初始化项目，由ModelHub XC社区提供模型
Model: magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-v2-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
48
.gitattributes
vendored
Normal file
48
.gitattributes
vendored
Normal file
@@ -0,0 +1,48 @@
|
||||
*.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
|
||||
Model-LM-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-LM-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-LM-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-LM-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-LM-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-LM-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-LM-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-LM-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-MQ-Q4_K_M_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-MQ-Q5_K_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Model-MQ-Q6_K_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
imatrix.dat filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
202
LICENSE
Normal file
202
LICENSE
Normal file
@@ -0,0 +1,202 @@
|
||||
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Copyright 2024 Alibaba Cloud
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
3
Model-LM-IQ2_S.gguf
Normal file
3
Model-LM-IQ2_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7b02b1a6ff087400e155331f96d53561aaf2762949c06a1fd0e3c0f10bc4cedc
|
||||
size 1417301696
|
||||
3
Model-LM-IQ2_XXS.gguf
Normal file
3
Model-LM-IQ2_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7aee9ae12eb82ada178bde3da4e58f151eb9f6b386baf4245e075cdd1a05c0f1
|
||||
size 1246621376
|
||||
3
Model-LM-IQ3_S.gguf
Normal file
3
Model-LM-IQ3_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:259c2000e9715623934638409b46c86a53e5f00584de02373fefe82d12e43b2f
|
||||
size 1899531456
|
||||
3
Model-LM-IQ3_XXS.gguf
Normal file
3
Model-LM-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1f1cf51402f25b24fdfd1159a8238ef2c43d732385e0dc05e3a62f0a6f0d2543
|
||||
size 1670188736
|
||||
3
Model-LM-IQ4_XS.gguf
Normal file
3
Model-LM-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:87469887828d9623bd56313d27df08125501f36bda982bb8dd3ee241661c430e
|
||||
size 2270751936
|
||||
3
Model-LM-Q4_K_S.gguf
Normal file
3
Model-LM-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:87acc0183e145e46834724b75d989f241e7d3088cd2ec17a6d8992b5035c1135
|
||||
size 2383310016
|
||||
3
Model-LM-Q6_K.gguf
Normal file
3
Model-LM-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bde91ab40b08cbddd3e87088f289171b44c51abf5809ecb449dc3bae6b50ed24
|
||||
size 3306261696
|
||||
3
Model-LM-Q8_0.gguf
Normal file
3
Model-LM-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9602503ed33808ae891c1c8ca9b0da58f7d04ac833ba3900161b34caacf39cac
|
||||
size 4280405696
|
||||
3
Model-MQ-Q4_K_M_1.gguf
Normal file
3
Model-MQ-Q4_K_M_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d7e83031e119a401d036372532dbbfac1e2c14bca3d87ca3055bc4fabd590081
|
||||
size 2618576576
|
||||
3
Model-MQ-Q5_K_1.gguf
Normal file
3
Model-MQ-Q5_K_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3543c5e6c893befe3bfba650beddd74e06c799e7b52c7b1ff056e0c0488b8c0f
|
||||
size 3090906816
|
||||
3
Model-MQ-Q6_K_1.gguf
Normal file
3
Model-MQ-Q6_K_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:35eb65b2647afcef8a85379a31d6321bddd5ecbef5f54bf4c13184ce64c23d47
|
||||
size 3846147776
|
||||
94
README.md
Normal file
94
README.md
Normal file
@@ -0,0 +1,94 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- gguf
|
||||
- text-generation
|
||||
- quantized
|
||||
- cpu
|
||||
- gpu
|
||||
- magicquant
|
||||
- magic_quant
|
||||
- qwen3
|
||||
- qwen
|
||||
- conversational
|
||||
base_model:
|
||||
- unsloth/Qwen3-4B-Instruct-2507
|
||||
---
|
||||
|
||||
# MagicQuant Hybrids (v2.0) - Qwen3-4B-Instruct-2507-unsloth
|
||||
|
||||
MagicQuant is **not** a quantization technique by itself.
|
||||
|
||||
It is a search, judging, and hybrid-discovery system that learns from baseline families such as llama.cpp and external/custom baseline sources, then uses isolated samples, rank-safe prediction, and real benchmarking to keep the practical survivors.
|
||||
|
||||
Sometimes a hybrid beats a pure baseline. Sometimes it does not. MagicQuant finds non linear good trades to discover potential better hybrids, good sub spaces between anchor baselines and more.
|
||||
|
||||
Read more on the [MagicQuant Wiki Here](https://github.com/magiccodingman/MagicQuant-Wiki).
