初始化项目，由ModelHub XC社区提供模型
Model: universitytehran/PersianMind-v1.0 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
438
LICENSE
Normal file
438
LICENSE
Normal file
@@ -0,0 +1,438 @@
|
|||||||
|
Attribution-NonCommercial-ShareAlike 4.0 International
|
||||||
|
|
||||||
|
=======================================================================
|
||||||
|
|
||||||
|
Creative Commons Corporation ("Creative Commons") is not a law firm and
|
||||||
|
does not provide legal services or legal advice. Distribution of
|
||||||
|
Creative Commons public licenses does not create a lawyer-client or
|
||||||
|
other relationship. Creative Commons makes its licenses and related
|
||||||
|
information available on an "as-is" basis. Creative Commons gives no
|
||||||
|
warranties regarding its licenses, any material licensed under their
|
||||||
|
terms and conditions, or any related information. Creative Commons
|
||||||
|
disclaims all liability for damages resulting from their use to the
|
||||||
|
fullest extent possible.
|
||||||
|
|
||||||
|
Using Creative Commons Public Licenses
|
||||||
|
|
||||||
|
Creative Commons public licenses provide a standard set of terms and
|
||||||
|
conditions that creators and other rights holders may use to share
|
||||||
|
original works of authorship and other material subject to copyright
|
||||||
|
and certain other rights specified in the public license below. The
|
||||||
|
following considerations are for informational purposes only, are not
|
||||||
|
exhaustive, and do not form part of our licenses.
|
||||||
|
|
||||||
|
Considerations for licensors: Our public licenses are
|
||||||
|
intended for use by those authorized to give the public
|
||||||
|
permission to use material in ways otherwise restricted by
|
||||||
|
copyright and certain other rights. Our licenses are
|
||||||
|
irrevocable. Licensors should read and understand the terms
|
||||||
|
and conditions of the license they choose before applying it.
|
||||||
|
Licensors should also secure all rights necessary before
|
||||||
|
applying our licenses so that the public can reuse the
|
||||||
|
material as expected. Licensors should clearly mark any
|
||||||
|
material not subject to the license. This includes other CC-
|
||||||
|
licensed material, or material used under an exception or
|
||||||
|
limitation to copyright. More considerations for licensors:
|
||||||
|
wiki.creativecommons.org/Considerations_for_licensors
|
||||||
|
|
||||||
|
Considerations for the public: By using one of our public
|
||||||
|
licenses, a licensor grants the public permission to use the
|
||||||
|
licensed material under specified terms and conditions. If
|
||||||
|
the licensor's permission is not necessary for any reason--for
|
||||||
|
example, because of any applicable exception or limitation to
|
||||||
|
copyright--then that use is not regulated by the license. Our
|
||||||
|
licenses grant only permissions under copyright and certain
|
||||||
|
other rights that a licensor has authority to grant. Use of
|
||||||
|
the licensed material may still be restricted for other
|
||||||
|
reasons, including because others have copyright or other
|
||||||
|
rights in the material. A licensor may make special requests,
|
||||||
|
such as asking that all changes be marked or described.
|
||||||
|
Although not required by our licenses, you are encouraged to
|
||||||
|
respect those requests where reasonable. More considerations
|
||||||
|
for the public:
|
||||||
|
wiki.creativecommons.org/Considerations_for_licensees
|
||||||
|
|
||||||
|
=======================================================================
|
||||||
|
|
||||||
|
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
|
||||||
|
Public License
|
||||||
|
|
||||||
|
By exercising the Licensed Rights (defined below), You accept and agree
|
||||||
|
to be bound by the terms and conditions of this Creative Commons
|
||||||
|
Attribution-NonCommercial-ShareAlike 4.0 International Public License
|
||||||
|
("Public License"). To the extent this Public License may be
|
||||||
|
interpreted as a contract, You are granted the Licensed Rights in
|
||||||
|
consideration of Your acceptance of these terms and conditions, and the
|
||||||
|
Licensor grants You such rights in consideration of benefits the
|
||||||
|
Licensor receives from making the Licensed Material available under
|
||||||
|
these terms and conditions.
|
||||||
|
|
||||||
|
|
||||||
|
Section 1 -- Definitions.
|
||||||
|
|
||||||
|
a. Adapted Material means material subject to Copyright and Similar
|
||||||
|
Rights that is derived from or based upon the Licensed Material
|
||||||
|
and in which the Licensed Material is translated, altered,
|
||||||
|
arranged, transformed, or otherwise modified in a manner requiring
|
||||||
|
permission under the Copyright and Similar Rights held by the
|
||||||
|
Licensor. For purposes of this Public License, where the Licensed
|
||||||
|
Material is a musical work, performance, or sound recording,
|
||||||
|
Adapted Material is always produced where the Licensed Material is
|
||||||
|
synched in timed relation with a moving image.
|
||||||
|
|
||||||
|
b. Adapter's License means the license You apply to Your Copyright
|
||||||
|
and Similar Rights in Your contributions to Adapted Material in
|
||||||
|
accordance with the terms and conditions of this Public License.
|
||||||
|
|
||||||
|
c. BY-NC-SA Compatible License means a license listed at
|
||||||
|
creativecommons.org/compatiblelicenses, approved by Creative
|
||||||
|
Commons as essentially the equivalent of this Public License.
