hadadxyz/Qwen3-4B-Diversity
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: hadadxyz/Qwen3-4B-Diversity
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-09 19:29:05 +08:00
commit 664bf50338
32 changed files with 157172 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
.gitattributes vendored Normal file
View File

@@ -0,0 +1,37 @@
*.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
tokenizer.json filter=lfs diff=lfs merge=lfs -text
evaluations/mmlu.png filter=lfs diff=lfs merge=lfs -text

203
LICENSE Normal file
View File

@@ -0,0 +1,203 @@
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
Copyright 2026 Hadad <hadad@linuxmail.org>
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.

833
README.md Normal file
View File

@@ -0,0 +1,833 @@
---
base_model:
- Qwen/Qwen3-4B
tags:
- distillation
- distilled
- sft
- peft
- qwen3
datasets:
- ianncity/KIMI-K2.5-550000x
- Jackrong/Qwen3.5-reasoning-700x
- nohurry/Opus-4.6-Reasoning-3000x-filtered
- TeichAI/claude-4.5-opus-high-reasoning-250x
- TeichAI/gemini-3-pro-preview-high-reasoning-250x
- TeichAI/claude-haiku-4.5-high-reasoning-1700x
- TeichAI/gpt-5.2-high-reasoning-250x
- Roman1111111/gemini-3.1-pro-hard-high-reasoning
- Jackrong/glm-4.7-multiturn-CoT
- bmeyer2025/glm5-reasoning-traces
- TeichAI/claude-sonnet-4.5-high-reasoning-250x
- TeichAI/deepseek-v3.2-speciale-openr1-math-3k
- TeichAI/deepseek-v3.2-speciale-OpenCodeReasoning-3k
- TeichAI/deepseek-v3.2-speciale-1000x
- TeichAI/gpt-5-codex-1000x
model-index:
- name: hadadxyz/Qwen3-4B-Diversity
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu
type: cais/mmlu
metrics:
- type: acc
value: 67.8
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Humanities
type: cais/mmlu
metrics:
- type: acc
value: 57.9
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Formal Logic
type: cais/mmlu
metrics:
- type: acc
value: 58.7
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School European History
type: cais/mmlu
metrics:
- type: acc
value: 78.2
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Us History
type: cais/mmlu
metrics:
- type: acc
value: 84.8
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School World History
type: cais/mmlu
metrics:
- type: acc
value: 83.1
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu International Law
type: cais/mmlu
metrics:
- type: acc
value: 77.7
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Jurisprudence
type: cais/mmlu
metrics:
- type: acc
value: 78.7
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Logical Fallacies
type: cais/mmlu
metrics:
- type: acc
value: 82.8
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Moral Disputes
type: cais/mmlu
metrics:
- type: acc
value: 71.1
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Moral Scenarios
type: cais/mmlu
metrics:
- type: acc
value: 28.4
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Philosophy
type: cais/mmlu
metrics:
- type: acc
value: 73.3
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Prehistory
type: cais/mmlu
metrics:
- type: acc
value: 76.2
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Professional Law
type: cais/mmlu
metrics:
- type: acc
value: 47.4
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu World Religions
type: cais/mmlu
metrics:
- type: acc
value: 78.4
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Other
type: cais/mmlu
metrics:
- type: acc
value: 72.1
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Business Ethics
type: cais/mmlu
metrics:
- type: acc
value: 73.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Clinical Knowledge
type: cais/mmlu
metrics:
- type: acc
value: 75.5
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu College Medicine
type: cais/mmlu
metrics:
- type: acc
value: 71.1
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Global Facts
type: cais/mmlu
metrics:
- type: acc
value: 41.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Human Aging
type: cais/mmlu
metrics:
- type: acc
value: 67.7
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Management
type: cais/mmlu
metrics:
- type: acc
value: 84.5
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Marketing
type: cais/mmlu
metrics:
- type: acc
value: 85.5
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Medical Genetics
type: cais/mmlu
metrics:
- type: acc
value: 75.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Miscellaneous
type: cais/mmlu
metrics:
- type: acc
value: 79.7
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Nutrition
type: cais/mmlu
metrics:
- type: acc
value: 74.8
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Professional Accounting
type: cais/mmlu
metrics:
- type: acc
value: 55.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Professional Medicine