|
||||
|
||||
## Final surviving downloadable outputs
|
||||
|
||||
| Name | Provider | Quant Family | KLD | Size (GB) | Download |
|
||||
|---|---|---|---:|---:|---|
|
||||
| LM-Q8_0 | llama.cpp | Q8_0 | 0.001339 | 3.99 | [Link](./../../resolve/main/Model-LM-Q8_0.gguf?download=true) |
|
||||
| MQ-Q6_K_1 | MagicQuant | Q6_K | 0.001817 | 3.58 | [Link](./../../resolve/main/Model-MQ-Q6_K_1.gguf?download=true) |
|
||||
| UD-Q6_K_XL | Unsloth | UD-Q6_K_XL | 0.002111 | 3.41 | [Link](https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF) |
|
||||
| LM-Q6_K | llama.cpp | Q6_K | 0.004640 | 3.08 | [Link](./../../resolve/main/Model-LM-Q6_K.gguf?download=true) |
|
||||
| [<u>MQ-Q5_K_1</u>](#winner-notes "Replaced: MQ-Q5_K") | MagicQuant | Q5_K | 0.006632 | 2.88 | [Link](./../../resolve/main/Model-MQ-Q5_K_1.gguf?download=true) |
|
||||
| [<u>UD-Q5_K_XL</u>](#winner-notes "Replaced: LM-Q5_K, LM-Q5_K_S") | Unsloth | UD-Q5_K_XL | 0.009839 | 2.73 | [Link](https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF) |
|
||||
| [<u>MQ-Q4_K_M_1</u>](#winner-notes "Replaced: MQ-Q4_K_M, UD-Q4_K_XL, LM-Q4_K_M + 1 more") | MagicQuant | Q4_K_M | 0.020346 | 2.44 | [Link](./../../resolve/main/Model-MQ-Q4_K_M_1.gguf?download=true) |
|
||||
| [<u>LM-Q4_K_S</u>](#winner-notes "Replaced: LM-IQ4_NL") | llama.cpp | Q4_K_S | 0.029803 | 2.22 | [Link](./../../resolve/main/Model-LM-Q4_K_S.gguf?download=true) |
|
||||
| LM-IQ4_XS | llama.cpp | IQ4_XS | 0.031300 | 2.11 | [Link](./../../resolve/main/Model-LM-IQ4_XS.gguf?download=true) |
|
||||
| UD-Q3_K_XL | Unsloth | UD-Q3_K_XL | 0.072278 | 1.98 | [Link](https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF) |
|
||||
| [<u>LM-IQ3_S</u>](#winner-notes "Replaced: LM-IQ3_XS") | llama.cpp | IQ3_S | 0.091992 | 1.77 | [Link](./../../resolve/main/Model-LM-IQ3_S.gguf?download=true) |
|
||||
| LM-IQ3_XXS | llama.cpp | IQ3_XXS | 0.190404 | 1.56 | [Link](./../../resolve/main/Model-LM-IQ3_XXS.gguf?download=true) |
|
||||
| [<u>LM-IQ2_S</u>](#winner-notes "Replaced: LM-IQ2_XS") | llama.cpp | IQ2_S | 0.431128 | 1.32 | [Link](./../../resolve/main/Model-LM-IQ2_S.gguf?download=true) |
|
||||
| LM-IQ2_XXS | llama.cpp | IQ2_XXS | 0.938021 | 1.16 | [Link](./../../resolve/main/Model-LM-IQ2_XXS.gguf?download=true) |
|
||||
|
||||
---
|
||||
|
||||
## Release metadata
|
||||
|
||||
- [Final survivor metrics](./../../resolve/main/magicquant.final-survivors.json?download=true) — full file names, KLD, PPL delta %, byte sizes, download targets, and replacement lineage. PPL delta % is measured against the native/reference PPL when available; negative is better and larger positive values are worse.
|
||||
- [Hybrid tensor map](./../../resolve/main/magicquant.hybrid-map.json?download=true) — tensor-group assignments and effective-state details for MagicQuant hybrid GGUFs.
|
||||
- [Replacement details](./../../resolve/main/magicquant.replacements.json?download=true) — structured details for baselines or anchors removed from the final download table, including reason codes, KLD deltas, PPL delta %, and size deltas.
|
||||
|
||||
---
|
||||
|
||||
<details>
|
||||
<summary>Replacement reason codes</summary>
|
||||
|
||||
- `STRICT_DOMINANCE` — the winner was no larger and had lower real KLD than the removed anchor.
|
||||
- `NEAR_BASELINE_PREMIUM` — the winner used only the configured near-baseline size premium and beat the real linear KLD trade line.
|
||||
- `INTERIOR_DISCOVERY` — the winner was selected as a useful interior point inside a size/KLD gap between anchors.
|
||||
- `SPACING_COLLAPSE` — two candidates were too close in practical output space, so the stronger one was kept.
|
||||
- `FINAL_DOMINANCE` — a later validated survivor dominated this artifact in final real benchmark comparison.
|
||||
|
||||
<a id="winner-notes"></a>
|
||||
Underlined names in the table replaced or ultimately inherited the replacement of another artifact. Hover the name for the short replacement summary, or inspect `magicquant.replacements.json` for exact KLD/PPL/size deltas.
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
<details>
|
||||
<summary>Provider credits</summary>
|
||||
|
||||
- [llama.cpp](https://github.com/ggml-org/llama.cpp) — Baseline quantization formats and llama.cpp tooling.
|
||||
- [Unsloth](https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF) — External learned baseline source (UD).
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>Warning</summary>
|
||||
|
||||
External/custom baselines are normalized into MagicQuant's controlled comparison flow. MagicQuant may rebuild a learned baseline under native-source / MagicQuant-controlled conditions, including its own imatrix handling, so hybrids can be judged on a more equal footing. That does **not** mean MagicQuant proved the original upstream artifact or upstream imatrix was worse. These comparisons exist for internal hybrid-search consistency, not as a universal judgment of the original creator's exact release artifact.
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Support
|
||||
|
||||
I’m a solo developer working full time for myself to achieve my dream. I build open source code on the side. If you like any of my work, buying me a coffee is always appreciated. Otherwise, I hope you enjoy, maybe give me a star or something. Or just send me good vibes. Either way, thank you!
|
||||
|
||||
[Click here to see ways to support](https://sayou.biz/support) - BTC, Paypal, GitHub sponsors.