|
||||||
|
|
||||||
|
d. Copyright and Similar Rights means copyright and/or similar rights
|
||||||
|
closely related to copyright including, without limitation,
|
||||||
|
performance, broadcast, sound recording, and Sui Generis Database
|
||||||
|
Rights, without regard to how the rights are labeled or
|
||||||
|
categorized. For purposes of this Public License, the rights
|
||||||
|
specified in Section 2(b)(1)-(2) are not Copyright and Similar
|
||||||
|
Rights.
|
||||||
|
|
||||||
|
e. Effective Technological Measures means those measures that, in the
|
||||||
|
absence of proper authority, may not be circumvented under laws
|
||||||
|
fulfilling obligations under Article 11 of the WIPO Copyright
|
||||||
|
Treaty adopted on December 20, 1996, and/or similar international
|
||||||
|
agreements.
|
||||||
|
|
||||||
|
f. Exceptions and Limitations means fair use, fair dealing, and/or
|
||||||
|
any other exception or limitation to Copyright and Similar Rights
|
||||||
|
that applies to Your use of the Licensed Material.
|
||||||
|
|
||||||
|
g. License Elements means the license attributes listed in the name
|
||||||
|
of a Creative Commons Public License. The License Elements of this
|
||||||
|
Public License are Attribution, NonCommercial, and ShareAlike.
|
||||||
|
|
||||||
|
h. Licensed Material means the artistic or literary work, database,
|
||||||
|
or other material to which the Licensor applied this Public
|
||||||
|
License.
|
||||||
|
|
||||||
|
i. Licensed Rights means the rights granted to You subject to the
|
||||||
|
terms and conditions of this Public License, which are limited to
|
||||||
|
all Copyright and Similar Rights that apply to Your use of the
|
||||||
|
Licensed Material and that the Licensor has authority to license.
|
||||||
|
|
||||||
|
j. Licensor means the individual(s) or entity(ies) granting rights
|
||||||
|
under this Public License.
|
||||||
|
|
||||||
|
k. NonCommercial means not primarily intended for or directed towards
|
||||||
|
commercial advantage or monetary compensation. For purposes of
|
||||||
|
this Public License, the exchange of the Licensed Material for
|
||||||
|
other material subject to Copyright and Similar Rights by digital
|
||||||
|
file-sharing or similar means is NonCommercial provided there is
|
||||||
|
no payment of monetary compensation in connection with the
|
||||||
|
exchange.
|
||||||
|
|
||||||
|
l. Share means to provide material to the public by any means or
|
||||||
|
process that requires permission under the Licensed Rights, such
|
||||||
|
as reproduction, public display, public performance, distribution,
|
||||||
|
dissemination, communication, or importation, and to make material
|
||||||
|
available to the public including in ways that members of the
|
||||||
|
public may access the material from a place and at a time
|
||||||
|
individually chosen by them.
|
||||||
|
|
||||||
|
m. Sui Generis Database Rights means rights other than copyright
|
||||||
|
resulting from Directive 96/9/EC of the European Parliament and of
|
||||||
|
the Council of 11 March 1996 on the legal protection of databases,
|
||||||
|
as amended and/or succeeded, as well as other essentially
|
||||||
|
equivalent rights anywhere in the world.
|
||||||
|
|
||||||
|
n. You means the individual or entity exercising the Licensed Rights
|
||||||
|
under this Public License. Your has a corresponding meaning.
|
||||||
|
|
||||||
|
|
||||||
|
Section 2 -- Scope.
|
||||||
|
|
||||||
|
a. License grant.
|
||||||
|
|
||||||
|
1. Subject to the terms and conditions of this Public License,
|
||||||
|
the Licensor hereby grants You a worldwide, royalty-free,
|
||||||
|
non-sublicensable, non-exclusive, irrevocable license to
|
||||||
|
exercise the Licensed Rights in the Licensed Material to:
|
||||||
|
|
||||||
|
a. reproduce and Share the Licensed Material, in whole or
|
||||||
|
in part, for NonCommercial purposes only; and
|
||||||
|
|
||||||
|
b. produce, reproduce, and Share Adapted Material for
|
||||||
|
NonCommercial purposes only.
|
||||||
|
|
||||||
|
2. Exceptions and Limitations. For the avoidance of doubt, where
|
||||||
|
Exceptions and Limitations apply to Your use, this Public
|
||||||
|
License does not apply, and You do not need to comply with
|
||||||
|
its terms and conditions.
|
||||||
|
|
||||||
|
3. Term. The term of this Public License is specified in Section
|
||||||
|
6(a).
|
||||||
|
|
||||||
|
4. Media and formats; technical modifications allowed. The
|
||||||
|
Licensor authorizes You to exercise the Licensed Rights in
|
||||||
|
all media and formats whether now known or hereafter created,
|
||||||
|
and to make technical modifications necessary to do so. The
|
||||||
|
Licensor waives and/or agrees not to assert any right or
|
||||||
|
authority to forbid You from making technical modifications
|
||||||
|
necessary to exercise the Licensed Rights, including
|
||||||
|
technical modifications necessary to circumvent Effective
|
||||||
|
Technological Measures. For purposes of this Public License,
|
||||||
|
simply making modifications authorized by this Section 2(a)
|
||||||
|
(4) never produces Adapted Material.