type: cais/mmlu
metrics:
- type: acc
value: 71.7
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Virology
type: cais/mmlu
metrics:
- type: acc
value: 53.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Social Sciences
type: cais/mmlu
metrics:
- type: acc
value: 78.4
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Econometrics
type: cais/mmlu
metrics:
- type: acc
value: 64.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Geography
type: cais/mmlu
metrics:
- type: acc
value: 84.3
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Government And Politics
type: cais/mmlu
metrics:
- type: acc
value: 87.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Macroeconomics
type: cais/mmlu
metrics:
- type: acc
value: 74.6
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Microeconomics
type: cais/mmlu
metrics:
- type: acc
value: 80.7
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Psychology
type: cais/mmlu
metrics:
- type: acc
value: 87.2
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Human Sexuality
type: cais/mmlu
metrics:
- type: acc
value: 75.6
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Professional Psychology
type: cais/mmlu
metrics:
- type: acc
value: 71.2
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Public Relations
type: cais/mmlu
metrics:
- type: acc
value: 71.8
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Security Studies
type: cais/mmlu
metrics:
- type: acc
value: 74.3
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Sociology
type: cais/mmlu
metrics:
- type: acc
value: 84.1
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Us Foreign Policy
type: cais/mmlu
metrics:
- type: acc
value: 81.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Stem
type: cais/mmlu
metrics:
- type: acc
value: 68.1
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Abstract Algebra
type: cais/mmlu
metrics:
- type: acc
value: 45.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Anatomy
type: cais/mmlu
metrics:
- type: acc
value: 61.5
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Astronomy
type: cais/mmlu
metrics:
- type: acc
value: 78.9
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu College Biology
type: cais/mmlu
metrics:
- type: acc
value: 83.3
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu College Chemistry
type: cais/mmlu
metrics:
- type: acc
value: 54.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu College Computer Science
type: cais/mmlu
metrics:
- type: acc
value: 69.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu College Mathematics
type: cais/mmlu
metrics:
- type: acc
value: 58.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu College Physics
type: cais/mmlu
metrics:
- type: acc
value: 53.9
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Computer Security
type: cais/mmlu
metrics:
- type: acc
value: 80.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Conceptual Physics
type: cais/mmlu
metrics:
- type: acc
value: 77.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Electrical Engineering
type: cais/mmlu
metrics:
- type: acc
value: 76.6
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Elementary Mathematics
type: cais/mmlu
metrics:
- type: acc
value: 65.6
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Biology
type: cais/mmlu
metrics:
- type: acc
value: 86.1
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Chemistry
type: cais/mmlu
metrics:
- type: acc
value: 70.4
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Computer Science
type: cais/mmlu
metrics:
- type: acc
value: 86.0
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Mathematics
type: cais/mmlu
metrics:
- type: acc
value: 42.6
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Physics
type: cais/mmlu
metrics:
- type: acc
value: 62.9
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu High School Statistics
type: cais/mmlu
metrics:
- type: acc
value: 71.3
name: accuracy
- task:
type: text-generation
name: Text Generation
dataset:
name: Mmlu Machine Learning
type: cais/mmlu
metrics:
- type: acc
value: 57.1
name: accuracy
pipeline_tag: text-generation
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/hadadxyz/Qwen3-4B-Diversity/blob/main/LICENSE
---
# Introduction
![MMLU](evaluations/mmlu.png)
Qwen3-4B-Diversity is a fine-tuned language model based on [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) that has been trained on a diverse collection of high-quality reasoning datasets. This model combines knowledge distilled from various state-of-the-art AI systems to provide enhanced reasoning capabilities across multiple domains including mathematics, coding, general problem-solving, and multi-turn conversations.