|
||||
86
chat_template.jinja
Normal file
86
chat_template.jinja
Normal file
@@ -0,0 +1,86 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
69
config.json
Normal file
69
config.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151654,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.55.0",
|
||||
"unsloth_fixed": true,
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_length": 262144,
|
||||
"pad_token_id": 151654,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.55.0"
|
||||
}
|
||||
3
imatrix.dat
Normal file
3
imatrix.dat
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f25f8832e97ee9c4526820f8e011a189808ac8c7e1a7cd2f058c12e43ee8ef5e
|
||||
size 3872704
|
||||
408
magicquant.final-survivors.json
Normal file
408
magicquant.final-survivors.json
Normal file
@@ -0,0 +1,408 @@
|
||||
[
|
||||
{
|
||||
"key": "0:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-Q8_0.gguf",
|
||||
"displayName": "Model-LM-Q8_0",
|
||||
"shortName": "LM-Q8_0",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "Q8_0",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-LM-Q8_0.gguf?download=true",
|
||||
"kld": 0.001339,
|
||||
"ppl": 8.883911,
|
||||
"pplDeltaPercent": 0.0035008329956318406,
|
||||
"sizeBytes": 4280405696,
|
||||
"sizeGiB": 3.9864384531974792,
|
||||
"expectedSizeBytes": 4280405696,
|
||||
"actualSizeBytes": 4280405696,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": []
|
||||
},
|
||||
{
|
||||
"key": "0:1:0:1:1:1:2:1:0:0",
|
||||
"fileName": "Model-MQ-Q6_K_1.gguf",
|
||||
"displayName": "Model-MQ-Q6_K_1",
|
||||
"shortName": "MQ-Q6_K_1",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q6_K",
|
||||
"isHybrid": true,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-MQ-Q6_K_1.gguf?download=true",
|
||||
"kld": 0.001817,
|
||||
"ppl": 8.895891,
|
||||
"pplDeltaPercent": 0.13835607186277143,
|
||||
"sizeBytes": 3846147776,
|
||||
"sizeGiB": 3.5820042490959167,
|
||||
"expectedSizeBytes": 3846147776,
|
||||
"actualSizeBytes": 3846147776,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": []
|
||||
},
|
||||
{
|
||||
"key": "102:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-UD-Q6_K_XL.gguf",
|
||||
"displayName": "Model-UD-Q6_K_XL",
|
||||
"shortName": "UD-Q6_K_XL",
|
||||
"provider": "Unsloth",
|
||||
"quantFamily": "UD-Q6_K_XL",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": true,
|
||||
"downloadTarget": "https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF",
|
||||
"kld": 0.002111,
|
||||
"ppl": 8.908457,
|
||||
"pplDeltaPercent": 0.27980773560269256,
|
||||
"sizeBytes": 3658223296,
|
||||
"sizeGiB": 3.4069859385490417,
|
||||
"expectedSizeBytes": 3658223296,
|
||||
"actualSizeBytes": null,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": []
|
||||
},
|
||||
{
|
||||
"key": "1:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-Q6_K.gguf",
|
||||
"displayName": "Model-LM-Q6_K",
|
||||
"shortName": "LM-Q6_K",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "Q6_K",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-LM-Q6_K.gguf?download=true",
|
||||
"kld": 0.00464,
|
||||
"ppl": 8.872275,
|
||||
"pplDeltaPercent": -0.12748210185059394,
|
||||
"sizeBytes": 3306261696,
|
||||
"sizeGiB": 3.0791961550712585,
|
||||
"expectedSizeBytes": 3306261696,
|
||||
"actualSizeBytes": 3306261696,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": []
|
||||
},
|
||||
{
|
||||
"key": "0:1:0:2:1:2:102:14:0:0",
|
||||
"fileName": "Model-MQ-Q5_K_1.gguf",
|
||||
"displayName": "Model-MQ-Q5_K_1",
|
||||
"shortName": "MQ-Q5_K_1",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q5_K",
|
||||
"isHybrid": true,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-MQ-Q5_K_1.gguf?download=true",
|
||||
"kld": 0.006632,
|
||||
"ppl": 8.900069,
|
||||
"pplDeltaPercent": 0.1853865550002334,
|
||||
"sizeBytes": 3090906816,
|
||||
"sizeGiB": 2.878631293773651,
|
||||
"expectedSizeBytes": 3090906816,
|
||||
"actualSizeBytes": 3090906816,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": [
|
||||
{
|
||||
"key": "0:1:0:3:1:2:102:14:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-Q8_0-D-Q5_K_S-E-Q8_0-K-Q8_0-O-Q6_K-Q-Q5_K-U-UD-Q5_K_XL",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-Q8_0-D-Q5_K_S-E-Q8_0-K-Q8_0-O-Q6_K-Q-Q5_K-U-UD-Q5_K_XL",
|
||||
"kld": 0.006925,
|
||||
"ppl": 8.901754,
|
||||
"pplDeltaPercent": 0.204354090683967,
|
||||
"sizeBytes": 3040771776,
|
||||
"sizeGiB": 2.831939399242401,
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reason": "meaningful spacing collapse; size gap below 91,013,530 bytes"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"key": "101:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-UD-Q5_K_XL.gguf",
|
||||
"displayName": "Model-UD-Q5_K_XL",
|
||||
"shortName": "UD-Q5_K_XL",
|
||||
"provider": "Unsloth",
|
||||
"quantFamily": "UD-Q5_K_XL",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": true,
|
||||
"downloadTarget": "https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF",
|
||||
"kld": 0.009839,
|
||||
"ppl": 8.923979,
|
||||
"pplDeltaPercent": 0.45453419784771626,
|
||||
"sizeBytes": 2930382016,
|
||||
"sizeGiB": 2.7291309237480164,
|
||||
"expectedSizeBytes": 2930382016,
|
||||
"actualSizeBytes": null,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": [
|
||||
{
|
||||
"key": "2:0:0:0:0:0:0:0:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-Q5_K",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-Q5_K",
|
||||
"kld": 0.009942,
|
||||
"ppl": 8.896878,
|
||||
"pplDeltaPercent": 0.14946643252735017,
|
||||