|
||||||
|
|
||||||
|
5. Downstream recipients.
|
||||||
|
|
||||||
|
a. Offer from the Licensor -- Licensed Material. Every
|
||||||
|
recipient of the Licensed Material automatically
|
||||||
|
receives an offer from the Licensor to exercise the
|
||||||
|
Licensed Rights under the terms and conditions of this
|
||||||
|
Public License.
|
||||||
|
|
||||||
|
b. Additional offer from the Licensor -- Adapted Material.
|
||||||
|
Every recipient of Adapted Material from You
|
||||||
|
automatically receives an offer from the Licensor to
|
||||||
|
exercise the Licensed Rights in the Adapted Material
|
||||||
|
under the conditions of the Adapter's License You apply.
|
||||||
|
|
||||||
|
c. No downstream restrictions. You may not offer or impose
|
||||||
|
any additional or different terms or conditions on, or
|
||||||
|
apply any Effective Technological Measures to, the
|
||||||
|
Licensed Material if doing so restricts exercise of the
|
||||||
|
Licensed Rights by any recipient of the Licensed
|
||||||
|
Material.
|
||||||
|
|
||||||
|
6. No endorsement. Nothing in this Public License constitutes or
|
||||||
|
may be construed as permission to assert or imply that You
|
||||||
|
are, or that Your use of the Licensed Material is, connected
|
||||||
|
with, or sponsored, endorsed, or granted official status by,
|
||||||
|
the Licensor or others designated to receive attribution as
|
||||||
|
provided in Section 3(a)(1)(A)(i).
|
||||||
|
|
||||||
|
b. Other rights.
|
||||||
|
|
||||||
|
1. Moral rights, such as the right of integrity, are not
|
||||||
|
licensed under this Public License, nor are publicity,
|
||||||
|
privacy, and/or other similar personality rights; however, to
|
||||||
|
the extent possible, the Licensor waives and/or agrees not to
|
||||||
|
assert any such rights held by the Licensor to the limited
|
||||||
|
extent necessary to allow You to exercise the Licensed
|
||||||
|
Rights, but not otherwise.
|
||||||
|
|
||||||
|
2. Patent and trademark rights are not licensed under this
|
||||||
|
Public License.
|
||||||
|
|
||||||
|
3. To the extent possible, the Licensor waives any right to
|
||||||
|
collect royalties from You for the exercise of the Licensed
|
||||||
|
Rights, whether directly or through a collecting society
|
||||||
|
under any voluntary or waivable statutory or compulsory
|
||||||
|
licensing scheme. In all other cases the Licensor expressly
|
||||||
|
reserves any right to collect such royalties, including when
|
||||||
|
the Licensed Material is used other than for NonCommercial
|
||||||
|
purposes.
|
||||||
|
|
||||||
|
|
||||||
|
Section 3 -- License Conditions.
|
||||||
|
|
||||||
|
Your exercise of the Licensed Rights is expressly made subject to the
|
||||||
|
following conditions.
|
||||||
|
|
||||||
|
a. Attribution.
|
||||||
|
|
||||||
|
1. If You Share the Licensed Material (including in modified
|
||||||
|
form), You must:
|
||||||
|
|
||||||
|
a. retain the following if it is supplied by the Licensor
|
||||||
|
with the Licensed Material:
|
||||||
|
|
||||||
|
i. identification of the creator(s) of the Licensed
|
||||||
|
Material and any others designated to receive
|
||||||
|
attribution, in any reasonable manner requested by
|
||||||
|
the Licensor (including by pseudonym if
|
||||||
|
designated);
|
||||||
|
|
||||||
|
ii. a copyright notice;
|
||||||
|
|
||||||
|
iii. a notice that refers to this Public License;
|
||||||
|
|
||||||
|
iv. a notice that refers to the disclaimer of
|
||||||
|
warranties;
|
||||||
|
|
||||||
|
v. a URI or hyperlink to the Licensed Material to the
|
||||||
|
extent reasonably practicable;
|
||||||
|
|
||||||
|
b. indicate if You modified the Licensed Material and
|
||||||
|
retain an indication of any previous modifications; and
|
||||||
|
|
||||||
|
c. indicate the Licensed Material is licensed under this
|
||||||
|
Public License, and include the text of, or the URI or
|
||||||
|
hyperlink to, this Public License.
|
||||||
|
|
||||||
|
2. You may satisfy the conditions in Section 3(a)(1) in any
|
||||||
|
reasonable manner based on the medium, means, and context in
|
||||||
|
which You Share the Licensed Material. For example, it may be
|
||||||
|
reasonable to satisfy the conditions by providing a URI or
|
||||||
|
hyperlink to a resource that includes the required
|
||||||
|
information.
|
||||||
|
3. If requested by the Licensor, You must remove any of the
|
||||||
|
information required by Section 3(a)(1)(A) to the extent
|
||||||
|
reasonably practicable.
|
||||||
|
|
||||||
|
b. ShareAlike.
|
||||||
|
|
||||||
|
In addition to the conditions in Section 3(a), if You Share
|
||||||
|
Adapted Material You produce, the following conditions also apply.
