.1.self_attn.k_norm.weight": "model.safetensors",
|
| 70 |
+
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
| 71 |
+
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 72 |
+
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 73 |
+
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
| 74 |
+
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
| 75 |
+
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
| 76 |
+
"model.layers.1.self_attn.q_norm.weight": "model.safetensors",
|
| 77 |
+
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
| 78 |
+
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 79 |
+
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 80 |
+
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
| 81 |
+
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 82 |
+
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 83 |
+
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 84 |
+
"model.layers.10.layer_scalar": "model.safetensors",
|
| 85 |
+
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
| 86 |
+
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
| 87 |
+
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 88 |
+
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
| 89 |
+
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
| 90 |
+
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 91 |
+
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
| 92 |
+
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
| 93 |
+
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 94 |
+
"model.layers.10.per_layer_input_gate.biases": "model.safetensors",
|
| 95 |
+
"model.layers.10.per_layer_input_gate.scales": "model.safetensors",
|
| 96 |
+
"model.layers.10.per_layer_input_gate.weight": "model.safetensors",
|
| 97 |
+
"model.layers.10.per_layer_projection.biases": "model.safetensors",
|
| 98 |
+
"model.layers.10.per_layer_projection.scales": "model.safetensors",
|
| 99 |
+
"model.layers.10.per_layer_projection.weight": "model.safetensors",
|
| 100 |
+
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 101 |
+
"model.layers.10.post_feedforward_layernorm.weight": "model.safetensors",
|
| 102 |
+
"model.layers.10.post_per_layer_input_norm.weight": "model.safetensors",
|
| 103 |
+
"model.layers.10.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 104 |
+
"model.layers.10.self_attn.k_norm.weight": "model.safetensors",
|
| 105 |
+
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 106 |
+
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 107 |
+
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 108 |
+
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
| 109 |
+
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
| 110 |
+
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
| 111 |
+
"model.layers.10.self_attn.q_norm.weight": "model.safetensors",
|
| 112 |
+
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 113 |
+
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 114 |
+
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 115 |
+
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 116 |
+
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 117 |
+
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 118 |
+
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 119 |
+
"model.layers.11.layer_scalar": "model.safetensors",
|
| 120 |
+
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
| 121 |
+
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
| 122 |
+
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 123 |
+
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
| 124 |
+
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
| 125 |
+
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 126 |
+
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
| 127 |
+
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
| 128 |
+
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 129 |
+
"model.layers.11.per_layer_input_gate.biases": "model.safetensors",
|
| 130 |
+
"model.layers.11.per_layer_input_gate.scales": "model.safetensors",
|
| 131 |
+
"model.layers.11.per_layer_input_gate.weight": "model.safetensors",
|
| 132 |
+
"model.layers.11.per_layer_projection.biases": "model.safetensors",
|
| 133 |
+
"model.layers.11.per_layer_projection.scales": "model.safetensors",
|
| 134 |
+
"model.layers.11.per_layer_projection.weight": "model.safetensors",
|
| 135 |
+
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 136 |
+
"model.layers.11.post_feedforward_layernorm.weight": "model.safetensors",
|
| 137 |
+
"model.layers.11.post_per_layer_input_norm.weight": "model.safetensors",
|
| 138 |
+
"model.layers.11.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 139 |
+
"model.layers.11.self_attn.k_norm.weight": "model.safetensors",
|
| 140 |
+
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
| 141 |
+
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 142 |
+
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 143 |
+
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
| 144 |
+
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
| 145 |
+
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 146 |
+
"model.layers.11.self_attn.q_norm.weight": "model.safetensors",
|
| 147 |
+
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
| 148 |
+
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 149 |
+
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 150 |
+
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
| 151 |
+
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 152 |
+
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 153 |
+
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 154 |
+
"model.layers.12.layer_scalar": "model.safetensors",
|
| 155 |
+
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
| 156 |
+
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
| 157 |
+
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 158 |
+
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
| 159 |
+
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
| 160 |
+
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 161 |
+
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
| 162 |
+
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
| 163 |
+
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 164 |
+
"model.layers.12.per_layer_input_gate.biases": "model.safetensors",
|
| 165 |
+
"model.layers.12.per_layer_input_gate.scales": "model.safetensors",
|
| 166 |
+
"model.layers.12.per_layer_input_gate.weight": "model.safetensors",
|
| 167 |
+
"model.layers.12.per_layer_projection.biases": "model.safetensors",
|
| 168 |
+
"model.layers.12.per_layer_projection.scales": "model.safetensors",
|
| 169 |
+
"model.layers.12.per_layer_projection.weight": "model.safetensors",
|
| 170 |
+
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 171 |
+
"model.layers.12.post_feedforward_layernorm.weight": "model.safetensors",
|
| 172 |
+
"model.layers.12.post_per_layer_input_norm.weight": "model.safetensors",
|
| 173 |
+
"model.layers.12.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 174 |
+
"model.layers.12.self_attn.k_norm.weight": "model.safetensors",
|
| 175 |
+
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 176 |
+
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 177 |
+
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 178 |
+
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
| 179 |
+
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
| 180 |
+
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
| 181 |
+
"model.layers.12.self_attn.q_norm.weight": "model.safetensors",
|
| 182 |
+
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 183 |
+
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 184 |
+
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 185 |
+
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 186 |
+
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 187 |
+
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 188 |
+
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 189 |
+
"model.layers.13.layer_scalar": "model.safetensors",
|
| 190 |
+
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
| 191 |
+
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
| 192 |
+
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 193 |
+
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
| 194 |
+
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
| 195 |
+
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 196 |
+
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
| 197 |
+
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
| 198 |
+
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 199 |
+
"model.layers.13.per_layer_input_gate.biases": "model.safetensors",
|
| 200 |
+
"model.layers.13.per_layer_input_gate.scales": "model.safetensors",
|
| 201 |
+
"model.layers.13.per_layer_input_gate.weight": "model.safetensors",
|
| 202 |
+
"model.layers.13.per_layer_projection.biases": "model.safetensors",
|
| 203 |
+
"model.layers.13.per_layer_projection.scales": "model.safetensors",
|
| 204 |
+
"model.layers.13.per_layer_projection.weight": "model.safetensors",
|
| 205 |
+
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 206 |
+
"model.layers.13.post_feedforward_layernorm.weight": "model.safetensors",
|
| 207 |
+
"model.layers.13.post_per_layer_input_norm.weight": "model.safetensors",
|
| 208 |
+
"model.layers.13.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 209 |
+
"model.layers.13.self_attn.k_norm.weight": "model.safetensors",
|
| 210 |
+
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
| 211 |
+
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 212 |
+
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 213 |
+
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
| 214 |
+
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
| 215 |
+
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
| 216 |
+
"model.layers.13.self_attn.q_norm.weight": "model.safetensors",
|
| 217 |
+
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
| 218 |
+
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 219 |
+
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 220 |
+
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
| 221 |
+
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 222 |
+
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 223 |
+
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 224 |
+
"model.layers.14.layer_scalar": "model.safetensors",
|
| 225 |
+
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
| 226 |
+