"sizeBytes": 2889514176,
|
||||
"sizeGiB": 2.691069781780243,
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reason": "meaningful spacing collapse; size gap below 91,013,530 bytes"
|
||||
},
|
||||
{
|
||||
"key": "13:0:0:0:0:0:0:0:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-Q5_K_S",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-Q5_K_S",
|
||||
"kld": 0.010808,
|
||||
"ppl": 8.919999,
|
||||
"pplDeltaPercent": 0.40973254086182603,
|
||||
"sizeBytes": 2823711936,
|
||||
"sizeGiB": 2.6297866702079773,
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reason": "meaningful spacing collapse; size gap below 91,013,530 bytes"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"key": "0:1:0:3:1:2:7:7:0:0",
|
||||
"fileName": "Model-MQ-Q4_K_M_1.gguf",
|
||||
"displayName": "Model-MQ-Q4_K_M_1",
|
||||
"shortName": "MQ-Q4_K_M_1",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q4_K_M",
|
||||
"isHybrid": true,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-MQ-Q4_K_M_1.gguf?download=true",
|
||||
"kld": 0.020346,
|
||||
"ppl": 8.95744,
|
||||
"pplDeltaPercent": 0.8311945607636608,
|
||||
"sizeBytes": 2618576576,
|
||||
"sizeGiB": 2.4387394785881042,
|
||||
"expectedSizeBytes": 2618576576,
|
||||
"actualSizeBytes": 2618576576,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": [
|
||||
{
|
||||
"key": "0:1:0:7:1:2:7:15:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-Q8_0-D-Q4_K_S-E-Q8_0-K-Q8_0-O-Q6_K-Q-IQ4_XS-U-IQ4_XS",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-Q8_0-D-Q4_K_S-E-Q8_0-K-Q8_0-O-Q6_K-Q-IQ4_XS-U-IQ4_XS",
|
||||
"kld": 0.021705,
|
||||
"ppl": 8.964544,
|
||||
"pplDeltaPercent": 0.9111621414741836,
|
||||
"sizeBytes": 2600062656,
|
||||
"sizeGiB": 2.4214970469474792,
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reason": "meaningful spacing collapse; size gap below 91,013,530 bytes"
|
||||
},
|
||||
{
|
||||
"key": "100:0:0:0:0:0:0:0:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-UD-Q4_K_XL",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-UD-Q4_K_XL",
|
||||
"kld": 0.022351,
|
||||
"ppl": 8.997353,
|
||||
"pplDeltaPercent": 1.2804831374668026,
|
||||
"sizeBytes": 2591284416,
|
||||
"sizeGiB": 2.4133216738700867,
|
||||
"reasonCode": "NEAR_BASELINE_PREMIUM",
|
||||
"reason": "near-baseline replacement within \u002B1% size premium"
|
||||
},
|
||||
{
|
||||
"key": "0:1:0:7:1:2:7:7:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-Q8_0-D-IQ4_XS-E-Q8_0-K-Q8_0-O-Q6_K-Q-IQ4_XS-U-IQ4_XS",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-Q8_0-D-IQ4_XS-E-Q8_0-K-Q8_0-O-Q6_K-Q-IQ4_XS-U-IQ4_XS",
|
||||
"kld": 0.023119,
|
||||
"ppl": 8.965156,
|
||||
"pplDeltaPercent": 0.9180512404881,
|
||||
"sizeBytes": 2559594176,
|
||||
"sizeGiB": 2.3838078379631042,
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reason": "meaningful spacing collapse; size gap below 91,013,530 bytes"
|
||||
},
|
||||
{
|
||||
"key": "3:0:0:0:0:0:0:0:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-Q4_K_M",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-Q4_K_M",
|
||||
"kld": 0.025432,
|
||||
"ppl": 9.030426,
|
||||
"pplDeltaPercent": 1.6527759016614976,
|
||||
"sizeBytes": 2497281216,
|
||||
"sizeGiB": 2.325774371623993,
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reason": "meaningful spacing collapse; size gap below 91,013,530 bytes"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"key": "14:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-Q4_K_S.gguf",
|
||||
"displayName": "Model-LM-Q4_K_S",
|
||||
"shortName": "LM-Q4_K_S",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "Q4_K_S",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-LM-Q4_K_S.gguf?download=true",
|
||||
"kld": 0.029803,
|
||||
"ppl": 9.010033,
|
||||
"pplDeltaPercent": 1.4232180647485306,
|
||||
"sizeBytes": 2383310016,
|
||||
"sizeGiB": 2.2196304202079773,
|
||||
"expectedSizeBytes": 2383310016,
|
||||
"actualSizeBytes": 2383310016,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": [
|
||||
{
|
||||
"key": "5:0:0:0:0:0:0:0:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-IQ4_NL",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-IQ4_NL",
|
||||
"kld": 0.030626,
|
||||
"ppl": 8.946429,
|
||||
"pplDeltaPercent": 0.7072470620018989,
|
||||
"sizeBytes": 2381343936,
|
||||
"sizeGiB": 2.2177993655204773,
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reason": "meaningful spacing collapse; size gap below 91,013,530 bytes"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"key": "6:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ4_XS.gguf",
|
||||
"displayName": "Model-LM-IQ4_XS",
|
||||
"shortName": "LM-IQ4_XS",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ4_XS",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-LM-IQ4_XS.gguf?download=true",
|
||||
"kld": 0.0313,
|
||||
"ppl": 8.961936,
|
||||
"pplDeltaPercent": 0.8818046737809018,
|
||||
"sizeBytes": 2270751936,
|
||||
"sizeGiB": 2.1148025393486023,
|
||||
"expectedSizeBytes": 2270751936,
|
||||
"actualSizeBytes": 2270751936,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": []
|
||||
},
|
||||
{
|
||||
"key": "103:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-UD-Q3_K_XL.gguf",
|
||||
"displayName": "Model-UD-Q3_K_XL",
|
||||
"shortName": "UD-Q3_K_XL",
|
||||
"provider": "Unsloth",
|
||||
"quantFamily": "UD-Q3_K_XL",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": true,
|
||||
"downloadTarget": "https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF",
|
||||
"kld": 0.072278,
|
||||
"ppl": 9.232857,
|
||||