|
||||||
|
|
||||||
|
1. The Adapter's License You apply must be a Creative Commons
|
||||||
|
license with the same License Elements, this version or
|
||||||
|
later, or a BY-NC-SA Compatible License.
|
||||||
|
|
||||||
|
2. You must include the text of, or the URI or hyperlink to, the
|
||||||
|
Adapter's License You apply. You may satisfy this condition
|
||||||
|
in any reasonable manner based on the medium, means, and
|
||||||
|
context in which You Share Adapted Material.
|
||||||
|
|
||||||
|
3. You may not offer or impose any additional or different terms
|
||||||
|
or conditions on, or apply any Effective Technological
|
||||||
|
Measures to, Adapted Material that restrict exercise of the
|
||||||
|
rights granted under the Adapter's License You apply.
|
||||||
|
|
||||||
|
|
||||||
|
Section 4 -- Sui Generis Database Rights.
|
||||||
|
|
||||||
|
Where the Licensed Rights include Sui Generis Database Rights that
|
||||||
|
apply to Your use of the Licensed Material:
|
||||||
|
|
||||||
|
a. for the avoidance of doubt, Section 2(a)(1) grants You the right
|
||||||
|
to extract, reuse, reproduce, and Share all or a substantial
|
||||||
|
portion of the contents of the database for NonCommercial purposes
|
||||||
|
only;
|
||||||
|
|
||||||
|
b. if You include all or a substantial portion of the database
|
||||||
|
contents in a database in which You have Sui Generis Database
|
||||||
|
Rights, then the database in which You have Sui Generis Database
|
||||||
|
Rights (but not its individual contents) is Adapted Material,
|
||||||
|
including for purposes of Section 3(b); and
|
||||||
|
|
||||||
|
c. You must comply with the conditions in Section 3(a) if You Share
|
||||||
|
all or a substantial portion of the contents of the database.
|
||||||
|
|
||||||
|
For the avoidance of doubt, this Section 4 supplements and does not
|
||||||
|
replace Your obligations under this Public License where the Licensed
|
||||||
|
Rights include other Copyright and Similar Rights.
|
||||||
|
|
||||||
|
|
||||||
|
Section 5 -- Disclaimer of Warranties and Limitation of Liability.
|
||||||
|
|
||||||
|
a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
|
||||||
|
EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
|
||||||
|
AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
|
||||||
|
ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
|
||||||
|
IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
|
||||||
|
WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
|
||||||
|
PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
|
||||||
|
ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
|
||||||
|
KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
|
||||||
|
ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
|
||||||
|
|
||||||
|
b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
|
||||||
|
TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
|
||||||
|
NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
|
||||||
|
INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
|
||||||
|
COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
|
||||||
|
USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
|
||||||
|
ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
|
||||||
|
DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
|
||||||
|
IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
|
||||||
|
|
||||||
|
c. The disclaimer of warranties and limitation of liability provided
|
||||||
|
above shall be interpreted in a manner that, to the extent
|
||||||
|
possible, most closely approximates an absolute disclaimer and
|
||||||
|
waiver of all liability.
|
||||||
|
|
||||||
|
|
||||||
|
Section 6 -- Term and Termination.
|
||||||
|
|
||||||
|
a. This Public License applies for the term of the Copyright and
|
||||||
|
Similar Rights licensed here. However, if You fail to comply with
|
||||||
|
this Public License, then Your rights under this Public License
|
||||||
|
terminate automatically.
|
||||||
|
|
||||||
|
b. Where Your right to use the Licensed Material has terminated under
|
||||||
|
Section 6(a), it reinstates:
|
||||||
|
|
||||||
|
1. automatically as of the date the violation is cured, provided
|
||||||
|
it is cured within 30 days of Your discovery of the
|
||||||
|
violation; or
|
||||||
|
|
||||||
|
2. upon express reinstatement by the Licensor.
|
||||||
|
|
||||||
|
For the avoidance of doubt, this Section 6(b) does not affect any
|
||||||
|
right the Licensor may have to seek remedies for Your violations
|
||||||
|
of this Public License.
|
||||||
|
|
||||||
|
c. For the avoidance of doubt, the Licensor may also offer the
|
||||||
|
Licensed Material under separate terms or conditions or stop
|
||||||
|
distributing the Licensed Material at any time; however, doing so
|
||||||
|
will not terminate this Public License.
|
||||||
|
|
||||||
|
d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
|
||||||
|
License.
|
||||||
|
|
||||||
|
|
||||||
|
Section 7 -- Other Terms and Conditions.
|
||||||
|
|
||||||
|
a. The Licensor shall not be bound by any additional or different
|
||||||
|
terms or conditions communicated by You unless expressly agreed.
|
||||||
|
|
||||||
|
b. Any arrangements, understandings, or agreements regarding the
|
||||||
|
Licensed Material not stated herein are separate from and
|
||||||
|
independent of the terms and conditions of this Public License.
|
||||||
|
|
||||||
|
|
||||||
|
Section 8 -- Interpretation.
|
||||||
|
|
||||||
|
a. For the avoidance of doubt, this Public License does not, and
|
||||||
|
shall not be interpreted to, reduce, limit, restrict, or impose
|
||||||
|
conditions on any use of the Licensed Material that could lawfully
|
||||||
|
be made without permission under this Public License.