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
| 227 |
+
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 228 |
+
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
| 229 |
+
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
| 230 |
+
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 231 |
+
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
| 232 |
+
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
| 233 |
+
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 234 |
+
"model.layers.14.per_layer_input_gate.biases": "model.safetensors",
|
| 235 |
+
"model.layers.14.per_layer_input_gate.scales": "model.safetensors",
|
| 236 |
+
"model.layers.14.per_layer_input_gate.weight": "model.safetensors",
|
| 237 |
+
"model.layers.14.per_layer_projection.biases": "model.safetensors",
|
| 238 |
+
"model.layers.14.per_layer_projection.scales": "model.safetensors",
|
| 239 |
+
"model.layers.14.per_layer_projection.weight": "model.safetensors",
|
| 240 |
+
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 241 |
+
"model.layers.14.post_feedforward_layernorm.weight": "model.safetensors",
|
| 242 |
+
"model.layers.14.post_per_layer_input_norm.weight": "model.safetensors",
|
| 243 |
+
"model.layers.14.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 244 |
+
"model.layers.14.self_attn.k_norm.weight": "model.safetensors",
|
| 245 |
+
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 246 |
+
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 247 |
+
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 248 |
+
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
| 249 |
+
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
| 250 |
+
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
| 251 |
+
"model.layers.14.self_attn.q_norm.weight": "model.safetensors",
|
| 252 |
+
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 253 |
+
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 254 |
+
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 255 |
+
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 256 |
+
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 257 |
+
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 258 |
+
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 259 |
+
"model.layers.15.layer_scalar": "model.safetensors",
|
| 260 |
+
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
| 261 |
+
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
| 262 |
+
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 263 |
+
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
| 264 |
+
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
| 265 |
+
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 266 |
+
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
| 267 |
+
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
| 268 |
+
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 269 |
+
"model.layers.15.per_layer_input_gate.biases": "model.safetensors",
|
| 270 |
+
"model.layers.15.per_layer_input_gate.scales": "model.safetensors",
|
| 271 |
+
"model.layers.15.per_layer_input_gate.weight": "model.safetensors",
|
| 272 |
+
"model.layers.15.per_layer_projection.biases": "model.safetensors",
|
| 273 |
+
"model.layers.15.per_layer_projection.scales": "model.safetensors",
|
| 274 |
+
"model.layers.15.per_layer_projection.weight": "model.safetensors",
|
| 275 |
+
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 276 |
+
"model.layers.15.post_feedforward_layernorm.weight": "model.safetensors",
|
| 277 |
+
"model.layers.15.post_per_layer_input_norm.weight": "model.safetensors",
|
| 278 |
+
"model.layers.15.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 279 |
+
"model.layers.15.self_attn.k_norm.weight": "model.safetensors",
|
| 280 |
+
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
| 281 |
+
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 282 |
+
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 283 |
+
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
| 284 |
+
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
| 285 |
+
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 286 |
+
"model.layers.15.self_attn.q_norm.weight": "model.safetensors",
|
| 287 |
+
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
| 288 |
+
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 289 |
+
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 290 |
+
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
| 291 |
+
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 292 |
+
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 293 |
+
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 294 |
+
"model.layers.16.layer_scalar": "model.safetensors",
|
| 295 |
+
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
| 296 |
+
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
| 297 |
+
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 298 |
+
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
| 299 |
+
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
| 300 |
+
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 301 |
+
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
| 302 |
+
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
| 303 |
+
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 304 |
+
"model.layers.16.per_layer_input_gate.biases": "model.safetensors",
|
| 305 |
+
"model.layers.16.per_layer_input_gate.scales": "model.safetensors",
|
| 306 |
+
"model.layers.16.per_layer_input_gate.weight": "model.safetensors",
|
| 307 |
+
"model.layers.16.per_layer_projection.biases": "model.safetensors",
|
| 308 |
+
"model.layers.16.per_layer_projection.scales": "model.safetensors",
|
| 309 |
+
"model.layers.16.per_layer_projection.weight": "model.safetensors",
|
| 310 |
+
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 311 |
+
"model.layers.16.post_feedforward_layernorm.weight": "model.safetensors",
|
| 312 |
+
"model.layers.16.post_per_layer_input_norm.weight": "model.safetensors",
|
| 313 |
+
"model.layers.16.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 314 |
+
"model.layers.16.self_attn.k_norm.weight": "model.safetensors",
|
| 315 |
+
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
| 316 |
+
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 317 |
+
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 318 |
+
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
| 319 |
+
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
| 320 |
+
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
| 321 |
+
"model.layers.16.self_attn.q_norm.weight": "model.safetensors",
|
| 322 |
+
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
| 323 |
+
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 324 |
+
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 325 |
+
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
| 326 |
+
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 327 |
+
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 328 |
+
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 329 |
+
"model.layers.17.layer_scalar": "model.safetensors",
|
| 330 |
+
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
| 331 |
+
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
| 332 |
+
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 333 |
+
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
| 334 |
+
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
| 335 |
+
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 336 |
+
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
| 337 |
+
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
| 338 |
+
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 339 |
+
"model.layers.17.per_layer_input_gate.biases": "model.safetensors",
|
| 340 |
+
"model.layers.17.per_layer_input_gate.scales": "model.safetensors",
|
| 341 |
+
"model.layers.17.per_layer_input_gate.weight": "model.safetensors",
|
| 342 |
+
"model.layers.17.per_layer_projection.biases": "model.safetensors",
|
| 343 |
+
"model.layers.17.per_layer_projection.scales": "model.safetensors",
|
| 344 |
+
"model.layers.17.per_layer_projection.weight": "model.safetensors",
|
| 345 |
+
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 346 |
+
"model.layers.17.post_feedforward_layernorm.weight": "model.safetensors",
|
| 347 |
+
"model.layers.17.post_per_layer_input_norm.weight": "model.safetensors",
|
| 348 |
+
"model.layers.17.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 349 |
+
"model.layers.17.self_attn.k_norm.weight": "model.safetensors",
|
| 350 |
+
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
| 351 |
+
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 352 |
+
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 353 |
+
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
| 354 |
+
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
| 355 |
+
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
| 356 |
+
"model.layers.17.self_attn.q_norm.weight": "model.safetensors",
|
| 357 |
+
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
| 358 |
+
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 359 |
+
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 360 |
+
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
| 361 |
+
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 362 |
+
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 363 |
+
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 364 |
+
"model.layers.18.layer_scalar": "model.safetensors",
|
| 365 |
+
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
| 366 |
+
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
| 367 |
+
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 368 |
+
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
| 369 |
+
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
| 370 |
+
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 371 |
+
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
| 372 |
+
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
| 373 |
+
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 374 |
+
"model.layers.18.per_layer_input_gate.biases": "model.safetensors",
|
| 375 |
+
"model.layers.18.per_layer_input_gate.scales": "model.safetensors",
|
| 376 |
+
"model.layers.18.per_layer_input_gate.weight": "model.safetensors",
|
| 377 |
+
"model.layers.18.per_layer_projection.biases": "model.safetensors",
|
| 378 |
+
"model.layers.18.per_layer_projection.scales": "model.safetensors",
|
| 379 |
+
"model.layers.18.per_layer_projection.weight": "model.safetensors",
|
| 380 |
+
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 381 |
+