"pplDeltaPercent": 3.9314804808861243,
|
||||
"sizeBytes": 2128385216,
|
||||
"sizeGiB": 1.9822131991386414,
|
||||
"expectedSizeBytes": 2128385216,
|
||||
"actualSizeBytes": null,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": []
|
||||
},
|
||||
{
|
||||
"key": "7:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ3_S.gguf",
|
||||
"displayName": "Model-LM-IQ3_S",
|
||||
"shortName": "LM-IQ3_S",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ3_S",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-LM-IQ3_S.gguf?download=true",
|
||||
"kld": 0.091992,
|
||||
"ppl": 9.349099,
|
||||
"pplDeltaPercent": 5.239981539015728,
|
||||
"sizeBytes": 1899531456,
|
||||
"sizeGiB": 1.7690765261650085,
|
||||
"expectedSizeBytes": 1899531456,
|
||||
"actualSizeBytes": 1899531456,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": [
|
||||
{
|
||||
"key": "8:0:0:0:0:0:0:0:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-IQ3_XS",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-IQ3_XS",
|
||||
"kld": 0.11761,
|
||||
"ppl": 9.485851,
|
||||
"pplDeltaPercent": 6.779357467693287,
|
||||
"sizeBytes": 1814375616,
|
||||
"sizeGiB": 1.6897689700126648,
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reason": "meaningful spacing collapse; size gap below 91,013,530 bytes"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"key": "9:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ3_XXS.gguf",
|
||||
"displayName": "Model-LM-IQ3_XXS",
|
||||
"shortName": "LM-IQ3_XXS",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ3_XXS",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-LM-IQ3_XXS.gguf?download=true",
|
||||
"kld": 0.190404,
|
||||
"ppl": 10.19284,
|
||||
"pplDeltaPercent": 14.737718942770957,
|
||||
"sizeBytes": 1670188736,
|
||||
"sizeGiB": 1.5554844737052917,
|
||||
"expectedSizeBytes": 1670188736,
|
||||
"actualSizeBytes": 1670188736,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": []
|
||||
},
|
||||
{
|
||||
"key": "10:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ2_S.gguf",
|
||||
"displayName": "Model-LM-IQ2_S",
|
||||
"shortName": "LM-IQ2_S",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ2_S",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-LM-IQ2_S.gguf?download=true",
|
||||
"kld": 0.431128,
|
||||
"ppl": 12.334448,
|
||||
"pplDeltaPercent": 38.84515286595525,
|
||||
"sizeBytes": 1417301696,
|
||||
"sizeGiB": 1.3199650645256042,
|
||||
"expectedSizeBytes": 1417301696,
|
||||
"actualSizeBytes": 1417301696,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": [
|
||||
{
|
||||
"key": "11:0:0:0:0:0:0:0:0:0",
|
||||
"shortName": "Qwen3-4B-Instruct-2507-unsloth-IQ2_XS",
|
||||
"internalDisplayName": "Qwen3-4B-Instruct-2507-unsloth-IQ2_XS",
|
||||
"kld": 0.529564,
|
||||
"ppl": 13.498521,
|
||||
"pplDeltaPercent": 51.94877076860733,
|
||||
"sizeBytes": 1354100416,
|
||||
"sizeGiB": 1.2611042857170105,
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reason": "meaningful spacing collapse; size gap below 91,013,530 bytes"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"key": "12:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ2_XXS.gguf",
|
||||
"displayName": "Model-LM-IQ2_XXS",
|
||||
"shortName": "LM-IQ2_XXS",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ2_XXS",
|
||||
"isHybrid": false,
|
||||
"isExternalReference": false,
|
||||
"downloadTarget": "./../../resolve/main/Model-LM-IQ2_XXS.gguf?download=true",
|
||||
"kld": 0.938021,
|
||||
"ppl": 19.44567,
|
||||
"pplDeltaPercent": 118.89402944752128,
|
||||
"sizeBytes": 1246621376,
|
||||
"sizeGiB": 1.1610066294670105,
|
||||
"expectedSizeBytes": 1246621376,
|
||||
"actualSizeBytes": 1246621376,
|
||||
"usedImatrix": true,
|
||||
"replacedArtifacts": []
|
||||
}
|
||||
]
|
||||
68
magicquant.hybrid-map.json
Normal file
68
magicquant.hybrid-map.json
Normal file
@@ -0,0 +1,68 @@
|
||||
[
|
||||
{
|
||||
"ExportedFileName": "Model-MQ-Q6_K_1.gguf",
|
||||
"DisplayName": "Model-MQ-Q6_K_1",
|
||||
"ProviderSource": "MagicQuant",
|
||||
"BaselineFamily": "Q6_K",
|
||||
"OriginalReferenceBaseline": "Q8_0",
|
||||
"TensorGroups": {
|
||||
"embeddings": "Q8_0",
|
||||
"attn_q": "Q8_0",
|
||||
"attn_kv": "Q8_0",
|
||||
"attn_output": "Q8_0",
|
||||
"ffn_up_gate": "Q6_K",
|
||||
"ffn_down": "Q8_0"
|
||||
},
|
||||
"EffectiveQuantStateKey": "base=standard:q8_0|attn_kv=effective:Q8_0|attn_output=effective:Q8_0|attn_q=effective:Q8_0|embeddings=effective:Q8_0|ffn_down=effective:Q8_0|ffn_up_gate=effective:Q6_K|lm_head=base|moe_experts=base|moe_router=base",
|
||||
"HasUnknownMappings": false,
|
||||
"Warnings": [],
|
||||
"UsedImatrix": true,
|
||||
"ExpectedSizeBytes": 3846147776,
|
||||
"ActualSizeBytes": 3846147776,
|
||||
"OriginalExternalSource": null
|
||||
},
|
||||
{
|
||||
"ExportedFileName": "Model-MQ-Q5_K_1.gguf",
|
||||
"DisplayName": "Model-MQ-Q5_K_1",
|
||||
"ProviderSource": "MagicQuant",
|
||||
"BaselineFamily": "Q5_K",
|
||||
"OriginalReferenceBaseline": "Q8_0",
|
||||
"TensorGroups": {
|
||||
"embeddings": "Q8_0",
|
||||
"attn_q": "Q6_K",
|
||||
"attn_kv": "Q8_0",
|
||||
"attn_output": "Q6_K",
|
||||
"ffn_up_gate": "UD-Q5_K_XL",
|
||||
"ffn_down": "Q5_K_S"
|
||||
},
|
||||
"EffectiveQuantStateKey": "base=standard:q8_0|attn_kv=effective:Q8_0|attn_output=effective:Q6_K|attn_q=effective:Q6_K|embeddings=effective:Q8_0|ffn_down=effective:Q5_K|ffn_up_gate=effective-map:0f95b03efeed21325cd9db1482ad29f6b4e758cb7c069d8a7e3e7dd34756d17f|lm_head=base|moe_experts=base|moe_router=base",
|
||||
"HasUnknownMappings": false,
|
||||
"Warnings": [],