|
||||||
|
|
||||||
|
b. To the extent possible, if any provision of this Public License is
|
||||||
|
deemed unenforceable, it shall be automatically reformed to the
|
||||||
|
minimum extent necessary to make it enforceable. If the provision
|
||||||
|
cannot be reformed, it shall be severed from this Public License
|
||||||
|
without affecting the enforceability of the remaining terms and
|
||||||
|
conditions.
|
||||||
|
|
||||||
|
c. No term or condition of this Public License will be waived and no
|
||||||
|
failure to comply consented to unless expressly agreed to by the
|
||||||
|
Licensor.
|
||||||
|
|
||||||
|
d. Nothing in this Public License constitutes or may be interpreted
|
||||||
|
as a limitation upon, or waiver of, any privileges and immunities
|
||||||
|
that apply to the Licensor or You, including from the legal
|
||||||
|
processes of any jurisdiction or authority.
|
||||||
|
|
||||||
|
=======================================================================
|
||||||
|
|
||||||
|
Creative Commons is not a party to its public
|
||||||
|
licenses. Notwithstanding, Creative Commons may elect to apply one of
|
||||||
|
its public licenses to material it publishes and in those instances
|
||||||
|
will be considered the “Licensor.” The text of the Creative Commons
|
||||||
|
public licenses is dedicated to the public domain under the CC0 Public
|
||||||
|
Domain Dedication. Except for the limited purpose of indicating that
|
||||||
|
material is shared under a Creative Commons public license or as
|
||||||
|
otherwise permitted by the Creative Commons policies published at
|
||||||
|
creativecommons.org/policies, Creative Commons does not authorize the
|
||||||
|
use of the trademark "Creative Commons" or any other trademark or logo
|
||||||
|
of Creative Commons without its prior written consent including,
|
||||||
|
without limitation, in connection with any unauthorized modifications
|
||||||
|
to any of its public licenses or any other arrangements,
|
||||||
|
understandings, or agreements concerning use of licensed material. For
|
||||||
|
the avoidance of doubt, this paragraph does not form part of the
|
||||||
|
public licenses.
|
||||||
|
|
||||||
|
Creative Commons may be contacted at creativecommons.org.
|
||||||
|
|
||||||
126
LLaMa2_LICENSE
Normal file
126
LLaMa2_LICENSE
Normal file
@@ -0,0 +1,126 @@
|
|||||||
|
LLAMA 2 COMMUNITY LICENSE AGREEMENT
|
||||||
|
Llama 2 Version Release Date: July 18, 2023
|
||||||
|
|
||||||
|
"Agreement" means the terms and conditions for use, reproduction, distribution and
|
||||||
|
modification of the Llama Materials set forth herein.
|
||||||
|
|
||||||
|
"Documentation" means the specifications, manuals and documentation
|
||||||
|
accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and-
|
||||||
|
libraries/llama-downloads/.
|
||||||
|
|
||||||
|
"Licensee" or "you" means you, or your employer or any other person or entity (if
|
||||||
|
you are entering into this Agreement on such person or entity's behalf), of the age
|
||||||
|
required under applicable laws, rules or regulations to provide legal consent and that
|
||||||
|
has legal authority to bind your employer or such other person or entity if you are
|
||||||
|
entering in this Agreement on their behalf.
|
||||||
|
|
||||||
|
"Llama 2" means the foundational large language models and software and
|
||||||
|
algorithms, including machine-learning model code, trained model weights,
|
||||||
|
inference-enabling code, training-enabling code, fine-tuning enabling code and other
|
||||||
|
elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-
|
||||||
|
libraries/llama-downloads/.
|
||||||
|
|
||||||
|
"Llama Materials" means, collectively, Meta's proprietary Llama 2 and
|
||||||
|
Documentation (and any portion thereof) made available under this Agreement.
|
||||||
|
|
||||||
|
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you
|
||||||
|
are an entity, your principal place of business is in the EEA or Switzerland) and Meta
|
||||||
|
Platforms, Inc. (if you are located outside of the EEA or Switzerland).
|
||||||
|
|
||||||
|
By clicking "I Accept" below or by using or distributing any portion or element of the
|
||||||
|
Llama Materials, you agree to be bound by this Agreement.
|
||||||
|
|
||||||
|
1. License Rights and Redistribution.
|
||||||
|
|
||||||
|
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-
|
||||||
|
transferable and royalty-free limited license under Meta's intellectual property or
|
||||||
|
other rights owned by Meta embodied in the Llama Materials to use, reproduce,
|
||||||
|
distribute, copy, create derivative works of, and make modifications to the Llama
|
||||||
|
Materials.
|
||||||
|
|
||||||
|
b. Redistribution and Use.
|
||||||
|
|
||||||
|
i. If you distribute or make the Llama Materials, or any derivative works
|
||||||
|
thereof, available to a third party, you shall provide a copy of this Agreement to such
|
||||||
|
third party.
|
||||||
|
ii. If you receive Llama Materials, or any derivative works thereof, from
|
||||||
|
a Licensee as part of an integrated end user product, then Section 2 of this
|
||||||
|
Agreement will not apply to you.
