初始化项目，由ModelHub XC社区提供模型
Model: skt/A.X-4.0-Light Source: Original Platform
This commit is contained in:
ModelHub XC
39
.gitattributes
vendored
Normal file
39
.gitattributes
vendored
Normal file
@@ -0,0 +1,39 @@
|
||||
*.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
|
||||
assets/A.X_logo_ko.jpg filter=lfs diff=lfs merge=lfs -text
|
||||
A.X_logo_ko.png filter=lfs diff=lfs merge=lfs -text
|
||||
assets/A.X_logo_ko.png filter=lfs diff=lfs merge=lfs -text
|
||||
assets/A.X_logo_ko_4x3.png filter=lfs diff=lfs merge=lfs -text
|
||||
233
LICENSE
Normal file
233
LICENSE
Normal file
@@ -0,0 +1,233 @@
|
||||
Copyright (c) 2025 SK Telecom Co., Ltd. All rights reserved.
|
||||
|
||||
Built with Qwen 2.5 — original model by Alibaba Cloud, licensed under the Apache License 2.0.
|
||||
|
||||
Unless otherwise stated, all files in this repository (including modified model weights
|
||||
and tokenizer files) are distributed under the terms of the Apache License, Version 2.0
|
||||
(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.
|
||||
|
||||
================================================================================
|
||||
NOTICE (Apache-2.0 §4 d)
|
||||
================================================================================
|
||||
|
||||
This product is built with Qwen 2.5 developed by Alibaba Cloud
|
||||
(https://github.com/QwenLM) and distributed under the Apache License 2.0.
|
||||
|
||||
See the upstream Qwen 2.5 repository for additional attribution details.
|
||||
|
||||
================================================================================
|
||||
TRADEMARK
|
||||
================================================================================
|
||||
|
||||
"SK Telecom" and associated logos are trademarks of SK Telecom Co., Ltd.
|
||||
This License does not grant permission to use these trademarks without prior
|
||||
written consent.
|
||||
|
||||
================================================================================
|
||||
APACHE LICENSE 2.0
|
||||
================================================================================
|
||||
|
||||
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.
|
||||
542
README.md
Normal file
542
README.md
Normal file
@@ -0,0 +1,542 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
license_link: https://huggingface.co/skt/A.X-4.0-Light/blob/main/LICENSE
|
||||
language:
|
||||
- en
|
||||
- ko
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
model_id: skt/A.X-4.0-Light
|
||||
developers: SKT AI Model Lab
|
||||
model-index:
|
||||
- name: A.X-4.0-Light
|
||||
results:
|
||||
- task:
|
||||
type: generate_until
|
||||
name: mmlu
|
||||
dataset:
|
||||
name: mmlu (chat CoT)
|
||||
type: hails/mmlu_no_train
|
||||
metrics:
|
||||
- type: exact_match
|
||||
value: 75.43
|
||||
name: exact_match
|
||||
- task:
|
||||
type: generate_until
|
||||
name: kmmlu
|
||||
dataset:
|
||||
name: kmmlu (chat CoT)
|
||||
type: HAERAE-HUB/KMMLU
|
||||
metrics:
|
||||
- type: exact_match
|
||||
value: 64.15
|
||||
name: exact_match
|
||||
---
|
||||
|
||||
# A.X 4.0 Light
|
||||
|
||||
<p align="center">
|
||||
<picture>
|
||||
<img src="./assets/A.X_logo_ko_4x3.png" width="45%" style="margin: 40px auto;">
|
||||
</picture>
|
||||
</p>
|
||||
<p align="center"> <a href="https://huggingface.co/collections/skt/ax-4-68637ebaa63b9cc51925e886">🤗 Models</a> | <a href="https://sktax.chat/chat">💬 Chat</a> | <a href="https://github.com/SKT-AI/A.X-4.0/blob/main/apis/README.md">📬 APIs (FREE!)</a> | <a href="https://github.com/SKT-AI/A.X-4.0">🖥️ Github</a> </p>
|
||||
|
||||
## A.X 4.0 Family Highlights
|
||||
|
||||
SK Telecom released **A.X 4.0** (pronounced "A dot X"), a large language model (LLM) optimized for Korean-language understanding and enterprise deployment, on July 03, 2025. Built on the open-source [Qwen2.5](https://huggingface.co/collections/Qwen/qwen25-66e81a666513e518adb90d9e) model, A.X 4.0 has been further trained with large-scale Korean datasets to deliver outstanding performance in real-world business environments.