"model.layers.18.post_feedforward_layernorm.weight": "model.safetensors",
|
| 382 |
+
"model.layers.18.post_per_layer_input_norm.weight": "model.safetensors",
|
| 383 |
+
"model.layers.18.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 384 |
+
"model.layers.18.self_attn.k_norm.weight": "model.safetensors",
|
| 385 |
+
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
| 386 |
+
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 387 |
+
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 388 |
+
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
| 389 |
+
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
| 390 |
+
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
| 391 |
+
"model.layers.18.self_attn.q_norm.weight": "model.safetensors",
|
| 392 |
+
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
| 393 |
+
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 394 |
+
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 395 |
+
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
| 396 |
+
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 397 |
+
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 398 |
+
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 399 |
+
"model.layers.19.layer_scalar": "model.safetensors",
|
| 400 |
+
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
| 401 |
+
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
| 402 |
+
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 403 |
+
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
| 404 |
+
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
| 405 |
+
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 406 |
+
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
| 407 |
+
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
| 408 |
+
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 409 |
+
"model.layers.19.per_layer_input_gate.biases": "model.safetensors",
|
| 410 |
+
"model.layers.19.per_layer_input_gate.scales": "model.safetensors",
|
| 411 |
+
"model.layers.19.per_layer_input_gate.weight": "model.safetensors",
|
| 412 |
+
"model.layers.19.per_layer_projection.biases": "model.safetensors",
|
| 413 |
+
"model.layers.19.per_layer_projection.scales": "model.safetensors",
|
| 414 |
+
"model.layers.19.per_layer_projection.weight": "model.safetensors",
|
| 415 |
+
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 416 |
+
"model.layers.19.post_feedforward_layernorm.weight": "model.safetensors",
|
| 417 |
+
"model.layers.19.post_per_layer_input_norm.weight": "model.safetensors",
|
| 418 |
+
"model.layers.19.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 419 |
+
"model.layers.19.self_attn.k_norm.weight": "model.safetensors",
|
| 420 |
+
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
| 421 |
+
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 422 |
+
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 423 |
+
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
| 424 |
+
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
| 425 |
+
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 426 |
+
"model.layers.19.self_attn.q_norm.weight": "model.safetensors",
|
| 427 |
+
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
| 428 |
+
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 429 |
+
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 430 |
+
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
| 431 |
+
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 432 |
+
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 433 |
+
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 434 |
+
"model.layers.2.layer_scalar": "model.safetensors",
|
| 435 |
+
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
| 436 |
+
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
| 437 |
+
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 438 |
+
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
| 439 |
+
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
| 440 |
+
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 441 |
+
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
| 442 |
+
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
| 443 |
+
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 444 |
+
"model.layers.2.per_layer_input_gate.biases": "model.safetensors",
|
| 445 |
+
"model.layers.2.per_layer_input_gate.scales": "model.safetensors",
|
| 446 |
+
"model.layers.2.per_layer_input_gate.weight": "model.safetensors",
|
| 447 |
+
"model.layers.2.per_layer_projection.biases": "model.safetensors",
|
| 448 |
+
"model.layers.2.per_layer_projection.scales": "model.safetensors",
|
| 449 |
+
"model.layers.2.per_layer_projection.weight": "model.safetensors",
|
| 450 |
+
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 451 |
+
"model.layers.2.post_feedforward_layernorm.weight": "model.safetensors",
|
| 452 |
+
"model.layers.2.post_per_layer_input_norm.weight": "model.safetensors",
|
| 453 |
+
"model.layers.2.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 454 |
+
"model.layers.2.self_attn.k_norm.weight": "model.safetensors",
|
| 455 |
+
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 456 |
+
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 457 |
+
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 458 |
+
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
| 459 |
+
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 460 |
+
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 461 |
+
"model.layers.2.self_attn.q_norm.weight": "model.safetensors",
|
| 462 |
+
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 463 |
+
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 464 |
+
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 465 |
+
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 466 |
+
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 467 |
+
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 468 |
+
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 469 |
+
"model.layers.20.layer_scalar": "model.safetensors",
|
| 470 |
+
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
| 471 |
+
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 472 |
+
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 473 |
+
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
| 474 |
+
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 475 |
+
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 476 |
+
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
| 477 |
+
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 478 |
+
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 479 |
+
"model.layers.20.per_layer_input_gate.biases": "model.safetensors",
|
| 480 |
+
"model.layers.20.per_layer_input_gate.scales": "model.safetensors",
|
| 481 |
+
"model.layers.20.per_layer_input_gate.weight": "model.safetensors",
|
| 482 |
+
"model.layers.20.per_layer_projection.biases": "model.safetensors",
|
| 483 |
+
"model.layers.20.per_layer_projection.scales": "model.safetensors",
|
| 484 |
+
"model.layers.20.per_layer_projection.weight": "model.safetensors",
|
| 485 |
+
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 486 |
+
"model.layers.20.post_feedforward_layernorm.weight": "model.safetensors",
|
| 487 |
+
"model.layers.20.post_per_layer_input_norm.weight": "model.safetensors",
|
| 488 |
+
"model.layers.20.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 489 |
+
"model.layers.20.self_attn.k_norm.weight": "model.safetensors",
|
| 490 |
+
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 491 |
+
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 492 |
+
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 493 |
+
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
| 494 |
+
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 495 |
+
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 496 |
+
"model.layers.20.self_attn.q_norm.weight": "model.safetensors",
|
| 497 |
+
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 498 |
+
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 499 |
+
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 500 |
+
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 501 |
+
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 502 |
+
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 503 |
+
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 504 |
+
"model.layers.21.layer_scalar": "model.safetensors",
|
| 505 |
+
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
| 506 |
+
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 507 |
+
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 508 |
+
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
| 509 |
+
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 510 |
+
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 511 |
+
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
| 512 |
+
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 513 |
+
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 514 |
+
"model.layers.21.per_layer_input_gate.biases": "model.safetensors",
|
| 515 |
+
"model.layers.21.per_layer_input_gate.scales": "model.safetensors",
|
| 516 |
+
"model.layers.21.per_layer_input_gate.weight": "model.safetensors",
|
| 517 |
+
"model.layers.21.per_layer_projection.biases": "model.safetensors",
|
| 518 |
+
"model.layers.21.per_layer_projection.scales": "model.safetensors",
|
| 519 |
+
"model.layers.21.per_layer_projection.weight": "model.safetensors",
|
| 520 |
+
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 521 |
+
"model.layers.21.post_feedforward_layernorm.weight": "model.safetensors",
|
| 522 |
+
"model.layers.21.post_per_layer_input_norm.weight": "model.safetensors",
|
| 523 |
+
"model.layers.21.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 524 |
+
"model.layers.21.self_attn.k_norm.weight": "model.safetensors",
|
| 525 |
+
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 526 |
+
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 527 |
+
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 528 |
+
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
| 529 |
+
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 530 |
+
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 531 |
+
"model.layers.21.self_attn.q_norm.weight": "model.safetensors",
|
| 532 |
+
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 533 |
+
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 534 |
+
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 535 |
+
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 536 |
+
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 537 |
+
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 538 |