|
||||||
|
|
||||||
|
iii. You must retain in all copies of the Llama Materials that you
|
||||||
|
distribute the following attribution notice within a "Notice" text file distributed as a
|
||||||
|
part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License,
|
||||||
|
Copyright (c) Meta Platforms, Inc. All Rights Reserved."
|
||||||
|
|
||||||
|
iv. Your use of the Llama Materials must comply with applicable laws
|
||||||
|
and regulations (including trade compliance laws and regulations) and adhere to the
|
||||||
|
Acceptable Use Policy for the Llama Materials (available at
|
||||||
|
https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into
|
||||||
|
this Agreement.
|
||||||
|
|
||||||
|
v. You will not use the Llama Materials or any output or results of the
|
||||||
|
Llama Materials to improve any other large language model (excluding Llama 2 or
|
||||||
|
derivative works thereof).
|
||||||
|
|
||||||
|
2. Additional Commercial Terms. If, on the Llama 2 version release date, the
|
||||||
|
monthly active users of the products or services made available by or for Licensee,
|
||||||
|
or Licensee's affiliates, is greater than 700 million monthly active users in the
|
||||||
|
preceding calendar month, you must request a license from Meta, which Meta may
|
||||||
|
grant to you in its sole discretion, and you are not authorized to exercise any of the
|
||||||
|
rights under this Agreement unless or until Meta otherwise expressly grants you
|
||||||
|
such rights.
|
||||||
|
|
||||||
|
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE
|
||||||
|
LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE
|
||||||
|
PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
|
||||||
|
EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY
|
||||||
|
WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR
|
||||||
|
FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
|
||||||
|
FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING
|
||||||
|
THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
|
||||||
|
USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
|
||||||
|
|
||||||
|
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE
|
||||||
|
LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT,
|
||||||
|
NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS
|
||||||
|
AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL,
|
||||||
|
CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
|
||||||
|
IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF
|
||||||
|
ANY OF THE FOREGOING.
|
||||||
|
|
||||||
|
5. Intellectual Property.
|
||||||
|
|
||||||
|
a. No trademark licenses are granted under this Agreement, and in
|
||||||
|
connection with the Llama Materials, neither Meta nor Licensee may use any name
|
||||||
|
or mark owned by or associated with the other or any of its affiliates, except as
|
||||||
|
required for reasonable and customary use in describing and redistributing the
|
||||||
|
Llama Materials.
|
||||||
|
|
||||||
|
b. Subject to Meta's ownership of Llama Materials and derivatives made by or
|
||||||
|
for Meta, with respect to any derivative works and modifications of the Llama
|
||||||
|
Materials that are made by you, as between you and Meta, you are and will be the
|
||||||
|
owner of such derivative works and modifications.
|
||||||
|
|
||||||
|
c. If you institute litigation or other proceedings against Meta or any entity
|
||||||
|
(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama
|
||||||
|
Materials or Llama 2 outputs or results, or any portion of any of the foregoing,
|
||||||
|
constitutes an infringement of intellectual property or other rights owned or licensable
|
||||||
|
by you, then any licenses granted to you under this Agreement shall terminate as of
|
||||||
|
the date such litigation or claim is filed or instituted. You will indemnify and hold
|
||||||
|
harmless Meta from and against any claim by any third party arising out of or related
|
||||||
|
to your use or distribution of the Llama Materials.
|
||||||
|
|
||||||
|
6. Term and Termination. The term of this Agreement will commence upon your
|
||||||
|
acceptance of this Agreement or access to the Llama Materials and will continue in
|
||||||
|
full force and effect until terminated in accordance with the terms and conditions
|
||||||
|
herein. Meta may terminate this Agreement if you are in breach of any term or
|
||||||
|
condition of this Agreement. Upon termination of this Agreement, you shall delete
|
||||||
|
and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the
|
||||||
|
termination of this Agreement.
|
||||||
|
|
||||||
|
7. Governing Law and Jurisdiction. This Agreement will be governed and
|
||||||
|
construed under the laws of the State of California without regard to choice of law
|
||||||
|
principles, and the UN Convention on Contracts for the International Sale of Goods
|
||||||
|
does not apply to this Agreement. The courts of California shall have exclusive
|
||||||
|
jurisdiction of any dispute arising out of this Agreement.
|
||||||
|
|
||||||
BIN
PersianMind.jpg
Normal file
BIN
PersianMind.jpg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 86 KiB |
151
README.md
Normal file
151
README.md
Normal file
@@ -0,0 +1,151 @@
|
|||||||
|
---
|
||||||
|
license: cc-by-nc-sa-4.0
|
||||||
|
language:
|
||||||
|
- multilingual
|
||||||
|
- fa
|
||||||
|
- en
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- text-generation-inference
|
||||||
|
inference: false
|
||||||
|
metrics:
|
||||||
|
- bleu
|
||||||
|
- comet
|
||||||
|
- accuracy
|
||||||
|
- perplexity
|
||||||
|
- spearmanr
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
co2_eq_emissions:
|
||||||
|
emissions: 232380
|
||||||
|
source: "PersianMind: A Cross-Lingual Persian-English Large Language Model. https://arxiv.org/abs/2401.06466"
|
||||||
|
training_type: "fine-tuning"
|
||||||
|
hardware_used: "4 RTX3090 24GB GPUs"
|
||||||
|
geographical_location: "Tehran, Iran"
|
||||||
|
---
|
||||||
|
|
||||||
|
<p align="center">
|
||||||
|
<img src="PersianMind.jpg" alt="PersianMind logo" width=200/>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
|
||||||
|
# <span style="font-variant:small-caps;">PersianMind</span>
|
||||||
|
|
||||||
|
<span style="font-variant:small-caps;">PersianMind</span> is a cross-lingual Persian-English large language model.