|
||||
|
||||
- **Superior Korean Proficiency**: Achieved a score of 78.3 on [KMMLU](https://huggingface.co/datasets/HAERAE-HUB/KMMLU), the leading benchmark for Korean-language evaluation and a Korean-specific adaptation of MMLU, outperforming GPT-4o (72.5).
|
||||
- **Deep Cultural Understanding**: Scored 83.5 on [CLIcK](https://huggingface.co/datasets/EunsuKim/CLIcK), a benchmark for Korean cultural and contextual comprehension, surpassing GPT-4o (80.2).
|
||||
- **Efficient Token Usage**: A.X 4.0 uses approximately 33% fewer tokens than GPT-4o for the same Korean input, enabling more cost-effective and efficient processing.
|
||||
- **Deployment Flexibility**: Offered in both a 72B-parameter standard model (A.X 4.0) and a 7B lightweight version (A.X 4.0 Light).
|
||||
- **Long Context Handling**: Supports up to 131,072 tokens, allowing comprehension of lengthy documents and conversations. (Lightweight model supports up to 16,384 tokens length)
|
||||
|
||||
## Performance
|
||||
|
||||
### Model Performance
|
||||
|
||||
<table><thead>
|
||||
<tr>
|
||||
<th colspan="2">Benchmarks</th>
|
||||
<th>A.X 4.0</th>
|
||||
<th>Qwen3-235B-A22B<br/>(w/o reasoning)</th>
|
||||
<th>Qwen2.5-72B</th>
|
||||
<th>GPT-4o</th>
|
||||
</tr></thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td rowspan="6">Knowledge</td>
|
||||
<td>KMMLU</td>
|
||||
<td>78.32</td>
|
||||
<td>73.64</td>
|
||||
<td>66.44</td>
|
||||
<td>72.51</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>KMMLU-pro</td>
|
||||
<td>72.43</td>
|
||||
<td>64.4</td>
|
||||
<td>56.27</td>
|
||||
<td>66.97</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>KMMLU-redux</td>
|
||||
<td>74.18</td>
|
||||
<td>71.17</td>
|
||||
<td>58.76</td>
|
||||
<td>69.08</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>CLIcK</td>
|
||||
<td>83.51</td>
|
||||
<td>74.55</td>
|
||||
<td>72.59</td>
|
||||
<td>80.22</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>KoBALT</td>
|
||||
<td>47.30</td>
|
||||
<td>41.57</td>
|
||||
<td>37.00</td>
|
||||
<td>44.00</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MMLU</td>
|
||||
<td>86.62</td>
|
||||
<td>87.37</td>
|
||||
<td>85.70</td>
|
||||
<td>88.70</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="3">General</td>
|
||||
<td>Ko-MT-Bench</td>
|
||||
<td>86.69</td>
|
||||
<td>88.00</td>
|
||||
<td>82.69</td>
|
||||
<td>88.44</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MT-Bench</td>
|
||||
<td>83.25</td>
|
||||
<td>86.56</td>
|
||||
<td>93.50</td>
|
||||
<td>88.19</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>LiveBench<sup>2024.11</sup></td>
|
||||
<td>52.30</td>
|
||||
<td>64.50</td>
|
||||
<td>54.20</td>
|
||||
<td>52.19</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="2">Instruction Following</td>
|
||||
<td>Ko-IFEval</td>
|
||||
<td>77.96</td>
|
||||
<td>77.53</td>
|
||||
<td>77.07</td>
|
||||
<td>75.38</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>IFEval</td>
|
||||
<td>86.05</td>
|
||||
<td>85.77</td>
|
||||
<td>86.54</td>
|
||||
<td>83.86</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="2">Math</td>
|
||||
<td>HRM8K</td>
|
||||
<td>48.55</td>
|
||||
<td>54.52</td>
|
||||
<td>46.37</td>
|
||||
<td>43.27</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MATH</td>
|
||||
<td>74.28</td>
|
||||
<td>72.72</td>
|
||||
<td>77.00</td>
|
||||
<td>72.38</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="3">Code</td>
|
||||
<td>HumanEval+</td>
|
||||
<td>79.27</td>
|
||||
<td>79.27</td>
|
||||
<td>81.71</td>
|
||||
<td>86.00</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MBPP+</td>
|
||||
<td>73.28</td>
|
||||
<td>70.11</td>
|
||||
<td>75.66</td>
|
||||
<td>75.10</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>LiveCodeBench<sup>2024.10~2025.04</sup></td>
|
||||
<td>26.07</td>
|
||||
<td>33.09</td>
|
||||
<td>27.58</td>
|
||||