### Training Configuration
The model was trained using supervised fine-tuning techniques with parameter-efficient methods to optimize performance while maintaining computational efficiency. Key training parameters include:
| Parameter | Value |
|------------------|--------|
| Number of Epochs | 2 |
| Context Length | 40,960 |
### Hardware and Resources
| Resource | Specification |
|-------------------|------------------------|
| GPU | A100-80GB |
| Training Duration | Approximately 17 hours |
| Estimated Cost | $27 to $30 |
### Training Data
| Dataset | Rows Used | Model |
|--------------------------------------------------------------------------------------------------------------------------------------------|------------|------------------------------------|
| [ianncity/KIMI-K2.5-550000x](https://huggingface.co/datasets/ianncity/KIMI-K2.5-550000x) (General-Distillation) | 1,000 | Kimi K2.5 |
| [Jackrong/Qwen3.5-reasoning-700x](https://huggingface.co/datasets/Jackrong/Qwen3.5-reasoning-700x) | 633 | Qwen3.5 |
| [nohurry/Opus-4.6-Reasoning-3000x-filtered](https://huggingface.co/datasets/nohurry/Opus-4.6-Reasoning-3000x-filtered) | 2,326 | Claude Opus 4.6 |
| [TeichAI/claude-4.5-opus-high-reasoning-250x](https://huggingface.co/datasets/TeichAI/claude-4.5-opus-high-reasoning-250x) | 250 | Claude Opus 4.5 |
| [TeichAI/gemini-3-pro-preview-high-reasoning-250x](https://huggingface.co/datasets/TeichAI/gemini-3-pro-preview-high-reasoning-250x) | 248 | Gemini 3 Pro |
| [TeichAI/claude-haiku-4.5-high-reasoning-1700x](https://huggingface.co/datasets/TeichAI/claude-haiku-4.5-high-reasoning-1700x) | 1,688 | Claude Haiku 4.5 |
| [TeichAI/gpt-5.2-high-reasoning-250x](https://huggingface.co/datasets/TeichAI/gpt-5.2-high-reasoning-250x) | 249 | GPT-5.2 |
| [Roman1111111/gemini-3.1-pro-hard-high-reasoning](https://huggingface.co/datasets/Roman1111111/gemini-3.1-pro-hard-high-reasoning) | 3,150 | Gemini 3.1 Pro |
| [Jackrong/glm-4.7-multiturn-CoT](https://huggingface.co/datasets/Jackrong/glm-4.7-multiturn-CoT) | 5,090 | GLM-4.7 |
| [bmeyer2025/glm5-reasoning-traces](https://huggingface.co/datasets/bmeyer2025/glm5-reasoning-traces) | 1,744 | GLM-5 |
| [TeichAI/claude-sonnet-4.5-high-reasoning-250x](https://huggingface.co/datasets/TeichAI/claude-sonnet-4.5-high-reasoning-250x) | 247 | Claude Sonnet 4.5 |
| [TeichAI/deepseek-v3.2-speciale-openr1-math-3k](https://huggingface.co/datasets/TeichAI/deepseek-v3.2-speciale-openr1-math-3k) | 3,317 | DeepSeek V3.2-Speciale |
| [TeichAI/deepseek-v3.2-speciale-OpenCodeReasoning-3k](https://huggingface.co/datasets/TeichAI/deepseek-v3.2-speciale-OpenCodeReasoning-3k) | 2,953 | DeepSeek V3.2-Speciale |
| [TeichAI/deepseek-v3.2-speciale-1000x](https://huggingface.co/datasets/TeichAI/deepseek-v3.2-speciale-1000x) | 991 | DeepSeek V3.2-Speciale |
| [TeichAI/gpt-5-codex-1000x](https://huggingface.co/datasets/TeichAI/gpt-5-codex-1000x) | 991 | GPT-5 Codex |
| **Total** | **24,877** | Combined diverse reasoning dataset |
## Model Capabilities
This model excels in several key areas:
1. **Advanced Reasoning**: The model can break down complex problems into steps and provide detailed reasoning processes.
2. **Mathematical Problem Solving**: Enhanced capabilities for mathematical reasoning and problem-solving through dedicated math-focused datasets.
3. **Code Generation and Understanding**: Improved coding abilities from multiple code-reasoning datasets including DeepSeek and GPT-5 Codex data.
4. **Multi-Turn Conversations**: Better handling of extended dialogues and context-aware responses.
5. **Domain Versatility**: Exposure to reasoning patterns from various AI systems provides flexibility across different domains and task types.
## Usage
### Quick Demo
If you are looking for a quick demo that is completely free and without any cost, you can use [Google Colab](https://colab.research.google.com/drive/1qy1n9MigDuwT0cA1Y6ImHChAIlsZPIcC).
### Ollama (Local)
```bash
# https://ollama.com/hadad/qwen3-4bd
# hadad/qwen3-4bd:Q8_0 | 4.3GB
# hadad/qwen3-4bd:BF16 | 8.1GB
# ollama pull hadad/qwen3-4bd:Q8_0
ollama run hadad/qwen3-4bd:Q8_0
```
If you are using Ollama and are interested in **tools** or **function calling**, it is recommended to use the **OpenAI-compatible API** provided by Ollama. This approach is more powerful.