|
||||||
|
The model achieves state-of-the-art results on Persian subset of the [<span style="font-variant:small-caps;">Belebele</span>](https://github.com/facebookresearch/belebele) benchmark
|
||||||
|
and the [ParsiNLU multiple-choice QA](https://github.com/persiannlp/parsinlu) task.
|
||||||
|
It also attains performance comparable to GPT-3.5-turbo in a Persian reading comprehension task.
|
||||||
|
|
||||||
|
## Model Description
|
||||||
|
|
||||||
|
- **Developed by:** [Pedram Rostami](mailto:pedram.rostami@ut.ac.ir), [Ali Salemi](mailto:alisalemi@ut.ac.ir), and [Mohammad Javad Dousti](mailto:mjdousti@ut.ac.ir)
|
||||||
|
- **Model type:** Language model
|
||||||
|
- **Languages:** English and Persian
|
||||||
|
- **License:** [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) (non-commercial use only.)
|
||||||
|
|
||||||
|
## How to Get Started with the Model
|
||||||
|
|
||||||
|
Use the code below to get started with the model.
|
||||||
|
Note that you need to install <code><b>sentencepiece</b></code> and <code><b>accelerate</b></code> libraries along with <code><b>PyTorch</b></code> and <code><b>🤗Transformers</b></code> to run this code.
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||||
|
import torch
|
||||||
|
|
||||||
|
device = "cuda" if torch.cuda.is_available() else "cpu"
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"universitytehran/PersianMind-v1.0",
|
||||||
|
torch_dtype=torch.bfloat16,
|
||||||
|
low_cpu_mem_usage=True,
|
||||||
|
device_map={"": device},
|
||||||
|
)
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(
|
||||||
|
"universitytehran/PersianMind-v1.0",
|
||||||
|
)
|
||||||
|
|
||||||
|
TEMPLATE = "{context}\nYou: {prompt}\nPersianMind: "
|
||||||
|
CONTEXT = "This is a conversation with PersianMind. It is an artificial intelligence model designed by a team of " \
|
||||||
|
"NLP experts at the University of Tehran to help you with various tasks such as answering questions, " \
|
||||||
|
"providing recommendations, and helping with decision making. You can ask it anything you want and " \
|
||||||
|
"it will do its best to give you accurate and relevant information."
|
||||||
|
PROMPT = "در مورد هوش مصنوعی توضیح بده."
|
||||||
|
|
||||||
|
model_input = TEMPLATE.format(context=CONTEXT, prompt=PROMPT)
|
||||||
|
input_tokens = tokenizer(model_input, return_tensors="pt")
|
||||||
|
input_tokens = input_tokens.to(device)
|
||||||
|
generate_ids = model.generate(**input_tokens, max_new_tokens=512, do_sample=False, repetition_penalty=1.1)
|
||||||
|
model_output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
|
||||||
|
|
||||||
|
print(model_output[len(model_input):])
|
||||||
|
```
|
||||||
|
|
||||||
|
### How to Quantize the Model
|
||||||
|
|
||||||
|
Quantized models can be run on resource-constrained devices.
|
||||||
|
To quantize the model, you should install the <code><b>bitsandbytes</b></code> library.
|
||||||
|
In order to quantize the model in 8-bit (`INT8`), use the code below.
|
||||||
|
|
||||||
|
```python
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"universitytehran/PersianMind-v1.0",
|
||||||
|
device_map="auto",
|
||||||
|
low_cpu_mem_usage=True,
|
||||||
|
load_in_8bit=True
|
||||||
|
)
|
||||||
|
```
|
||||||
|
|
||||||
|
Alternatively, you can quantize the model in 4-bit (`NormalFloat4`) with the following code.
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import BitsAndBytesConfig
|
||||||
|
|
||||||
|
quantization_config = BitsAndBytesConfig(
|
||||||
|
load_in_4bit=True,
|
||||||
|
bnb_4bit_use_double_quant=True,
|
||||||
|
bnb_4bit_quant_type="nf4",
|
||||||
|
)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"universitytehran/PersianMind-v1.0",
|
||||||
|
quantization_config=quantization_config,
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
```
|
||||||
|
|
||||||
|
### Evaluating Quantized Models
|
||||||
|
|
||||||
|
| Model | <span style="font-variant:small-caps;">Belebele</span> (Persian) | Fa→En Translation<br>(<span style="font-variant:small-caps;">Comet</span>) | En→Fa Translation<br>(<span style="font-variant:small-caps;">Comet</span>) | Model Size | Tokens/sec |
|
||||||
|
| :----------------------------------------------------------------: | :--------------------------------------------------------------: | :------------------------------------------------------------------------: | :------------------------------------------------------------------------: | :--------: | :--------: |
|
||||||
|
| <span style="font-variant:small-caps;">PersianMind</span> (`BF16`) | 73.9 | 83.61 | 79.44 | 13.7G | 25.35 |
|
||||||
|
| <span style="font-variant:small-caps;">PersianMind</span> (`INT8`) | 73.7 | 82.32 | 78.61 | 7.2G | 11.36 |
|
||||||
|
| <span style="font-variant:small-caps;">PersianMind</span> (`NF4`) | 70.2 | 82.07 | 80.36 | 3.9G | 24.36 |
|
||||||
|
|
||||||
|
We evaluated quantized models in various tasks against the original model.