<td>29.30</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Long Context</td>
|
||||
<td>LongBench<sup><128K</sup></td>
|
||||
<td>56.70</td>
|
||||
<td>49.40</td>
|
||||
<td>45.60</td>
|
||||
<td>47.50</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Tool-use</td>
|
||||
<td>FunctionChatBench</td>
|
||||
<td>85.96</td>
|
||||
<td>82.43</td>
|
||||
<td>88.30</td>
|
||||
<td>95.70</td>
|
||||
</tr>
|
||||
</tbody></table>
|
||||
|
||||
### Lightweight Model Performance
|
||||
|
||||
<table><thead>
|
||||
<tr>
|
||||
<th colspan="2">Benchmarks</th>
|
||||
<th>A.X 4.0 Light</th>
|
||||
<th>Qwen3-8B<br/>(w/o reasoning)</th>
|
||||
<th>Qwen2.5-7B</th>
|
||||
<th>EXAONE-3.5-7.8B</th>
|
||||
<th>Kanana-1.5-8B</th>
|
||||
</tr></thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td rowspan="6">Knowledge</td>
|
||||
<td>KMMLU</td>
|
||||
<td>64.15</td>
|
||||
<td>63.53</td>
|
||||
<td>49.56</td>
|
||||
<td>53.76</td>
|
||||
<td>48.28</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>KMMLU-pro</td>
|
||||
<td>50.28</td>
|
||||
<td>50.71</td>
|
||||
<td>38.87</td>
|
||||
<td>40.11</td>
|
||||
<td>37.63</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>KMMLU-redux</td>
|
||||
<td>56.05</td>
|
||||
<td>55.74</td>
|
||||
<td>38.58</td>
|
||||
<td>42.21</td>
|
||||
<td>35.33</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>CLIcK</td>
|
||||
<td>68.05</td>
|
||||
<td>62.71</td>
|
||||
<td>60.56</td>
|
||||
<td>64.30</td>
|
||||
<td>61.30</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>KoBALT</td>
|
||||
<td>30.29</td>
|
||||
<td>26.57</td>
|
||||
<td>21.57</td>
|
||||
<td>21.71</td>
|
||||
<td>23.14</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MMLU</td>
|
||||
<td>75.43</td>
|
||||
<td>82.89</td>
|
||||
<td>75.40</td>
|
||||
<td>72.20</td>
|
||||
<td>68.82</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="3">General</td>
|
||||
<td>Ko-MT-Bench</td>
|
||||
<td>79.50</td>
|
||||
<td>64.06</td>
|
||||
<td>61.31</td>
|
||||
<td>81.06</td>
|
||||
<td>76.30</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MT-Bench</td>
|
||||
<td>81.56</td>
|
||||
<td>65.69</td>
|
||||
<td>79.37</td>
|
||||
<td>83.50</td>
|
||||
<td>77.60</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>LiveBench</td>
|
||||
<td>37.10</td>
|
||||
<td>50.20</td>
|
||||
<td>37.00</td>
|
||||
<td>40.20</td>
|
||||
<td>29.40</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="2">Instruction Following</td>
|
||||
<td>Ko-IFEval</td>
|
||||
<td>72.99</td>
|
||||
<td>73.39</td>
|
||||
<td>60.73</td>
|
||||
<td>65.01</td>
|
||||
<td>69.96</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>IFEval</td>
|
||||
<td>84.68</td>
|
||||
<td>85.38</td>
|
||||
<td>76.73</td>
|
||||
<td>82.61</td>
|
||||
<td>80.11</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="2">Math</td>
|
||||
<td>HRM8K</td>
|
||||
<td>40.12</td>
|
||||
<td>52.50</td>
|
||||
<td>35.13</td>
|
||||
<td>31.88</td>
|
||||
<td>30.87</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MATH</td>
|
||||
<td>68.88</td>
|
||||
<td>71.48</td>
|
||||
<td>65.58</td>
|
||||
<td>63.20</td>
|
||||
<td>59.28</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="3">Code</td>
|
||||
<td>HumanEval+</td>
|
||||
<td>75.61</td>
|
||||
<td>77.44</td>
|
||||
<td>74.39</td>
|
||||
<td>76.83</td>
|
||||
<td>76.83</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MBPP+</td>
|
||||
<td>67.20</td>
|
||||
<td>62.17</td>
|
||||
<td>68.50</td>
|
||||
<td>64.29</td>
|
||||
<td>67.99</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>LiveCodeBench</td>
|
||||
<td>18.03</td>
|
||||
<td>23.93</td>
|
||||
<td>16.62</td>
|
||||
<td>17.98</td>
|
||||
<td>16.52</td>
|
||||
</tr>
|
||||
</tbody></table>
|
||||
|
||||
## 🚀 Quickstart
|
||||
|
||||
### with HuggingFace Transformers
|
||||
|
||||
- `transformers>=4.46.0` or the latest version is required to use `skt/A.X-4.0-Light`