Refer to the [Ollama documentation](https://docs.ollama.com/api/openai-compatibility).
### Python (Local)
```bash
#pip install transformers==4.56.2
```
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "hadadxyz/Qwen3-4B-Diversity"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
**model_inputs,
max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
# parsing thinking content
try:
# rindex finding 151668 (</think>)
index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
index = 0
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
print("thinking content:", thinking_content)
print("content:", content)
```
## Inference Parameters
For optimal results, we recommend the following generation parameters:
### Thinking
| Parameter | Recommended Value | Description |
|-----------------|-------------------|------------------------------------------|
| temperature | 0.6 | Controls randomness in generation |
| top_p | 0.95 | Nucleus sampling threshold |
| top_k | 20 | Top-k sampling parameter |
| min_p | 0 | Minimum probability threshold |
### Non-Thinking
| Parameter | Recommended Value | Description |
|-----------------|-------------------|------------------------------------------|
| temperature | 0.7 | Controls randomness in generation |
| top_p | 0.8 | Nucleus sampling threshold |
| top_k | 20 | Top-k sampling parameter |
| min_p | 0 | Minimum probability threshold |
## Citation
If you use this model in your research or applications, please cite both this model and the base model:
```bibtex
@misc{qwen3-4b-diversity,
author = {hadadxyz},
title = {Qwen3-4B-Diversity},
year = {2026},
url = {https://huggingface.co/hadadxyz/Qwen3-4B-Diversity}
}
```
## Acknowledgments
This model was made possible through the combination of multiple high-quality datasets from the community. We acknowledge and thank all dataset creators and the Qwen team for providing the excellent base model.

28
added_tokens.json Normal file
View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

89
chat_template.jinja Normal file
View File

@@ -0,0 +1,89 @@
{%- 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' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

68
config.json Normal file
View File

@@ -0,0 +1,68 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"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": 40960,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.56.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

3779
evaluations/mmlu.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
evaluations/mmlu.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2fa3c2b5880714db1ff1b0ec5419d337839aab4a3c99c5f0ee01c0fcd5364b98
size 672396

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.56.2"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a3293b085e2c90b6807719d47b58e29844fefa586f8eca6e84a484784c99fea
size 777912456

3
model-00002-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d321b17b355e0dd84bd10765460adb2108f4629e648bbeec02450a97833b64ca
size 456155752

3
model-00003-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:491c448c6ae920282a3f80c98ea9c70ea35f94c6a6a18c19895702f04e23c8f1
size 453533232

3
model-00004-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0dff20cea561294e3e05d648100b889795d434a89c691a0b2f9782de5d6a4650
size 453533232

3
model-00005-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5bf87cad8cdaffc9c374f65aa6bab8bf8481e331ec822ef0bb9639e3e24c7a2b
size 485001320

3
model-00006-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3acca73288cf0aef22df7faef5a812a849ac85a2def7a52016cf91a5378bca74
size 474505616

3
model-00007-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a31d63f8678d036265c610c8ded0dbd9ad4139a7b532386d70ca27db9aa81682
size 453533256

3
model-00008-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6c7e265c478dd030bb6330a7900d2e2de1e25b45c14ccbc2c46f01cef5ef4e73
size 485001352

3
model-00009-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fede905368ce59a678aec2c9be30051bbfb2b8fc13974b4bc3330bea47e33ff5
size 474505624

3
model-00010-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:16fdb0627c41b983eb7bcbb14928046dd9b0614527956b94cfe55420652c48e2
size 453533256

3
model-00011-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:30a16a8983ebec48d68f598e165642e6ff09f23a6659c6e0bb2cc63259cda4b9
size 485001352

3
model-00012-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95814389b3ecd20cce946bae3c4b1a931d684425af214365b3ffa6015e346c37
size 474505624

3
model-00013-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:81b9e1dc44275eb5d8c7e7b915f4ec66a9d9ddd94b24073936bd8a04dc955850
size 453533256

3
model-00014-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c964b969f6bf592338a8395820d030e42e91745f39818879bd5a293e48125232
size 485001352

3
model-00015-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:28b3cacfa97dad67b5f8ee2ffefdaf620c48a7c8193d981fcd80d407c393a570
size 474505624

3
model-00016-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:647187104b42d53b0df1fb480a40d685af44568ce047e6bc2e9a5a345cacae41
size 453533256

3
model-00017-of-00017.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c447a02b7f57c47774beb516afe96657b2f91fb1f2b9438bdb8a044aaad45f3
size 251686048

406
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,406 @@
{
"metadata": {
"total_parameters": 4022468096,
"total_size": 8044936192
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00017.safetensors",
"model.layers.0.input_layernorm.weight": "model-00002-of-00017.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
"model.layers.0.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.0.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.1.input_layernorm.weight": "model-00002-of-00017.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
"model.layers.1.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.1.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.10.input_layernorm.weight": "model-00006-of-00017.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
"model.layers.10.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.10.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.11.input_layernorm.weight": "model-00007-of-00017.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
"model.layers.11.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.11.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
"model.layers.12.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.12.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.13.input_layernorm.weight": "model-00008-of-00017.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
"model.layers.13.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.13.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
"model.layers.14.input_layernorm.weight": "model-00008-of-00017.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
"model.layers.14.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.14.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.15.input_layernorm.weight": "model-00008-of-00017.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