|
||||
"UsedImatrix": true,
|
||||
"ExpectedSizeBytes": 3090906816,
|
||||
"ActualSizeBytes": 3090906816,
|
||||
"OriginalExternalSource": null
|
||||
},
|
||||
{
|
||||
"ExportedFileName": "Model-MQ-Q4_K_M_1.gguf",
|
||||
"DisplayName": "Model-MQ-Q4_K_M_1",
|
||||
"ProviderSource": "MagicQuant",
|
||||
"BaselineFamily": "Q4_K_M",
|
||||
"OriginalReferenceBaseline": "Q8_0",
|
||||
"TensorGroups": {
|
||||
"embeddings": "Q8_0",
|
||||
"attn_q": "Q5_K",
|
||||
"attn_kv": "Q8_0",
|
||||
"attn_output": "Q6_K",
|
||||
"ffn_up_gate": "IQ4_XS",
|
||||
"ffn_down": "IQ4_XS"
|
||||
},
|
||||
"EffectiveQuantStateKey": "base=standard:q8_0|attn_kv=effective:Q8_0|attn_output=effective:Q6_K|attn_q=effective:Q5_K|embeddings=effective:Q8_0|ffn_down=effective:IQ4_XS|ffn_up_gate=effective:IQ4_XS|lm_head=base|moe_experts=base|moe_router=base",
|
||||
"HasUnknownMappings": false,
|
||||
"Warnings": [],
|
||||
"UsedImatrix": true,
|
||||
"ExpectedSizeBytes": 2618576576,
|
||||
"ActualSizeBytes": 2618576576,
|
||||
"OriginalExternalSource": null
|
||||
}
|
||||
]
|
||||
475
magicquant.replacements.json
Normal file
475
magicquant.replacements.json
Normal file
@@ -0,0 +1,475 @@
|
||||
[
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "0:1:0:3:1:2:102:14:0:0",
|
||||
"fileName": "Model-MQ-Q5_K.gguf",
|
||||
"displayName": "Model-MQ-Q5_K",
|
||||
"shortName": "MQ-Q5_K",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q8_0",
|
||||
"isHybrid": true,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.006925,
|
||||
"ppl": 8.901754,
|
||||
"pplDeltaPercent": 0.204354090683967,
|
||||
"sizeBytes": 3040771776,
|
||||
"sizeGiB": 2.831939399242401
|
||||
},
|
||||
"winner": {
|
||||
"key": "0:1:0:2:1:2:102:14:0:0",
|
||||
"fileName": "Model-MQ-Q5_K_1.gguf",
|
||||
"displayName": "Model-MQ-Q5_K_1",
|
||||
"shortName": "MQ-Q5_K_1",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q5_K",
|
||||
"isHybrid": true,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.006632,
|
||||
"ppl": 8.900069,
|
||||
"pplDeltaPercent": 0.1853865550002334,
|
||||
"sizeBytes": 3090906816,
|
||||
"sizeGiB": 2.878631293773651
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.00029299999999999986,
|
||||
"sizeBytes": -50135040,
|
||||
"sizeGiB": -0.04669189453125,
|
||||
"removedPplDeltaPercent": 0.204354090683967,
|
||||
"winnerPplDeltaPercent": 0.1853865550002334,
|
||||
"pplDeltaPercentImprovement": 0.018967535683733605
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "2:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-Q5_K.gguf",
|
||||
"displayName": "Model-LM-Q5_K",
|
||||
"shortName": "LM-Q5_K",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "Q5_K",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.009942,
|
||||
"ppl": 8.896878,
|
||||
"pplDeltaPercent": 0.14946643252735017,
|
||||
"sizeBytes": 2889514176,
|
||||
"sizeGiB": 2.691069781780243
|
||||
},
|
||||
"winner": {
|
||||
"key": "101:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-UD-Q5_K_XL.gguf",
|
||||
"displayName": "Model-UD-Q5_K_XL",
|
||||
"shortName": "UD-Q5_K_XL",
|
||||
"provider": "Unsloth",
|
||||
"quantFamily": "UD-Q5_K_XL",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": true,
|
||||
"kld": 0.009839,
|
||||
"ppl": 8.923979,
|
||||
"pplDeltaPercent": 0.45453419784771626,
|
||||
"sizeBytes": 2930382016,
|
||||
"sizeGiB": 2.7291309237480164
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.00010299999999999893,
|
||||
"sizeBytes": -40867840,
|
||||
"sizeGiB": -0.03806114196777344,
|
||||
"removedPplDeltaPercent": 0.14946643252735017,
|
||||
"winnerPplDeltaPercent": 0.45453419784771626,
|
||||
"pplDeltaPercentImprovement": -0.30506776532036606
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "13:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-Q5_K_S.gguf",
|
||||
"displayName": "Model-LM-Q5_K_S",
|
||||
"shortName": "LM-Q5_K_S",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "Q5_K_S",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.010808,
|
||||
"ppl": 8.919999,
|
||||
"pplDeltaPercent": 0.40973254086182603,
|
||||
"sizeBytes": 2823711936,
|
||||
"sizeGiB": 2.6297866702079773
|
||||
},
|
||||
"winner": {
|
||||
"key": "2:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-Q5_K.gguf",
|
||||
"displayName": "Model-LM-Q5_K",
|
||||
"shortName": "LM-Q5_K",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "Q5_K",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.009942,
|
||||
"ppl": 8.896878,
|
||||
"pplDeltaPercent": 0.14946643252735017,
|
||||
"sizeBytes": 2889514176,
|
||||
"sizeGiB": 2.691069781780243
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.0008660000000000004,
|
||||
"sizeBytes": -65802240,
|
||||
"sizeGiB": -0.061283111572265625,
|
||||
"removedPplDeltaPercent": 0.40973254086182603,
|
||||
"winnerPplDeltaPercent": 0.14946643252735017,
|
||||
"pplDeltaPercentImprovement": 0.26026610833447583
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "0:1:0:7:1:2:7:15:0:0",
|
||||
"fileName": "Model-MQ-Q4_K_M.gguf",
|
||||
"displayName": "Model-MQ-Q4_K_M",
|
||||
"shortName": "MQ-Q4_K_M",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q8_0",
|
||||
"isHybrid": true,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.021705,
|
||||
"ppl": 8.964544,
|
||||
"pplDeltaPercent": 0.9111621414741836,
|
||||
"sizeBytes": 2600062656,
|
||||
"sizeGiB": 2.4214970469474792
|
||||
},
|
||||
"winner": {
|
||||
"key": "0:1:0:3:1:2:7:7:0:0",
|
||||
"fileName": "Model-MQ-Q4_K_M_1.gguf",
|
||||
"displayName": "Model-MQ-Q4_K_M_1",
|
||||