|
||||
```bash
|
||||
pip install transformers>=4.46.0
|
||||
```
|
||||
|
||||
#### Example Usage
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "skt/A.X-4.0-Light"
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map="auto",
|
||||
)
|
||||
model.eval()
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": "당신은 사용자가 제공하는 영어 문장들을 한국어로 번역하는 AI 전문가입니다."},
|
||||
{"role": "user", "content": "The first human went into space and orbited the Earth on April 12, 1961."},
|
||||
]
|
||||
input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
|
||||
|
||||
with torch.no_grad():
|
||||
output = model.generate(
|
||||
input_ids,
|
||||
max_new_tokens=128,
|
||||
do_sample=False,
|
||||
)
|
||||
|
||||
len_input_prompt = len(input_ids[0])
|
||||
response = tokenizer.decode(output[0][len_input_prompt:], skip_special_tokens=True)
|
||||
print(response)
|
||||
# Output:
|
||||
# 1961년 4월 12일, 최초의 인간이 우주로 나가 지구를 공전했습니다.
|
||||
```
|
||||
|
||||
### with vLLM
|
||||
|
||||
- `vllm>=v0.6.4.post1` or the latest version is required to use tool-use function
|
||||
```bash
|
||||
pip install vllm>=v0.6.4.post1
|
||||
# if you don't want to activate tool-use function, just commenting out below vLLM option
|
||||
VLLM_OPTION="--enable-auto-tool-choice --tool-call-parser hermes"
|
||||
vllm serve skt/A.X-4.0-Light $VLLM_OPTION
|
||||
```
|
||||
|
||||
#### Example Usage
|
||||
|
||||
```python
|
||||
from openai import OpenAI
|
||||
|
||||
def call(messages, model):
|
||||
completion = client.chat.completions.create(
|
||||
model=model,
|
||||
messages=messages,
|
||||
)
|
||||
print(completion.choices[0].message)
|
||||
|
||||
client = OpenAI(
|
||||
base_url="http://localhost:8000/v1",
|
||||
api_key="api_key"
|
||||
)
|
||||
model = "skt/A.X-4.0-Light"
|
||||
messages = [{"role": "user", "content": "에어컨 여름철 적정 온도는? 한줄로 답변해줘"}]
|
||||
call(messages, model)
|
||||
# Output:
|
||||
# ChatCompletionMessage(content='여름철 적정 에어컨 온도는 일반적으로 24-26도입니다.', refusal=None, role='assistant', audio=None, function_call=None, tool_calls=[], reasoning_content=None)
|
||||
|
||||
messages = [{"role": "user", "content": "What is the appropriate temperature for air conditioning in summer? Response in a single sentence."}]
|
||||
call(messages, model)
|
||||
# Output:
|
||||
# ChatCompletionMessage(content='The appropriate temperature for air conditioning in summer generally ranges from 72°F to 78°F (22°C to 26°C) for comfort and energy efficiency.', refusal=None, role='assistant', audio=None, function_call=None, tool_calls=[], reasoning_content=None)
|
||||
```
|
||||
|
||||
#### Examples for tool-use
|
||||
```python
|
||||
from openai import OpenAI
|
||||
|
||||
|
||||
def call(messages, model):
|
||||
completion = client.chat.completions.create(
|
||||
model=model,
|
||||
messages=messages,
|
||||
tools=tools
|
||||
)
|
||||
print(completion.choices[0].message)
|
||||
|
||||
|
||||
client = OpenAI(
|
||||
base_url="http://localhost:8000/v1",
|
||||
api_key="api_key"
|
||||
)
|
||||
model = "skt/A.X-4.0-Light"
|
||||
|
||||
calculate_discount = {
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "calculate_discount",
|
||||
"description": "원가격과 할인율(퍼센트 단위)을 입력받아 할인된 가격을계산한다.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"original_price": {
|
||||
"type": "number",
|
||||
"description": "상품의 원래 가격"
|
||||
},
|
||||
"discount_percentage": {
|
||||
"type": "number",
|
||||
"description": "적용할 할인율(예: 20% 할인의 경우 20을 입력)"
|
||||
}
|
||||
},
|
||||
"required": ["original_price", "discount_percentage"]
|
||||
}
|
||||
}
|
||||
}
|
||||
get_exchange_rate = {
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_exchange_rate",
|
||||
"description": "두 통화 간의 환율을 가져온다.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"base_currency": {
|
||||
"type": "string",
|
||||
"description": "The currency to convert from."