+
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 539 |
+
"model.layers.22.layer_scalar": "model.safetensors",
|
| 540 |
+
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
| 541 |
+
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 542 |
+
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 543 |
+
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
| 544 |
+
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 545 |
+
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 546 |
+
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
| 547 |
+
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 548 |
+
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 549 |
+
"model.layers.22.per_layer_input_gate.biases": "model.safetensors",
|
| 550 |
+
"model.layers.22.per_layer_input_gate.scales": "model.safetensors",
|
| 551 |
+
"model.layers.22.per_layer_input_gate.weight": "model.safetensors",
|
| 552 |
+
"model.layers.22.per_layer_projection.biases": "model.safetensors",
|
| 553 |
+
"model.layers.22.per_layer_projection.scales": "model.safetensors",
|
| 554 |
+
"model.layers.22.per_layer_projection.weight": "model.safetensors",
|
| 555 |
+
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 556 |
+
"model.layers.22.post_feedforward_layernorm.weight": "model.safetensors",
|
| 557 |
+
"model.layers.22.post_per_layer_input_norm.weight": "model.safetensors",
|
| 558 |
+
"model.layers.22.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 559 |
+
"model.layers.22.self_attn.k_norm.weight": "model.safetensors",
|
| 560 |
+
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 561 |
+
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 562 |
+
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 563 |
+
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
| 564 |
+
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 565 |
+
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 566 |
+
"model.layers.22.self_attn.q_norm.weight": "model.safetensors",
|
| 567 |
+
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 568 |
+
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 569 |
+
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 570 |
+
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 571 |
+
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 572 |
+
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 573 |
+
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 574 |
+
"model.layers.23.layer_scalar": "model.safetensors",
|
| 575 |
+
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
| 576 |
+
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 577 |
+
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 578 |
+
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
| 579 |
+
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 580 |
+
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 581 |
+
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
| 582 |
+
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 583 |
+
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 584 |
+
"model.layers.23.per_layer_input_gate.biases": "model.safetensors",
|
| 585 |
+
"model.layers.23.per_layer_input_gate.scales": "model.safetensors",
|
| 586 |
+
"model.layers.23.per_layer_input_gate.weight": "model.safetensors",
|
| 587 |
+
"model.layers.23.per_layer_projection.biases": "model.safetensors",
|
| 588 |
+
"model.layers.23.per_layer_projection.scales": "model.safetensors",
|
| 589 |
+
"model.layers.23.per_layer_projection.weight": "model.safetensors",
|
| 590 |
+
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 591 |
+
"model.layers.23.post_feedforward_layernorm.weight": "model.safetensors",
|
| 592 |
+
"model.layers.23.post_per_layer_input_norm.weight": "model.safetensors",
|
| 593 |
+
"model.layers.23.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 594 |
+
"model.layers.23.self_attn.k_norm.weight": "model.safetensors",
|
| 595 |
+
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 596 |
+
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 597 |
+
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 598 |
+
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
| 599 |
+
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 600 |
+
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 601 |
+
"model.layers.23.self_attn.q_norm.weight": "model.safetensors",
|
| 602 |
+
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 603 |
+
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 604 |
+
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 605 |
+
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 606 |
+
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 607 |
+
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 608 |
+
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 609 |
+
"model.layers.24.layer_scalar": "model.safetensors",
|
| 610 |
+
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
| 611 |
+
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 612 |
+
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 613 |
+
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
| 614 |
+
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 615 |
+
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 616 |
+
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
| 617 |
+
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 618 |
+
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 619 |
+
"model.layers.24.per_layer_input_gate.biases": "model.safetensors",
|
| 620 |
+
"model.layers.24.per_layer_input_gate.scales": "model.safetensors",
|
| 621 |
+
"model.layers.24.per_layer_input_gate.weight": "model.safetensors",
|
| 622 |
+
"model.layers.24.per_layer_projection.biases": "model.safetensors",
|
| 623 |
+
"model.layers.24.per_layer_projection.scales": "model.safetensors",
|
| 624 |
+
"model.layers.24.per_layer_projection.weight": "model.safetensors",
|
| 625 |
+
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 626 |
+
"model.layers.24.post_feedforward_layernorm.weight": "model.safetensors",
|
| 627 |
+
"model.layers.24.post_per_layer_input_norm.weight": "model.safetensors",
|
| 628 |
+
"model.layers.24.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 629 |
+
"model.layers.24.self_attn.k_norm.weight": "model.safetensors",
|
| 630 |
+
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 631 |
+
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 632 |
+
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 633 |
+
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
| 634 |
+
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 635 |
+
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 636 |
+
"model.layers.24.self_attn.q_norm.weight": "model.safetensors",
|
| 637 |
+
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 638 |
+
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 639 |
+
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 640 |
+
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 641 |
+
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 642 |
+
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 643 |
+
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 644 |
+
"model.layers.25.layer_scalar": "model.safetensors",
|
| 645 |
+
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
| 646 |
+
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 647 |
+
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 648 |
+
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
| 649 |
+
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 650 |
+
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 651 |
+
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
| 652 |
+
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 653 |
+
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 654 |
+
"model.layers.25.per_layer_input_gate.biases": "model.safetensors",
|
| 655 |
+
"model.layers.25.per_layer_input_gate.scales": "model.safetensors",
|
| 656 |
+
"model.layers.25.per_layer_input_gate.weight": "model.safetensors",
|
| 657 |
+
"model.layers.25.per_layer_projection.biases": "model.safetensors",
|
| 658 |
+
"model.layers.25.per_layer_projection.scales": "model.safetensors",
|
| 659 |
+
"model.layers.25.per_layer_projection.weight": "model.safetensors",
|
| 660 |
+
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 661 |
+
"model.layers.25.post_feedforward_layernorm.weight": "model.safetensors",
|
| 662 |
+
"model.layers.25.post_per_layer_input_norm.weight": "model.safetensors",
|
| 663 |
+
"model.layers.25.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 664 |
+
"model.layers.25.self_attn.k_norm.weight": "model.safetensors",
|
| 665 |
+
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 666 |
+
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 667 |
+
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 668 |
+
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
| 669 |
+
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 670 |
+
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 671 |
+
"model.layers.25.self_attn.q_norm.weight": "model.safetensors",
|
| 672 |
+
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 673 |
+
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 674 |
+
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 675 |
+
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 676 |
+
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 677 |
+
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 678 |
+
"model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 679 |
+
"model.layers.26.layer_scalar": "model.safetensors",
|
| 680 |
+
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
| 681 |
+
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
| 682 |
+
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 683 |
+
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
| 684 |
+
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
| 685 |
+
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 686 |
+
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
| 687 |
+
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
| 688 |
+
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 689 |
+
"model.layers.26.per_layer_input_gate.biases": "model.safetensors",
|
| 690 |
+
"model.layers.26.per_layer_input_gate.scales": "model.safetensors",
|
| 691 |
+
"model.layers.26.per_layer_input_gate.weight": "model.safetensors",
|
| 692 |
+
"model.layers.26.per_layer_projection.biases": "model.safetensors",
|
| 693 |
+
"model.layers.26.per_layer_projection.scales": "model.safetensors",