"shortName": "MQ-Q4_K_M_1",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q4_K_M",
|
||||
"isHybrid": true,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.020346,
|
||||
"ppl": 8.95744,
|
||||
"pplDeltaPercent": 0.8311945607636608,
|
||||
"sizeBytes": 2618576576,
|
||||
"sizeGiB": 2.4387394785881042
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.001358999999999999,
|
||||
"sizeBytes": -18513920,
|
||||
"sizeGiB": -0.017242431640625,
|
||||
"removedPplDeltaPercent": 0.9111621414741836,
|
||||
"winnerPplDeltaPercent": 0.8311945607636608,
|
||||
"pplDeltaPercentImprovement": 0.07996758071052279
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "NEAR_BASELINE_PREMIUM",
|
||||
"reasonDescription": "The winner used only the configured near-baseline size premium and beat the real linear KLD trade line.",
|
||||
"rawReason": "near-baseline replacement within \u002B1% size premium",
|
||||
"removed": {
|
||||
"key": "100:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-UD-Q4_K_XL.gguf",
|
||||
"displayName": "Model-UD-Q4_K_XL",
|
||||
"shortName": "UD-Q4_K_XL",
|
||||
"provider": "Unsloth",
|
||||
"quantFamily": "UD-Q4_K_XL",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": true,
|
||||
"kld": 0.022351,
|
||||
"ppl": 8.997353,
|
||||
"pplDeltaPercent": 1.2804831374668026,
|
||||
"sizeBytes": 2591284416,
|
||||
"sizeGiB": 2.4133216738700867
|
||||
},
|
||||
"winner": {
|
||||
"key": "0:1:0:7:1:2:7:15:0:0",
|
||||
"fileName": "Model-MQ-Q4_K_M.gguf",
|
||||
"displayName": "Model-MQ-Q4_K_M",
|
||||
"shortName": "MQ-Q4_K_M",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q8_0",
|
||||
"isHybrid": true,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.021705,
|
||||
"ppl": 8.964544,
|
||||
"pplDeltaPercent": 0.9111621414741836,
|
||||
"sizeBytes": 2600062656,
|
||||
"sizeGiB": 2.4214970469474792
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.0006460000000000007,
|
||||
"sizeBytes": -8778240,
|
||||
"sizeGiB": -0.008175373077392578,
|
||||
"removedPplDeltaPercent": 1.2804831374668026,
|
||||
"winnerPplDeltaPercent": 0.9111621414741836,
|
||||
"pplDeltaPercentImprovement": 0.36932099599261903
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "100:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-UD-Q4_K_XL.gguf",
|
||||
"displayName": "Model-UD-Q4_K_XL",
|
||||
"shortName": "UD-Q4_K_XL",
|
||||
"provider": "Unsloth",
|
||||
"quantFamily": "UD-Q4_K_XL",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": true,
|
||||
"kld": 0.022351,
|
||||
"ppl": 8.997353,
|
||||
"pplDeltaPercent": 1.2804831374668026,
|
||||
"sizeBytes": 2591284416,
|
||||
"sizeGiB": 2.4133216738700867
|
||||
},
|
||||
"winner": {
|
||||
"key": "0:1:0:7:1:2:7:15:0:0",
|
||||
"fileName": "Model-MQ-Q4_K_M.gguf",
|
||||
"displayName": "Model-MQ-Q4_K_M",
|
||||
"shortName": "MQ-Q4_K_M",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q8_0",
|
||||
"isHybrid": true,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.021705,
|
||||
"ppl": 8.964544,
|
||||
"pplDeltaPercent": 0.9111621414741836,
|
||||
"sizeBytes": 2600062656,
|
||||
"sizeGiB": 2.4214970469474792
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.0006460000000000007,
|
||||
"sizeBytes": -8778240,
|
||||
"sizeGiB": -0.008175373077392578,
|
||||
"removedPplDeltaPercent": 1.2804831374668026,
|
||||
"winnerPplDeltaPercent": 0.9111621414741836,
|
||||
"pplDeltaPercentImprovement": 0.36932099599261903
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "0:1:0:7:1:2:7:7:0:0",
|
||||
"fileName": "Model-MQ-Q4_K_M.gguf",
|
||||
"displayName": "Model-MQ-Q4_K_M",
|
||||
"shortName": "MQ-Q4_K_M",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q8_0",
|
||||
"isHybrid": true,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.023119,
|
||||
"ppl": 8.965156,
|
||||
"pplDeltaPercent": 0.9180512404881,
|
||||
"sizeBytes": 2559594176,
|
||||
"sizeGiB": 2.3838078379631042
|
||||
},
|
||||
"winner": {
|
||||
"key": "100:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-UD-Q4_K_XL.gguf",
|
||||
"displayName": "Model-UD-Q4_K_XL",
|
||||
"shortName": "UD-Q4_K_XL",
|
||||
"provider": "Unsloth",
|
||||
"quantFamily": "UD-Q4_K_XL",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": true,
|
||||
"kld": 0.022351,
|
||||
"ppl": 8.997353,
|
||||
"pplDeltaPercent": 1.2804831374668026,
|
||||
"sizeBytes": 2591284416,
|
||||
"sizeGiB": 2.4133216738700867
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.0007680000000000013,
|
||||
"sizeBytes": -31690240,
|
||||
"sizeGiB": -0.029513835906982422,
|
||||
"removedPplDeltaPercent": 0.9180512404881,
|
||||
"winnerPplDeltaPercent": 1.2804831374668026,
|
||||
"pplDeltaPercentImprovement": -0.3624318969787026
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "3:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-Q4_K_M.gguf",
|
||||
"displayName": "Model-LM-Q4_K_M",
|
||||
"shortName": "LM-Q4_K_M",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "Q4_K_M",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.025432,
|
||||
"ppl": 9.030426,
|
||||
"pplDeltaPercent": 1.6527759016614976,
|
||||
"sizeBytes": 2497281216,
|
||||
"sizeGiB": 2.325774371623993
|
||||
},
|
||||
"winner": {
|
||||
"key": "0:1:0:7:1:2:7:7:0:0",
|
||||
"fileName": "Model-MQ-Q4_K_M.gguf",
|
||||
"displayName": "Model-MQ-Q4_K_M",
|
||||
"shortName": "MQ-Q4_K_M",
|
||||
"provider": "MagicQuant",
|
||||
"quantFamily": "Q8_0",
|
||||
"isHybrid": true,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.023119,
|
||||
"ppl": 8.965156,
|
||||
"pplDeltaPercent": 0.9180512404881,
|
||||
"sizeBytes": 2559594176,