|
||||
},
|
||||
"target_currency": {
|
||||
"type": "string",
|
||||
"description": "The currency to convert to."
|
||||
}
|
||||
},
|
||||
"required": ["base_currency", "target_currency"]
|
||||
}
|
||||
}
|
||||
}
|
||||
tools = [calculate_discount, get_exchange_rate]
|
||||
|
||||
### Slot filling ###
|
||||
messages = [{"role": "user", "content": "우리가 뭘 사야되는데 원래 57600원인데 직원할인 받을 수 있거든? 할인가좀 계산해줘"}]
|
||||
call(messages, model)
|
||||
# Output:
|
||||
# ChatCompletionMessage(content='할인율을 알려주시겠습니까?', refusal=None, role='assistant', audio=None, function_call=None, tool_calls=[], reasoning_content=None)
|
||||
|
||||
|
||||
### Function calling ###
|
||||
messages = [
|
||||
{"role": "user", "content": "우리가 뭘 사야되는데 원래 57600원인데 직원할인 받을 수 있거든? 할인가좀 계산해줘"},
|
||||
{"role": "assistant", "content": "할인율을 알려주시겠습니까?"},
|
||||
{"role": "user", "content": "15% 할인 받을 수 있어."},
|
||||
]
|
||||
call(messages, model)
|
||||
# Output:
|
||||
# ChatCompletionMessage(content=None, refusal=None, role='assistant', audio=None, function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='chatcmpl-tool-7778d1d9fca94bf2acbb44c79359502c', function=Function(arguments='{"original_price": 57600, "discount_percentage": 15}', name='calculate_discount'), type='function')], reasoning_content=None)
|
||||
|
||||
|
||||
### Completion ###
|
||||
messages = [
|
||||
{"role": "user", "content": "우리가 뭘 사야되는데 원래 57600원인데 직원할인 받을 수 있거든? 할인가좀 계산해줘"},
|
||||
{"role": "assistant", "content": "할인율을 알려주시겠습니까?"},
|
||||
{"role": "user", "content": "15% 할인 받을 수 있어."},
|
||||
{"role": "tool", "tool_call_id": "random_id", "name": "calculate_discount", "content": "{\"original_price\": 57600, \"discount_percentage\": 15, \"discounted_price\": 48960.0}"}
|
||||
]
|
||||
call(messages, model)
|
||||
# Output:
|
||||
# ChatCompletionMessage(content='57600원의 상품에서 15% 할인을 적용하면, 할인된 가격은 48960원입니다.', refusal=None, role='assistant', audio=None, function_call=None, tool_calls=[], reasoning_content=None)
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
The `A.X 4.0 Light` model is licensed under `Apache License 2.0`.