|
| 694 |
+
"model.layers.26.per_layer_projection.weight": "model.safetensors",
|
| 695 |
+
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 696 |
+
"model.layers.26.post_feedforward_layernorm.weight": "model.safetensors",
|
| 697 |
+
"model.layers.26.post_per_layer_input_norm.weight": "model.safetensors",
|
| 698 |
+
"model.layers.26.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 699 |
+
"model.layers.26.self_attn.k_norm.weight": "model.safetensors",
|
| 700 |
+
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
| 701 |
+
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
| 702 |
+
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
| 703 |
+
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
| 704 |
+
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
| 705 |
+
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
| 706 |
+
"model.layers.26.self_attn.q_norm.weight": "model.safetensors",
|
| 707 |
+
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
| 708 |
+
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
| 709 |
+
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
| 710 |
+
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
| 711 |
+
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
| 712 |
+
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
| 713 |
+
"model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 714 |
+
"model.layers.27.layer_scalar": "model.safetensors",
|
| 715 |
+
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
| 716 |
+
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
| 717 |
+
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 718 |
+
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
| 719 |
+
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
| 720 |
+
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 721 |
+
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
| 722 |
+
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
| 723 |
+
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 724 |
+
"model.layers.27.per_layer_input_gate.biases": "model.safetensors",
|
| 725 |
+
"model.layers.27.per_layer_input_gate.scales": "model.safetensors",
|
| 726 |
+
"model.layers.27.per_layer_input_gate.weight": "model.safetensors",
|
| 727 |
+
"model.layers.27.per_layer_projection.biases": "model.safetensors",
|
| 728 |
+
"model.layers.27.per_layer_projection.scales": "model.safetensors",
|
| 729 |
+
"model.layers.27.per_layer_projection.weight": "model.safetensors",
|
| 730 |
+
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 731 |
+
"model.layers.27.post_feedforward_layernorm.weight": "model.safetensors",
|
| 732 |
+
"model.layers.27.post_per_layer_input_norm.weight": "model.safetensors",
|
| 733 |
+
"model.layers.27.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 734 |
+
"model.layers.27.self_attn.k_norm.weight": "model.safetensors",
|
| 735 |
+
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
| 736 |
+
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
| 737 |
+
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 738 |
+
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
| 739 |
+
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
| 740 |
+
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 741 |
+
"model.layers.27.self_attn.q_norm.weight": "model.safetensors",
|
| 742 |
+
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
| 743 |
+
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
| 744 |
+
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 745 |
+
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
| 746 |
+
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
| 747 |
+
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 748 |
+
"model.layers.28.input_layernorm.weight": "model.safetensors",
|
| 749 |
+
"model.layers.28.layer_scalar": "model.safetensors",
|
| 750 |
+
"model.layers.28.mlp.down_proj.biases": "model.safetensors",
|
| 751 |
+
"model.layers.28.mlp.down_proj.scales": "model.safetensors",
|
| 752 |
+
"model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
| 753 |
+
"model.layers.28.mlp.gate_proj.biases": "model.safetensors",
|
| 754 |
+
"model.layers.28.mlp.gate_proj.scales": "model.safetensors",
|
| 755 |
+
"model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
| 756 |
+
"model.layers.28.mlp.up_proj.biases": "model.safetensors",
|
| 757 |
+
"model.layers.28.mlp.up_proj.scales": "model.safetensors",
|
| 758 |
+
"model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
| 759 |
+
"model.layers.28.per_layer_input_gate.biases": "model.safetensors",
|
| 760 |
+
"model.layers.28.per_layer_input_gate.scales": "model.safetensors",
|
| 761 |
+
"model.layers.28.per_layer_input_gate.weight": "model.safetensors",
|
| 762 |
+
"model.layers.28.per_layer_projection.biases": "model.safetensors",
|
| 763 |
+
"model.layers.28.per_layer_projection.scales": "model.safetensors",
|
| 764 |
+
"model.layers.28.per_layer_projection.weight": "model.safetensors",
|
| 765 |
+
"model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
| 766 |
+
"model.layers.28.post_feedforward_layernorm.weight": "model.safetensors",
|
| 767 |
+
"model.layers.28.post_per_layer_input_norm.weight": "model.safetensors",
|
| 768 |
+
"model.layers.28.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 769 |
+
"model.layers.28.self_attn.k_norm.weight": "model.safetensors",
|
| 770 |
+
"model.layers.28.self_attn.k_proj.biases": "model.safetensors",
|
| 771 |
+
"model.layers.28.self_attn.k_proj.scales": "model.safetensors",
|
| 772 |
+
"model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
| 773 |
+
"model.layers.28.self_attn.o_proj.biases": "model.safetensors",
|
| 774 |
+
"model.layers.28.self_attn.o_proj.scales": "model.safetensors",
|
| 775 |
+
"model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
| 776 |
+
"model.layers.28.self_attn.q_norm.weight": "model.safetensors",
|
| 777 |
+
"model.layers.28.self_attn.q_proj.biases": "model.safetensors",
|
| 778 |
+
"model.layers.28.self_attn.q_proj.scales": "model.safetensors",
|
| 779 |
+
"model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
| 780 |
+
"model.layers.28.self_attn.v_proj.biases": "model.safetensors",
|
| 781 |
+
"model.layers.28.self_attn.v_proj.scales": "model.safetensors",
|
| 782 |
+
"model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
| 783 |
+
"model.layers.29.input_layernorm.weight": "model.safetensors",
|
| 784 |
+
"model.layers.29.layer_scalar": "model.safetensors",
|
| 785 |
+
"model.layers.29.mlp.down_proj.biases": "model.safetensors",
|
| 786 |
+
"model.layers.29.mlp.down_proj.scales": "model.safetensors",
|
| 787 |
+
"model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
| 788 |
+
"model.layers.29.mlp.gate_proj.biases": "model.safetensors",
|
| 789 |
+
"model.layers.29.mlp.gate_proj.scales": "model.safetensors",
|
| 790 |
+
"model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
| 791 |
+
"model.layers.29.mlp.up_proj.biases": "model.safetensors",
|
| 792 |
+
"model.layers.29.mlp.up_proj.scales": "model.safetensors",
|
| 793 |
+
"model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
| 794 |
+
"model.layers.29.per_layer_input_gate.biases": "model.safetensors",
|
| 795 |
+
"model.layers.29.per_layer_input_gate.scales": "model.safetensors",
|
| 796 |
+
"model.layers.29.per_layer_input_gate.weight": "model.safetensors",
|
| 797 |
+
"model.layers.29.per_layer_projection.biases": "model.safetensors",
|
| 798 |
+
"model.layers.29.per_layer_projection.scales": "model.safetensors",
|
| 799 |
+
"model.layers.29.per_layer_projection.weight": "model.safetensors",
|
| 800 |
+
"model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
| 801 |
+
"model.layers.29.post_feedforward_layernorm.weight": "model.safetensors",
|
| 802 |
+
"model.layers.29.post_per_layer_input_norm.weight": "model.safetensors",
|
| 803 |
+
"model.layers.29.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 804 |
+
"model.layers.29.self_attn.k_norm.weight": "model.safetensors",
|
| 805 |
+
"model.layers.29.self_attn.k_proj.biases": "model.safetensors",
|
| 806 |
+
"model.layers.29.self_attn.k_proj.scales": "model.safetensors",
|
| 807 |
+
"model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
| 808 |
+
"model.layers.29.self_attn.o_proj.biases": "model.safetensors",
|
| 809 |
+
"model.layers.29.self_attn.o_proj.scales": "model.safetensors",
|
| 810 |
+
"model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
| 811 |
+
"model.layers.29.self_attn.q_norm.weight": "model.safetensors",
|
| 812 |
+
"model.layers.29.self_attn.q_proj.biases": "model.safetensors",
|
| 813 |
+
"model.layers.29.self_attn.q_proj.scales": "model.safetensors",
|
| 814 |
+
"model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
| 815 |
+
"model.layers.29.self_attn.v_proj.biases": "model.safetensors",
|
| 816 |
+
"model.layers.29.self_attn.v_proj.scales": "model.safetensors",
|
| 817 |
+
"model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
| 818 |
+
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 819 |
+
"model.layers.3.layer_scalar": "model.safetensors",
|
| 820 |
+
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
| 821 |
+
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 822 |
+
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 823 |
+
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
| 824 |
+
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 825 |
+
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 826 |
+
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
| 827 |
+
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 828 |
+
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 829 |
+
"model.layers.3.per_layer_input_gate.biases": "model.safetensors",
|
| 830 |
+
"model.layers.3.per_layer_input_gate.scales": "model.safetensors",
|
| 831 |
+
"model.layers.3.per_layer_input_gate.weight": "model.safetensors",
|
| 832 |
+
"model.layers.3.per_layer_projection.biases": "model.safetensors",
|
| 833 |
+
"model.layers.3.per_layer_projection.scales": "model.safetensors",
|
| 834 |
+
"model.layers.3.per_layer_projection.weight": "model.safetensors",
|
| 835 |
+
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 836 |
+
"model.layers.3.post_feedforward_layernorm.weight": "model.safetensors",
|
| 837 |
+
"model.layers.3.post_per_layer_input_norm.weight": "model.safetensors",
|
| 838 |
+
"model.layers.3.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 839 |
+
"model.layers.3.self_attn.k_norm.weight": "model.safetensors",
|
| 840 |
+
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 841 |
+
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 842 |