|
||||||
|
Specifically, we evaluated all models using the reading comprehension multiple-choice
|
||||||
|
question-answering benchmark of [<span style="font-variant:small-caps;">Belebele</span>](https://github.com/facebookresearch/belebele) (Persian subset) and reported the accuracy of each model.
|
||||||
|
Additionally, we evaluated our models for Persian-to-English and English-to-Persian translation tasks.
|
||||||
|
For this, we utilized the Persian-English subset of the [<span style="font-variant:small-caps;">Flores</span>-200](https://github.com/facebookresearch/flores/tree/main/flores200) dataset and
|
||||||
|
reported our results using the <span style="font-variant:small-caps;">Comet</span> metric.
|
||||||
|
Furthermore, we calculated the average number of generated tokens per second by each model during running the translation tasks.
|
||||||
|
To understand resource efficiency, we measured the memory usage of each model by employing the `get_memory_footprint()` function.
|
||||||
|
|
||||||
|
## License
|
||||||
|
<span style="font-variant:small-caps;">PersianMind</span> is subject to Meta's [LLaMa2 Community License](https://raw.githubusercontent.com/facebookresearch/llama/main/LICENSE).
|
||||||
|
It is further licensed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/), which allows non-commercial use of the model.
|
||||||
|
Commercial use of this model requires written agreement which must be obtained from the copyright holders who are listed as developers in this page.
|
||||||
|
If you suspect any violations, please reach out to us.
|
||||||
|
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
If you find this model helpful, please ensure to cite the following paper.
|
||||||
|
|
||||||
|
**BibTeX:**
|
||||||
|
```bibtex
|
||||||
|
@misc{persianmind,
|
||||||
|
title={{PersianMind: A Cross-Lingual Persian-English Large Language Model}},
|
||||||
|
author={Rostami, Pedram and Salemi, Ali and Dousti, Mohammad Javad},
|
||||||
|
year={2024}
|
||||||
|
eprint={2401.06466},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL}
|
||||||
|
}
|
||||||
|
```
|
||||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
{
|
||||||
|
"[PAD]": 41509
|
||||||
|
}
|
||||||
22
config.json
Normal file
22
config.json
Normal file
@@ -0,0 +1,22 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 11008,
|
||||||
|
"max_position_embeddings": 2048,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.28.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 41510
|
||||||
|
}
|
||||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"max_new_tokens": 512,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"repetition_penalty": 1.1,
|
||||||
|
"temperature": 0.4,
|
||||||
|
"transformers_version": "4.38.2"
|
||||||
|
}
|
||||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:46cb45c0da81c10256d4bfb09c144e9f7fae1475ba71621c34c2cf415fb2865e
|
||||||
|
size 9964290808
|
||||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:313419e66594e4a58532c39c87821e30e03de38b27ed85e97dbdd7e853bf1624
|
||||||
|
size 3668397608
|
||||||
330
model.safetensors.index.json
Normal file
330
model.safetensors.index.json
Normal file
@@ -0,0 +1,330 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 13632651264
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
3
pytorch_model-00001-of-00002.bin
Normal file
3
pytorch_model-00001-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:87a0f98e464fc5cb5e9c98947ed224fc5183fdc6e577bc569cb00c2057fce955
|
||||||
|
size 9964345517
|
||||||
3
pytorch_model-00002-of-00002.bin
Normal file
3
pytorch_model-00002-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aed32d525b28a16667d92ecb28d2e81d786657e91d9b3f95b55716866645b3d7
|
||||||
|
size 3668416393
|
||||||
330
pytorch_model.bin.index.json
Normal file
330
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,330 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 13632651264
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
||||||
|
}
|
||||||
|
}
|
||||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "[PAD]",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
120802
tokenizer.json
Normal file
120802
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c432aa35f6a9296b8b1ff2cfae92d1818b45348a284d133a1046e46458e4dc3b
|
||||||
|
size 688077
|
||||||
50
tokenizer_config.json
Normal file
50
tokenizer_config.json
Normal file
@@ -0,0 +1,50 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": true,
|
||||||
|
"add_eos_token": false,
|
||||||
|
"add_prefix_space": true,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"0": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"1": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"2": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"41509": {
|
||||||
|
"content": "[PAD]",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"bos_token": "<s>",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "</s>",
|
||||||
|
"legacy": true,
|
||||||
|
"model_max_length": 1000000000000000019884624838656,
|
||||||
|
"pad_token": "[PAD]",
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"spaces_between_special_tokens": false,
|
||||||
|
"tokenizer_class": "LlamaTokenizer",
|
||||||
|
"unk_token": "<unk>",
|
||||||
|
"use_default_system_prompt": false
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user