|
||||
|
||||
## Citation
|
||||
```
|
||||
@article{SKTAdotX4Light,
|
||||
title={A.X 4.0 Light},
|
||||
author={SKT AI Model Lab},
|
||||
year={2025},
|
||||
url={https://huggingface.co/skt/A.X-4.0-Light}
|
||||
}
|
||||
```
|
||||
|
||||
## Contact
|
||||
|
||||
- Business & Partnership Contact: [a.x@sk.com](a.x@sk.com)
|
||||
BIN
assets/A.X_logo.png
Normal file
BIN
assets/A.X_logo.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 71 KiB |
3
assets/A.X_logo_ko_4x3.png
Normal file
3
assets/A.X_logo_ko_4x3.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:45eecde59e22d7be0f8a451c2cd7bb7f1526e0bb5b021ed202ce12c0838fc53d
|
||||
size 182884
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 16384,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.3",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 102400
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 27,
|
||||
"max_new_tokens": 16384,
|
||||
"pad_token_id": 1,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
102104
merges.txt
Normal file
102104
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2f80502d7d801be45497f1391d82f0ff2e4afb7f0c26cbe988fcd3455d768655
|
||||
size 4987786168
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1725192e45669b4b6ee825aaa79832a82b2f92e9dac18a68a7f69d0bcfa5feec
|
||||
size 4932751024
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cfdeb1f54032d8b6a34b235a4f9f2a67325b1a3dfc26f7d271964ae1b1950822
|
||||
size 4598751568
|
||||
346
model.safetensors.index.json
Normal file
346
model.safetensors.index.json
Normal file
@@ -0,0 +1,346 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14519249920
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
88
special_tokens_map.json
Normal file
88
special_tokens_map.json
Normal file
@@ -0,0 +1,88 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|pad|>",
|
||||
"<|unk|>",
|
||||
"<|sep|>",
|
||||
"<|mask|>",
|
||||
"<|cls|>",
|
||||
"<|image|>",
|
||||
"<|audio|>",
|
||||
"<|user|>",
|
||||
"<|system|>",
|
||||
"<|assistant|>",
|
||||
"<|extra_id_0|>",
|
||||
"<|extra_id_1|>",
|
||||
"<|extra_id_2|>",
|
||||
"<|extra_id_3|>",
|
||||
"<|extra_id_4|>",
|
||||
"<|extra_id_5|>",
|
||||
"<|extra_id_6|>",
|
||||
"<|extra_id_7|>",
|
||||
"<|extra_id_8|>",
|
||||
"<|extra_id_9|>",
|
||||
"<|extra_id_10|>",
|
||||
"<|extra_id_13|>",
|
||||
"<|im_start|>",
|
||||
"<|im_sep|>",
|
||||
"<|im_end|>",
|
||||
"<|resident_reg|>",
|
||||
"<|foreigner_reg|>",
|
||||
"<|business_reg|>",
|
||||
"<|credit_card|>",
|
||||
"<|passport|>",
|
||||
"<|driver_license|>",
|
||||
"<|telephone|>",
|
||||
"<|health_insurance|>",
|
||||
"<|bank_account|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"cls_token": {
|
||||
"content": "<|cls|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"mask_token": {
|
||||
"content": "<|mask|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"sep_token": {
|
||||
"content": "<|sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|unk|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
511221
tokenizer.json
Normal file
511221
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
385
tokenizer_config.json
Normal file
385
tokenizer_config.json
Normal file
@@ -0,0 +1,385 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|unk|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<|sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<|mask|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<|cls|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<|image|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<|audio|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<|user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<|system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<|assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<|extra_id_0|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "<|extra_id_1|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "<|extra_id_2|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "<|extra_id_3|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "<|extra_id_4|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "<|extra_id_5|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"17": {
|
||||
"content": "<|extra_id_6|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"18": {
|
||||
"content": "<|extra_id_7|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"19": {
|
||||
"content": "<|extra_id_8|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"20": {
|
||||
"content": "<|extra_id_9|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"21": {
|
||||
"content": "<|extra_id_10|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"22": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"23": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"24": {