+
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 843 |
+
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
| 844 |
+
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 845 |
+
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 846 |
+
"model.layers.3.self_attn.q_norm.weight": "model.safetensors",
|
| 847 |
+
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 848 |
+
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 849 |
+
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 850 |
+
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 851 |
+
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 852 |
+
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 853 |
+
"model.layers.30.input_layernorm.weight": "model.safetensors",
|
| 854 |
+
"model.layers.30.layer_scalar": "model.safetensors",
|
| 855 |
+
"model.layers.30.mlp.down_proj.biases": "model.safetensors",
|
| 856 |
+
"model.layers.30.mlp.down_proj.scales": "model.safetensors",
|
| 857 |
+
"model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
| 858 |
+
"model.layers.30.mlp.gate_proj.biases": "model.safetensors",
|
| 859 |
+
"model.layers.30.mlp.gate_proj.scales": "model.safetensors",
|
| 860 |
+
"model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
| 861 |
+
"model.layers.30.mlp.up_proj.biases": "model.safetensors",
|
| 862 |
+
"model.layers.30.mlp.up_proj.scales": "model.safetensors",
|
| 863 |
+
"model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
| 864 |
+
"model.layers.30.per_layer_input_gate.biases": "model.safetensors",
|
| 865 |
+
"model.layers.30.per_layer_input_gate.scales": "model.safetensors",
|
| 866 |
+
"model.layers.30.per_layer_input_gate.weight": "model.safetensors",
|
| 867 |
+
"model.layers.30.per_layer_projection.biases": "model.safetensors",
|
| 868 |
+
"model.layers.30.per_layer_projection.scales": "model.safetensors",
|
| 869 |
+
"model.layers.30.per_layer_projection.weight": "model.safetensors",
|
| 870 |
+
"model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
| 871 |
+
"model.layers.30.post_feedforward_layernorm.weight": "model.safetensors",
|
| 872 |
+
"model.layers.30.post_per_layer_input_norm.weight": "model.safetensors",
|
| 873 |
+
"model.layers.30.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 874 |
+
"model.layers.30.self_attn.k_norm.weight": "model.safetensors",
|
| 875 |
+
"model.layers.30.self_attn.k_proj.biases": "model.safetensors",
|
| 876 |
+
"model.layers.30.self_attn.k_proj.scales": "model.safetensors",
|
| 877 |
+
"model.layers.30.self_attn.k_proj.weight": "model.safetensors",
|
| 878 |
+
"model.layers.30.self_attn.o_proj.biases": "model.safetensors",
|
| 879 |
+
"model.layers.30.self_attn.o_proj.scales": "model.safetensors",
|
| 880 |
+
"model.layers.30.self_attn.o_proj.weight": "model.safetensors",
|
| 881 |
+
"model.layers.30.self_attn.q_norm.weight": "model.safetensors",
|
| 882 |
+
"model.layers.30.self_attn.q_proj.biases": "model.safetensors",
|
| 883 |
+
"model.layers.30.self_attn.q_proj.scales": "model.safetensors",
|
| 884 |
+
"model.layers.30.self_attn.q_proj.weight": "model.safetensors",
|
| 885 |
+
"model.layers.30.self_attn.v_proj.biases": "model.safetensors",
|
| 886 |
+
"model.layers.30.self_attn.v_proj.scales": "model.safetensors",
|
| 887 |
+
"model.layers.30.self_attn.v_proj.weight": "model.safetensors",
|
| 888 |
+
"model.layers.31.input_layernorm.weight": "model.safetensors",
|
| 889 |
+
"model.layers.31.layer_scalar": "model.safetensors",
|
| 890 |
+
"model.layers.31.mlp.down_proj.biases": "model.safetensors",
|
| 891 |
+
"model.layers.31.mlp.down_proj.scales": "model.safetensors",
|
| 892 |
+
"model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
| 893 |
+
"model.layers.31.mlp.gate_proj.biases": "model.safetensors",
|
| 894 |
+
"model.layers.31.mlp.gate_proj.scales": "model.safetensors",
|
| 895 |
+
"model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
| 896 |
+
"model.layers.31.mlp.up_proj.biases": "model.safetensors",
|
| 897 |
+
"model.layers.31.mlp.up_proj.scales": "model.safetensors",
|
| 898 |
+
"model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
| 899 |
+
"model.layers.31.per_layer_input_gate.biases": "model.safetensors",
|
| 900 |
+
"model.layers.31.per_layer_input_gate.scales": "model.safetensors",
|
| 901 |
+
"model.layers.31.per_layer_input_gate.weight": "model.safetensors",
|
| 902 |
+
"model.layers.31.per_layer_projection.biases": "model.safetensors",
|
| 903 |
+
"model.layers.31.per_layer_projection.scales": "model.safetensors",
|
| 904 |
+
"model.layers.31.per_layer_projection.weight": "model.safetensors",
|
| 905 |
+
"model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
| 906 |
+
"model.layers.31.post_feedforward_layernorm.weight": "model.safetensors",
|
| 907 |
+
"model.layers.31.post_per_layer_input_norm.weight": "model.safetensors",
|
| 908 |
+
"model.layers.31.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 909 |
+
"model.layers.31.self_attn.k_norm.weight": "model.safetensors",
|
| 910 |
+
"model.layers.31.self_attn.k_proj.biases": "model.safetensors",
|
| 911 |
+
"model.layers.31.self_attn.k_proj.scales": "model.safetensors",
|
| 912 |
+
"model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
| 913 |
+
"model.layers.31.self_attn.o_proj.biases": "model.safetensors",
|
| 914 |
+
"model.layers.31.self_attn.o_proj.scales": "model.safetensors",
|
| 915 |
+
"model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
| 916 |
+
"model.layers.31.self_attn.q_norm.weight": "model.safetensors",
|
| 917 |
+
"model.layers.31.self_attn.q_proj.biases": "model.safetensors",
|
| 918 |
+
"model.layers.31.self_attn.q_proj.scales": "model.safetensors",
|
| 919 |
+
"model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
| 920 |
+
"model.layers.31.self_attn.v_proj.biases": "model.safetensors",
|
| 921 |
+
"model.layers.31.self_attn.v_proj.scales": "model.safetensors",
|
| 922 |
+
"model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
| 923 |
+
"model.layers.32.input_layernorm.weight": "model.safetensors",
|
| 924 |
+
"model.layers.32.layer_scalar": "model.safetensors",
|
| 925 |
+
"model.layers.32.mlp.down_proj.biases": "model.safetensors",
|
| 926 |
+
"model.layers.32.mlp.down_proj.scales": "model.safetensors",
|
| 927 |
+
"model.layers.32.mlp.down_proj.weight": "model.safetensors",
|
| 928 |
+
"model.layers.32.mlp.gate_proj.biases": "model.safetensors",
|
| 929 |
+
"model.layers.32.mlp.gate_proj.scales": "model.safetensors",
|
| 930 |
+
"model.layers.32.mlp.gate_proj.weight": "model.safetensors",
|
| 931 |
+
"model.layers.32.mlp.up_proj.biases": "model.safetensors",
|
| 932 |
+
"model.layers.32.mlp.up_proj.scales": "model.safetensors",
|
| 933 |
+
"model.layers.32.mlp.up_proj.weight": "model.safetensors",
|
| 934 |
+
"model.layers.32.per_layer_input_gate.biases": "model.safetensors",
|
| 935 |
+
"model.layers.32.per_layer_input_gate.scales": "model.safetensors",
|
| 936 |
+
"model.layers.32.per_layer_input_gate.weight": "model.safetensors",
|
| 937 |
+
"model.layers.32.per_layer_projection.biases": "model.safetensors",
|
| 938 |
+
"model.layers.32.per_layer_projection.scales": "model.safetensors",
|
| 939 |
+
"model.layers.32.per_layer_projection.weight": "model.safetensors",
|
| 940 |
+
"model.layers.32.post_attention_layernorm.weight": "model.safetensors",
|
| 941 |
+
"model.layers.32.post_feedforward_layernorm.weight": "model.safetensors",
|
| 942 |
+
"model.layers.32.post_per_layer_input_norm.weight": "model.safetensors",
|
| 943 |
+
"model.layers.32.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 944 |
+
"model.layers.32.self_attn.k_norm.weight": "model.safetensors",
|
| 945 |
+
"model.layers.32.self_attn.k_proj.biases": "model.safetensors",
|
| 946 |
+
"model.layers.32.self_attn.k_proj.scales": "model.safetensors",
|
| 947 |
+
"model.layers.32.self_attn.k_proj.weight": "model.safetensors",
|
| 948 |
+
"model.layers.32.self_attn.o_proj.biases": "model.safetensors",
|
| 949 |
+
"model.layers.32.self_attn.o_proj.scales": "model.safetensors",
|
| 950 |
+
"model.layers.32.self_attn.o_proj.weight": "model.safetensors",
|
| 951 |
+
"model.layers.32.self_attn.q_norm.weight": "model.safetensors",
|
| 952 |
+
"model.layers.32.self_attn.q_proj.biases": "model.safetensors",
|
| 953 |
+
"model.layers.32.self_attn.q_proj.scales": "model.safetensors",
|
| 954 |
+
"model.layers.32.self_attn.q_proj.weight": "model.safetensors",
|
| 955 |
+
"model.layers.32.self_attn.v_proj.biases": "model.safetensors",
|
| 956 |
+
"model.layers.32.self_attn.v_proj.scales": "model.safetensors",
|
| 957 |
+
"model.layers.32.self_attn.v_proj.weight": "model.safetensors",
|
| 958 |
+
"model.layers.33.input_layernorm.weight": "model.safetensors",
|
| 959 |
+
"model.layers.33.layer_scalar": "model.safetensors",
|
| 960 |
+
"model.layers.33.mlp.down_proj.biases": "model.safetensors",
|
| 961 |
+
"model.layers.33.mlp.down_proj.scales": "model.safetensors",
|
| 962 |
+
"model.layers.33.mlp.down_proj.weight": "model.safetensors",
|
| 963 |
+
"model.layers.33.mlp.gate_proj.biases": "model.safetensors",
|
| 964 |
+
"model.layers.33.mlp.gate_proj.scales": "model.safetensors",
|
| 965 |
+
"model.layers.33.mlp.gate_proj.weight": "model.safetensors",
|
| 966 |
+
"model.layers.33.mlp.up_proj.biases": "model.safetensors",
|
| 967 |
+
"model.layers.33.mlp.up_proj.scales": "model.safetensors",
|
| 968 |
+
"model.layers.33.mlp.up_proj.weight": "model.safetensors",
|
| 969 |
+
"model.layers.33.per_layer_input_gate.biases": "model.safetensors",
|
| 970 |
+
"model.layers.33.per_layer_input_gate.scales": "model.safetensors",
|
| 971 |
+
"model.layers.33.per_layer_input_gate.weight": "model.safetensors",
|
| 972 |
+
"model.layers.33.per_layer_projection.biases": "model.safetensors",
|
| 973 |
+
"model.layers.33.per_layer_projection.scales": "model.safetensors",
|
| 974 |
+
"model.layers.33.per_layer_projection.weight": "model.safetensors",
|
| 975 |
+
"model.layers.33.post_attention_layernorm.weight": "model.safetensors",
|
| 976 |
+
"model.layers.33.post_feedforward_layernorm.weight": "model.safetensors",
|
| 977 |
+
"model.layers.33.post_per_layer_input_norm.weight": "model.safetensors",
|
| 978 |
+
"model.layers.33.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 979 |
+
"model.layers.33.self_attn.k_norm.weight": "model.safetensors",
|
| 980 |
+
"model.layers.33.self_attn.k_proj.biases": "model.safetensors",
|
| 981 |
+
"model.layers.33.self_attn.k_proj.scales": "model.safetensors",
|
| 982 |
+
"model.layers.33.self_attn.k_proj.weight": "model.safetensors",
|
| 983 |
+
"model.layers.33.self_attn.o_proj.biases": "model.safetensors",
|
| 984 |
+