"model.layers.15.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.15.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.16.input_layernorm.weight": "model-00009-of-00017.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
"model.layers.16.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.16.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
"model.layers.17.input_layernorm.weight": "model-00009-of-00017.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
"model.layers.17.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.17.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.18.input_layernorm.weight": "model-00010-of-00017.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
"model.layers.18.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.18.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
"model.layers.19.input_layernorm.weight": "model-00010-of-00017.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
"model.layers.19.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.19.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.2.input_layernorm.weight": "model-00003-of-00017.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
"model.layers.2.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.2.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
"model.layers.20.input_layernorm.weight": "model-00011-of-00017.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
"model.layers.20.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.20.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
"model.layers.21.input_layernorm.weight": "model-00011-of-00017.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
"model.layers.21.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.21.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.22.input_layernorm.weight": "model-00011-of-00017.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
"model.layers.22.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.22.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.23.input_layernorm.weight": "model-00012-of-00017.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
"model.layers.23.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.23.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
"model.layers.24.input_layernorm.weight": "model-00012-of-00017.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
"model.layers.24.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.24.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.25.input_layernorm.weight": "model-00013-of-00017.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
"model.layers.25.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.25.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
"model.layers.26.input_layernorm.weight": "model-00013-of-00017.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
"model.layers.26.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.26.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.27.input_layernorm.weight": "model-00014-of-00017.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
"model.layers.27.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.27.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
"model.layers.28.input_layernorm.weight": "model-00014-of-00017.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
"model.layers.28.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.28.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.29.input_layernorm.weight": "model-00014-of-00017.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
"model.layers.29.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.29.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.3.input_layernorm.weight": "model-00003-of-00017.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
"model.layers.3.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.3.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.30.input_layernorm.weight": "model-00015-of-00017.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
"model.layers.30.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.30.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
"model.layers.31.input_layernorm.weight": "model-00015-of-00017.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
"model.layers.31.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.31.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.32.input_layernorm.weight": "model-00016-of-00017.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
"model.layers.32.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.32.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
"model.layers.33.input_layernorm.weight": "model-00016-of-00017.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
"model.layers.33.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.33.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.34.input_layernorm.weight": "model-00017-of-00017.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
"model.layers.34.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.34.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
"model.layers.35.input_layernorm.weight": "model-00017-of-00017.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
"model.layers.35.self_attn.k_norm.weight": "model-00017-of-00017.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
"model.layers.35.self_attn.q_norm.weight": "model-00017-of-00017.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
"model.layers.4.input_layernorm.weight": "model-00004-of-00017.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
"model.layers.4.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.4.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
"model.layers.5.input_layernorm.weight": "model-00004-of-00017.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
"model.layers.5.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.5.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.6.input_layernorm.weight": "model-00005-of-00017.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
"model.layers.6.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.6.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
"model.layers.7.input_layernorm.weight": "model-00005-of-00017.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
"model.layers.7.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.7.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.8.input_layernorm.weight": "model-00005-of-00017.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
"model.layers.8.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.8.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.9.input_layernorm.weight": "model-00006-of-00017.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
"model.layers.9.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
"model.layers.9.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
"model.norm.weight": "model-00017-of-00017.safetensors"
}
}

31
special_tokens_map.json Normal file
View File

@@ -0,0 +1,31 @@
{
"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|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
size 11422654

239
tokenizer_config.json Normal file
View File

@@ -0,0 +1,239 @@
{
"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": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long