|
||||
"content": "<|extra_id_13|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"25": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"26": {
|
||||
"content": "<|im_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"27": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"28": {
|
||||
"content": "<|resident_reg|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"29": {
|
||||
"content": "<|foreigner_reg|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"30": {
|
||||
"content": "<|business_reg|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"31": {
|
||||
"content": "<|credit_card|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32": {
|
||||
"content": "<|passport|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"33": {
|
||||
"content": "<|driver_license|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"34": {
|
||||
"content": "<|telephone|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"35": {
|
||||
"content": "<|health_insurance|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"36": {
|
||||
"content": "<|bank_account|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"37": {
|
||||
"content": "</tool_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"38": {
|
||||
"content": "<tool_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"39": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"40": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|pad|>",
|
||||
"<|unk|>",
|
||||
"<|sep|>",
|
||||
"<|mask|>",
|
||||
"<|cls|>",
|
||||
"<|image|>",
|
||||
"<|audio|>",
|
||||
"<|user|>",
|
||||
"<|system|>",
|
||||
"<|assistant|>",
|
||||
"<|extra_id_0|>",
|
||||
"<|extra_id_1|>",
|
||||
"<|extra_id_2|>",
|
||||
"<|extra_id_3|>",
|
||||
"<|extra_id_4|>",
|
||||
"<|extra_id_5|>",
|
||||
"<|extra_id_6|>",
|
||||
"<|extra_id_7|>",
|
||||
"<|extra_id_8|>",
|
||||
"<|extra_id_9|>",
|
||||
"<|extra_id_10|>",
|
||||
"<|extra_id_13|>",
|
||||
"<|im_start|>",
|
||||
"<|im_sep|>",
|
||||
"<|im_end|>",
|
||||
"<|resident_reg|>",
|
||||
"<|foreigner_reg|>",
|
||||
"<|business_reg|>",
|
||||
"<|credit_card|>",
|
||||
"<|passport|>",
|
||||
"<|driver_license|>",
|
||||
"<|telephone|>",
|
||||
"<|health_insurance|>",
|
||||
"<|bank_account|>"
|
||||
],
|
||||
"bos_token": "<|endoftext|>",
|
||||
"chat_template": "{%- if tools is iterable and tools | length > 0 %}\n {{- '<|im_start|><|system|>'}}\n {{- '당신은 도구 호출 기능을 갖춘 유용한 도우미입니다. 사용자의 요청을 처리하기 위해서 필요한 도구가 주어진 목록에 있는 경우 도구 호출로 응답하세요.\n필요한 도구가 목록에 없는 경우에는 도구 호출 없이 사용자가 요구한 정보를 제공하세요.\n필요한 도구가 목록에 있지만 해당 도구를 호출하는데 필요한 argument 정보가 부족한 경우 해당 정보를 사용자에게 요청하세요.\n사용자의 요청을 처리하기 위해 여러번 도구를 호출할 수 있어야 합니다.\n도구 호출 이후 도구 실행 결과를 입력으로 받으면 해당 결과를 활용하여 답변을 생성하세요.\n\n다음은 접근할 수 있는 도구들의 목록 입니다:\n<tools>\n'}}\n {%- for t in tools %}\n {{- t | tojson }}\n {{- '\n' }}\n {%- endfor %}\n {{- '</tools>' }}\n {{- '\n\n도구를 호출하려면 아래의 JSON으로 응답하세요.\n도구 호출 형식: <tool_call>{\"name\": 도구 이름, \"arguments\": dictionary 형태의 도구 인자값}</tool_call>' }}\n {{- '<|im_end|>' }}\n {%- endif %}\n \n {%- for message in messages %}\n {%- if message.role == 'system' %}\n {{- '<|im_start|><|system|>' + message.content + '<|im_end|>'}}\n {%- elif message.role == 'user' %}\n {{- '<|im_start|><|user|>' + message.content + '<|im_end|>'}}\n {%- elif message.role == 'assistant' %}\n {{- '<|im_start|><|assistant|>'}}\n {%- set content = '' %}\n {%- if message.content is defined %}\n {%- set content = message.content %}\n {%- endif %}\n \n {%- if add_generation_prompt and not (message.reasoning_content is defined and message.reasoning_content is not none) %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>'.strip())[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n \n {{- content}}\n {%- if message.tool_calls is defined %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>' }}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {%- if tool_call.arguments is defined %}\n {{- ', ' }}\n {{- '\"arguments\": ' }}\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 {{- '<|im_start|><|extra_id_13|><tool_output>' + message.content + '</tool_output><|im_end|>'}}\n {%- endif %}\n {%- endfor %}\n \n {%- if add_generation_prompt %}\n {{- '<|im_start|><|assistant|>' }}\n {%- endif %}",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"cls_token": "<|cls|>",
|
||||
"eod_token": "<|endoftext|>",
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"mask_token": "<|mask|>",
|
||||
"model_max_length": 16384,
|
||||
"pad_token": "<|pad|>",
|
||||
"sep_token": "<|sep|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|unk|>",
|
||||
"vocab_size": 102400
|
||||
}
|
||||
102402
vocab.json
Normal file
102402
vocab.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user