"model.layers.33.self_attn.o_proj.scales": "model.safetensors",
|
| 985 |
+
"model.layers.33.self_attn.o_proj.weight": "model.safetensors",
|
| 986 |
+
"model.layers.33.self_attn.q_norm.weight": "model.safetensors",
|
| 987 |
+
"model.layers.33.self_attn.q_proj.biases": "model.safetensors",
|
| 988 |
+
"model.layers.33.self_attn.q_proj.scales": "model.safetensors",
|
| 989 |
+
"model.layers.33.self_attn.q_proj.weight": "model.safetensors",
|
| 990 |
+
"model.layers.33.self_attn.v_proj.biases": "model.safetensors",
|
| 991 |
+
"model.layers.33.self_attn.v_proj.scales": "model.safetensors",
|
| 992 |
+
"model.layers.33.self_attn.v_proj.weight": "model.safetensors",
|
| 993 |
+
"model.layers.34.input_layernorm.weight": "model.safetensors",
|
| 994 |
+
"model.layers.34.layer_scalar": "model.safetensors",
|
| 995 |
+
"model.layers.34.mlp.down_proj.biases": "model.safetensors",
|
| 996 |
+
"model.layers.34.mlp.down_proj.scales": "model.safetensors",
|
| 997 |
+
"model.layers.34.mlp.down_proj.weight": "model.safetensors",
|
| 998 |
+
"model.layers.34.mlp.gate_proj.biases": "model.safetensors",
|
| 999 |
+
"model.layers.34.mlp.gate_proj.scales": "model.safetensors",
|
| 1000 |
+
"model.layers.34.mlp.gate_proj.weight": "model.safetensors",
|
| 1001 |
+
"model.layers.34.mlp.up_proj.biases": "model.safetensors",
|
| 1002 |
+
"model.layers.34.mlp.up_proj.scales": "model.safetensors",
|
| 1003 |
+
"model.layers.34.mlp.up_proj.weight": "model.safetensors",
|
| 1004 |
+
"model.layers.34.per_layer_input_gate.biases": "model.safetensors",
|
| 1005 |
+
"model.layers.34.per_layer_input_gate.scales": "model.safetensors",
|
| 1006 |
+
"model.layers.34.per_layer_input_gate.weight": "model.safetensors",
|
| 1007 |
+
"model.layers.34.per_layer_projection.biases": "model.safetensors",
|
| 1008 |
+
"model.layers.34.per_layer_projection.scales": "model.safetensors",
|
| 1009 |
+
"model.layers.34.per_layer_projection.weight": "model.safetensors",
|
| 1010 |
+
"model.layers.34.post_attention_layernorm.weight": "model.safetensors",
|
| 1011 |
+
"model.layers.34.post_feedforward_layernorm.weight": "model.safetensors",
|
| 1012 |
+
"model.layers.34.post_per_layer_input_norm.weight": "model.safetensors",
|
| 1013 |
+
"model.layers.34.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 1014 |
+
"model.layers.34.self_attn.k_norm.weight": "model.safetensors",
|
| 1015 |
+
"model.layers.34.self_attn.k_proj.biases": "model.safetensors",
|
| 1016 |
+
"model.layers.34.self_attn.k_proj.scales": "model.safetensors",
|
| 1017 |
+
"model.layers.34.self_attn.k_proj.weight": "model.safetensors",
|
| 1018 |
+
"model.layers.34.self_attn.o_proj.biases": "model.safetensors",
|
| 1019 |
+
"model.layers.34.self_attn.o_proj.scales": "model.safetensors",
|
| 1020 |
+
"model.layers.34.self_attn.o_proj.weight": "model.safetensors",
|
| 1021 |
+
"model.layers.34.self_attn.q_norm.weight": "model.safetensors",
|
| 1022 |
+
"model.layers.34.self_attn.q_proj.biases": "model.safetensors",
|
| 1023 |
+
"model.layers.34.self_attn.q_proj.scales": "model.safetensors",
|
| 1024 |
+
"model.layers.34.self_attn.q_proj.weight": "model.safetensors",
|
| 1025 |
+
"model.layers.34.self_attn.v_proj.biases": "model.safetensors",
|
| 1026 |
+
"model.layers.34.self_attn.v_proj.scales": "model.safetensors",
|
| 1027 |
+
"model.layers.34.self_attn.v_proj.weight": "model.safetensors",
|
| 1028 |
+
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 1029 |
+
"model.layers.4.layer_scalar": "model.safetensors",
|
| 1030 |
+
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 1031 |
+
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 1032 |
+
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 1033 |
+
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 1034 |
+
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 1035 |
+
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 1036 |
+
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 1037 |
+
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 1038 |
+
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 1039 |
+
"model.layers.4.per_layer_input_gate.biases": "model.safetensors",
|
| 1040 |
+
"model.layers.4.per_layer_input_gate.scales": "model.safetensors",
|
| 1041 |
+
"model.layers.4.per_layer_input_gate.weight": "model.safetensors",
|
| 1042 |
+
"model.layers.4.per_layer_projection.biases": "model.safetensors",
|
| 1043 |
+
"model.layers.4.per_layer_projection.scales": "model.safetensors",
|
| 1044 |
+
"model.layers.4.per_layer_projection.weight": "model.safetensors",
|
| 1045 |
+
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 1046 |
+
"model.layers.4.post_feedforward_layernorm.weight": "model.safetensors",
|
| 1047 |
+
"model.layers.4.post_per_layer_input_norm.weight": "model.safetensors",
|
| 1048 |
+
"model.layers.4.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 1049 |
+
"model.layers.4.self_attn.k_norm.weight": "model.safetensors",
|
| 1050 |
+
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 1051 |
+
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 1052 |
+
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 1053 |
+
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 1054 |
+
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 1055 |
+
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 1056 |
+
"model.layers.4.self_attn.q_norm.weight": "model.safetensors",
|
| 1057 |
+
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 1058 |
+
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 1059 |
+
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 1060 |
+
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 1061 |
+
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 1062 |
+
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 1063 |
+
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 1064 |
+
"model.layers.5.layer_scalar": "model.safetensors",
|
| 1065 |
+
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 1066 |
+
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 1067 |
+
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 1068 |
+
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 1069 |
+
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 1070 |
+
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 1071 |
+
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 1072 |
+
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 1073 |
+
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 1074 |
+
"model.layers.5.per_layer_input_gate.biases": "model.safetensors",
|
| 1075 |
+
"model.layers.5.per_layer_input_gate.scales": "model.safetensors",
|
| 1076 |
+
"model.layers.5.per_layer_input_gate.weight": "model.safetensors",
|
| 1077 |
+
"model.layers.5.per_layer_projection.biases": "model.safetensors",
|
| 1078 |
+
"model.layers.5.per_layer_projection.scales": "model.safetensors",
|
| 1079 |
+
"model.layers.5.per_layer_projection.weight": "model.safetensors",
|
| 1080 |
+
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 1081 |
+
"model.layers.5.post_feedforward_layernorm.weight": "model.safetensors",
|
| 1082 |
+
"model.layers.5.post_per_layer_input_norm.weight": "model.safetensors",
|
| 1083 |
+
"model.layers.5.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 1084 |
+
"model.layers.5.self_attn.k_norm.weight": "model.safetensors",
|
| 1085 |
+
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 1086 |
+
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 1087 |
+
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 1088 |
+
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 1089 |
+
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 1090 |
+
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 1091 |
+
"model.layers.5.self_attn.q_norm.weight": "model.safetensors",
|
| 1092 |
+
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 1093 |
+
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 1094 |
+
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 1095 |
+
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 1096 |
+
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 1097 |
+
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 1098 |
+
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 1099 |
+
"model.layers.6.layer_scalar": "model.safetensors",
|
| 1100 |
+
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 1101 |
+
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 1102 |
+
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 1103 |
+
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 1104 |
+
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 1105 |
+
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 1106 |
+
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 1107 |
+
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 1108 |
+
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 1109 |
+
"model.layers.6.per_layer_input_gate.biases": "model.safetensors",
|
| 1110 |
+
"model.layers.6.per_layer_input_gate.scales": "model.safetensors",
|
| 1111 |
+
"model.layers.6.per_layer_input_gate.weight": "model.safetensors",
|
| 1112 |
+
"model.layers.6.per_layer_projection.biases": "model.safetensors",
|
| 1113 |
+
"model.layers.6.per_layer_projection.scales": "model.safetensors",
|
| 1114 |
+
"model.layers.6.per_layer_projection.weight": "model.safetensors",
|
| 1115 |
+
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 1116 |
+
"model.layers.6.post_feedforward_layernorm.weight": "model.safetensors",
|
| 1117 |
+
"model.layers.6.post_per_layer_input_norm.weight": "model.safetensors",
|
| 1118 |
+
"model.layers.6.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 1119 |
+
"model.layers.6.self_attn.k_norm.weight": "model.safetensors",
|
| 1120 |
+
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 1121 |
+
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 1122 |
+
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 1123 |
+
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 1124 |
+
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 1125 |
+
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 1126 |
+
"model.layers.6.self_attn.q_norm.weight": "model.safetensors",
|
| 1127 |
+
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 1128 |
+
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 1129 |
+
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 1130 |
+
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 1131 |
+
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 1132 |
+
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 1133 |
+
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 1134 |
+