|
||||
"sizeGiB": 2.3838078379631042
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.002312999999999999,
|
||||
"sizeBytes": -62312960,
|
||||
"sizeGiB": -0.05803346633911133,
|
||||
"removedPplDeltaPercent": 1.6527759016614976,
|
||||
"winnerPplDeltaPercent": 0.9180512404881,
|
||||
"pplDeltaPercentImprovement": 0.7347246611733975
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "5:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ4_NL.gguf",
|
||||
"displayName": "Model-LM-IQ4_NL",
|
||||
"shortName": "LM-IQ4_NL",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ4_NL",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.030626,
|
||||
"ppl": 8.946429,
|
||||
"pplDeltaPercent": 0.7072470620018989,
|
||||
"sizeBytes": 2381343936,
|
||||
"sizeGiB": 2.2177993655204773
|
||||
},
|
||||
"winner": {
|
||||
"key": "14:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-Q4_K_S.gguf",
|
||||
"displayName": "Model-LM-Q4_K_S",
|
||||
"shortName": "LM-Q4_K_S",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "Q4_K_S",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.029803,
|
||||
"ppl": 9.010033,
|
||||
"pplDeltaPercent": 1.4232180647485306,
|
||||
"sizeBytes": 2383310016,
|
||||
"sizeGiB": 2.2196304202079773
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.0008230000000000008,
|
||||
"sizeBytes": -1966080,
|
||||
"sizeGiB": -0.0018310546875,
|
||||
"removedPplDeltaPercent": 0.7072470620018989,
|
||||
"winnerPplDeltaPercent": 1.4232180647485306,
|
||||
"pplDeltaPercentImprovement": -0.7159710027466317
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "8:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ3_XS.gguf",
|
||||
"displayName": "Model-LM-IQ3_XS",
|
||||
"shortName": "LM-IQ3_XS",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ3_XS",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.11761,
|
||||
"ppl": 9.485851,
|
||||
"pplDeltaPercent": 6.779357467693287,
|
||||
"sizeBytes": 1814375616,
|
||||
"sizeGiB": 1.6897689700126648
|
||||
},
|
||||
"winner": {
|
||||
"key": "7:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ3_S.gguf",
|
||||
"displayName": "Model-LM-IQ3_S",
|
||||
"shortName": "LM-IQ3_S",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ3_S",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.091992,
|
||||
"ppl": 9.349099,
|
||||
"pplDeltaPercent": 5.239981539015728,
|
||||
"sizeBytes": 1899531456,
|
||||
"sizeGiB": 1.7690765261650085
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.025618000000000002,
|
||||
"sizeBytes": -85155840,
|
||||
"sizeGiB": -0.07930755615234375,
|
||||
"removedPplDeltaPercent": 6.779357467693287,
|
||||
"winnerPplDeltaPercent": 5.239981539015728,
|
||||
"pplDeltaPercentImprovement": 1.5393759286775586
|
||||
}
|
||||
},
|
||||
{
|
||||
"reasonCode": "SPACING_COLLAPSE",
|
||||
"reasonDescription": "Two candidates were too close in practical output space; the stronger one was kept.",
|
||||
"rawReason": "meaningful spacing collapse; size gap below 91,013,530 bytes",
|
||||
"removed": {
|
||||
"key": "11:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ2_XS.gguf",
|
||||
"displayName": "Model-LM-IQ2_XS",
|
||||
"shortName": "LM-IQ2_XS",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ2_XS",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.529564,
|
||||
"ppl": 13.498521,
|
||||
"pplDeltaPercent": 51.94877076860733,
|
||||
"sizeBytes": 1354100416,
|
||||
"sizeGiB": 1.2611042857170105
|
||||
},
|
||||
"winner": {
|
||||
"key": "10:0:0:0:0:0:0:0:0:0",
|
||||
"fileName": "Model-LM-IQ2_S.gguf",
|
||||
"displayName": "Model-LM-IQ2_S",
|
||||
"shortName": "LM-IQ2_S",
|
||||
"provider": "llama.cpp",
|
||||
"quantFamily": "IQ2_S",
|
||||
"isHybrid": false,
|
||||
"isExternalPureBaseline": false,
|
||||
"kld": 0.431128,
|
||||
"ppl": 12.334448,
|
||||
"pplDeltaPercent": 38.84515286595525,
|
||||
"sizeBytes": 1417301696,
|
||||
"sizeGiB": 1.3199650645256042
|
||||
},
|
||||
"deltas": {
|
||||
"kld": 0.09843600000000002,
|
||||
"sizeBytes": -63201280,
|
||||
"sizeGiB": -0.05886077880859375,
|
||||
"removedPplDeltaPercent": 51.94877076860733,
|
||||
"winnerPplDeltaPercent": 38.84515286595525,
|
||||
"pplDeltaPercentImprovement": 13.103617902652083
|
||||
}
|
||||
}
|
||||
]
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 4022468096,
|
||||
"total_size": 8044936192
|
||||
},
|
||||
"weight_map": {
|
||||
"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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "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-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "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-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-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_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-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_norm.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_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "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_norm.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_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "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
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
241
tokenizer_config.json
Normal file
241
tokenizer_config.json
Normal file
@@ -0,0 +1,241 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 262144,
|
||||
"pad_token": "<|vision_pad|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}"
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user