"model.layers.7.layer_scalar": "model.safetensors",
|
| 1135 |
+
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 1136 |
+
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 1137 |
+
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 1138 |
+
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 1139 |
+
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 1140 |
+
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 1141 |
+
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 1142 |
+
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 1143 |
+
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 1144 |
+
"model.layers.7.per_layer_input_gate.biases": "model.safetensors",
|
| 1145 |
+
"model.layers.7.per_layer_input_gate.scales": "model.safetensors",
|
| 1146 |
+
"model.layers.7.per_layer_input_gate.weight": "model.safetensors",
|
| 1147 |
+
"model.layers.7.per_layer_projection.biases": "model.safetensors",
|
| 1148 |
+
"model.layers.7.per_layer_projection.scales": "model.safetensors",
|
| 1149 |
+
"model.layers.7.per_layer_projection.weight": "model.safetensors",
|
| 1150 |
+
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 1151 |
+
"model.layers.7.post_feedforward_layernorm.weight": "model.safetensors",
|
| 1152 |
+
"model.layers.7.post_per_layer_input_norm.weight": "model.safetensors",
|
| 1153 |
+
"model.layers.7.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 1154 |
+
"model.layers.7.self_attn.k_norm.weight": "model.safetensors",
|
| 1155 |
+
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 1156 |
+
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 1157 |
+
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 1158 |
+
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 1159 |
+
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 1160 |
+
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 1161 |
+
"model.layers.7.self_attn.q_norm.weight": "model.safetensors",
|
| 1162 |
+
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 1163 |
+
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 1164 |
+
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 1165 |
+
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 1166 |
+
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 1167 |
+
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 1168 |
+
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 1169 |
+
"model.layers.8.layer_scalar": "model.safetensors",
|
| 1170 |
+
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 1171 |
+
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 1172 |
+
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 1173 |
+
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 1174 |
+
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 1175 |
+
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 1176 |
+
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 1177 |
+
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 1178 |
+
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 1179 |
+
"model.layers.8.per_layer_input_gate.biases": "model.safetensors",
|
| 1180 |
+
"model.layers.8.per_layer_input_gate.scales": "model.safetensors",
|
| 1181 |
+
"model.layers.8.per_layer_input_gate.weight": "model.safetensors",
|
| 1182 |
+
"model.layers.8.per_layer_projection.biases": "model.safetensors",
|
| 1183 |
+
"model.layers.8.per_layer_projection.scales": "model.safetensors",
|
| 1184 |
+
"model.layers.8.per_layer_projection.weight": "model.safetensors",
|
| 1185 |
+
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 1186 |
+
"model.layers.8.post_feedforward_layernorm.weight": "model.safetensors",
|
| 1187 |
+
"model.layers.8.post_per_layer_input_norm.weight": "model.safetensors",
|
| 1188 |
+
"model.layers.8.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 1189 |
+
"model.layers.8.self_attn.k_norm.weight": "model.safetensors",
|
| 1190 |
+
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 1191 |
+
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 1192 |
+
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 1193 |
+
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 1194 |
+
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 1195 |
+
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 1196 |
+
"model.layers.8.self_attn.q_norm.weight": "model.safetensors",
|
| 1197 |
+
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 1198 |
+
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 1199 |
+
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 1200 |
+
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 1201 |
+
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 1202 |
+
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 1203 |
+
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 1204 |
+
"model.layers.9.layer_scalar": "model.safetensors",
|
| 1205 |
+
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 1206 |
+
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 1207 |
+
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 1208 |
+
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 1209 |
+
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 1210 |
+
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 1211 |
+
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 1212 |
+
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 1213 |
+
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 1214 |
+
"model.layers.9.per_layer_input_gate.biases": "model.safetensors",
|
| 1215 |
+
"model.layers.9.per_layer_input_gate.scales": "model.safetensors",
|
| 1216 |
+
"model.layers.9.per_layer_input_gate.weight": "model.safetensors",
|
| 1217 |
+
"model.layers.9.per_layer_projection.biases": "model.safetensors",
|
| 1218 |
+
"model.layers.9.per_layer_projection.scales": "model.safetensors",
|
| 1219 |
+
"model.layers.9.per_layer_projection.weight": "model.safetensors",
|
| 1220 |
+
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 1221 |
+
"model.layers.9.post_feedforward_layernorm.weight": "model.safetensors",
|
| 1222 |
+
"model.layers.9.post_per_layer_input_norm.weight": "model.safetensors",
|
| 1223 |
+
"model.layers.9.pre_feedforward_layernorm.weight": "model.safetensors",
|
| 1224 |
+
"model.layers.9.self_attn.k_norm.weight": "model.safetensors",
|
| 1225 |
+
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 1226 |
+
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 1227 |
+
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 1228 |
+
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 1229 |
+
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 1230 |
+
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 1231 |
+
"model.layers.9.self_attn.q_norm.weight": "model.safetensors",
|
| 1232 |
+
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 1233 |
+
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 1234 |
+
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 1235 |
+
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 1236 |
+
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 1237 |
+
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 1238 |
+
"model.norm.weight": "model.safetensors",
|
| 1239 |
+
"model.per_layer_model_projection.biases": "model.safetensors",
|
| 1240 |
+
"model.per_layer_model_projection.scales": "model.safetensors",
|
| 1241 |
+
"model.per_layer_model_projection.weight": "model.safetensors",
|
| 1242 |
+
"model.per_layer_projection_norm.weight": "model.safetensors"
|
| 1243 |
+
}
|
| 1244 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
|
| 3 |
+
size 32169626
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|audio|>",
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"boa_token": "<|audio>",
|
| 5 |
+
"boi_token": "<|image>",
|
| 6 |
+
"bos_token": "<bos>",
|
| 7 |
+
"eoa_token": "<audio|>",
|
| 8 |
+
"eoc_token": "<channel|>",
|
| 9 |
+
"eoi_token": "<image|>",
|
| 10 |
+
"eos_token": "<eos>",
|
| 11 |
+
"eot_token": "<turn|>",
|
| 12 |
+
"escape_token": "<|\"|>",
|
| 13 |
+
"etc_token": "<tool_call|>",
|
| 14 |
+
"etd_token": "<tool|>",
|
| 15 |
+
"etr_token": "<tool_response|>",
|
| 16 |
+
"extra_special_tokens": [
|
| 17 |
+
"<|video|>"
|
| 18 |
+
],
|
| 19 |
+
"image_token": "<|image|>",
|
| 20 |
+
"is_local": true,
|
| 21 |
+
"mask_token": "<mask>",
|
| 22 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
+
"model_specific_special_tokens": {
|
| 24 |
+
"audio_token": "<|audio|>",
|
| 25 |
+
"boa_token": "<|audio>",
|
| 26 |
+
"boi_token": "<|image>",
|
| 27 |
+
"eoa_token": "<audio|>",
|
| 28 |
+
"eoc_token": "<channel|>",
|
| 29 |
+
"eoi_token": "<image|>",
|
| 30 |
+
"eot_token": "<turn|>",
|
| 31 |
+
"escape_token": "<|\"|>",
|
| 32 |
+
"etc_token": "<tool_call|>",
|
| 33 |
+
"etd_token": "<tool|>",
|
| 34 |
+
"etr_token": "<tool_response|>",
|
| 35 |
+
"image_token": "<|image|>",
|
| 36 |
+
"soc_token": "<|channel>",
|
| 37 |
+
"sot_token": "<|turn>",
|
| 38 |
+
"stc_token": "<|tool_call>",
|
| 39 |
+
"std_token": "<|tool>",
|
| 40 |
+
"str_token": "<|tool_response>",
|
| 41 |
+
"think_token": "<|think|>"
|
| 42 |
+
},
|
| 43 |
+
"pad_token": "<pad>",
|
| 44 |
+
"padding_side": "left",
|
| 45 |
+
"processor_class": "Gemma4Processor",
|
| 46 |
+
"response_schema": {
|
| 47 |
+
"properties": {
|
| 48 |
+
"content": {
|
| 49 |
+
"type": "string"
|
| 50 |
+
},
|
| 51 |
+
"role": {
|
| 52 |
+
"const": "assistant"
|
| 53 |
+
},
|
| 54 |
+
"thinking": {
|
| 55 |
+
"type": "string"
|
| 56 |
+
},
|
| 57 |
+
"tool_calls": {
|
| 58 |
+
"items": {
|
| 59 |
+
"properties": {
|
| 60 |
+
"function": {
|
| 61 |
+
"properties": {
|
| 62 |
+
"arguments": {
|
| 63 |
+
"additionalProperties": {},
|
| 64 |
+
"type": "object",
|
| 65 |
+
"x-parser": "gemma4-tool-call"
|
| 66 |
+
},
|
| 67 |
+
"name": {
|
| 68 |
+
"type": "string"
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"type": "object",
|
| 72 |
+
"x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
|
| 73 |
+
},
|
| 74 |
+
"type": {
|
| 75 |
+
"const": "function"
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"type": "object"
|
| 79 |
+
},
|
| 80 |
+
"type": "array",
|
| 81 |
+
"x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
"type": "object",
|
| 85 |
+
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
|
| 86 |
+
},
|
| 87 |
+
"soc_token": "<|channel>",
|
| 88 |
+
"sot_token": "<|turn>",
|
| 89 |
+
"stc_token": "<|tool_call>",
|
| 90 |
+
"std_token": "<|tool>",
|
| 91 |
+
"str_token": "<|tool_response>",
|
| 92 |
+
"think_token": "<|think|>",
|
| 93 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 94 |
+
"tool_parser_type": "gemma4",
|
| 95 |
+
"unk_token": "<unk>"
|
| 96 |
+
}
|