skt/A.X-3.1
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: skt/A.X-3.1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-17 10:33:00 +08:00
commit c262f3b982
27 changed files with 615149 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.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_from_scratch_logo_ko_4x3.png filter=lfs diff=lfs merge=lfs -text

226
LICENSE Normal file
View File

@@ -0,0 +1,226 @@
Copyright (c) 2025 SK Telecom Co., Ltd. All rights reserved.
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.
================================================================================
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 2025 SK Telecom Co.
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.

562
README.md Normal file
View File

@@ -0,0 +1,562 @@
---
license: apache-2.0
license_link: https://huggingface.co/skt/A.X-3.1/blob/main/LICENSE
language:
- en
- ko
pipeline_tag: text-generation
library_name: transformers
model_id: skt/A.X-3.1
developers: SKT AI Model Lab
model-index:
- name: A.X-3.1
results:
- task:
type: generate_until
name: mmlu
dataset:
name: mmlu (chat CoT)
type: hails/mmlu_no_train
metrics:
- type: exact_match
value: 75.1
name: exact_match
- task:
type: generate_until
name: kmmlu
dataset:
name: kmmlu (chat CoT)
type: HAERAE-HUB/KMMLU
metrics:
- type: exact_match
value: 69.2
name: exact_match
---
# A.X 3.1
<div align="center">
<img src="./assets/A.X_from_scratch_logo_ko_4x3.png" alt="A.X Logo" width="300"/>
</div>
<p align="center"> <a href="https://huggingface.co/collections/skt/ax-3-686b288b3b05e1234f3f4c73">🤗 Models</a> | <a href="https://github.com/SKT-AI/A.X-3">🖥️ Github</a> </p>
## A.X 3.1 Highlights
SK Telecom released **A.X 3.1** (pronounced "A dot X"), a large language model (LLM) optimized for Korean-language understanding and enterprise deployment, on July 24, 2025.
This sovereign AI model was developed entirely in-house by SKT, encompassing model architecture, data curation, and training, all carried out on SKT’s proprietary supercomputing infrastructure, TITAN.
The model was trained from scratch on a high-quality multilingual corpus comprising **2.1 trillion tokens**, with a primary focus on the Korean language.
- **Authentic Korean Sovereign AI**: A.X 3.1 was trained on a high-quality multilingual dataset—fully curated in-house—using SKT’s proprietary GPU infrastructure.
- **Highly Efficient Multilingual LLM**: A.X 3.1 demonstrates superior performance among Korean LLMs, despite its relatively compact training size of 2.1 trillion tokens.
- **Superior Korean Proficiency**: A.X 3.1 achieved a score of **69.2** on the [KMMLU](https://huggingface.co/datasets/HAERAE-HUB/KMMLU): the leading benchmark for Korean-language evaluation and a Korean-specific adaptation of MMLU, outperforming other Korean-specified models.
- **Deep Korean Understanding**: A.X 3.1 obtained **77.4** on the [CLIcK](https://huggingface.co/datasets/EunsuKim/CLIcK): a benchmark for Korean cultural and contextual comprehension, outperforming other open-source models.
- **Efficient Token Usage**: A.X 3.1 requires approximately 33% fewer tokens than GPT-4o to process equivalent Korean inputs, facilitating more cost-effective and computationally efficient inference.
- **Long-Context Handling**: A.X 3.1 supports up to **32,768 tokens** natively, and up to **131,072 tokens** by applying YaRN.
## Core Technologies
A.X 3.1 represents **an efficient sovereign AI model**, developed end-to-end by SKT, encompassing model architecture, data curation, infrastructure deployment, and optimization.
### Model Architecture Specs
<table><thead>
<tr>
<th>Model</th>
<th># Params</th>
<th># Layers</th>
<th># KV-Heads</th>
<th>Hidden Dim</th>
<th>FFN Dim</th>
</tr>
<tr>
<th>A.X 3.1</th>
<th>34B</th>
<th>48</th>
<th>8</th>
<th>8192</th>
<th>21824</th>
</tr>
</thead>
</table>
### High-Quality Data Pipeline & Strategic Mixture
- We collected and curated a training dataset comprising 20 trillion tokens sourced from diverse domains.
- The entire dataset was processed through SKT’s proprietary data pipeline, incorporating synthetic data generation and comprehensive quality filtering.
- For training A.X 3.1, a total of **2.1 trillion tokens** were utilized, comprising a Korean-focused multilingual corpus.
## Benchmark Results
### Model Performance
<table>
<caption style="text-align:left; caption-side:bottom">* self-reported score</caption>
<thead>
<tr>
<th></th>
<th></th>
<th>A.X 3.1</th>
<th>EXAONE-3.5-32B</th>
<th>Kanana-flag-32.5B</th>
<th>Gemma-3-27B</th>
<th>Qwen2.5-32B</th>
</tr></thead>
<tbody>
<tr>
<td rowspan="5">Knowledge</td>
<td>KMMLU</td>
<td>69.73</td>
<td>57.17</td>
<td>64.19*</td>
<td>59.45</td>
<td>61.93</td>
</tr>
<tr>
<td>KMMLU-pro</td>
<td>54.89</td>
<td>45.39</td>
<td>-</td>
<td>50.43</td>
<td>52.34</td>
</tr>
<tr>
<td>KMMLU-redux</td>
<td>62.66</td>
<td>48.32</td>
<td>-</td>
<td>54.85</td>
<td>52.15</td>
</tr>
<tr>
<td>Click (chat CoT)</td>
<td>77.09</td>
<td>69.42</td>
<td>-</td>
<td>71.03</td>
<td>68.17</td>
</tr>
<tr>
<td>MMLU</td>
<td>75.20</td>
<td>77.1</td>
<td>81.08*</td>
<td>82.35</td>
<td>83.4</td>
</tr>
<tr>
<td rowspan="2">General</td>
<td>Ko-MT-bench</td>
<td>83.06</td>
<td>80.19</td>
<td>80.58*</td>
<td>85.5</td>
<td>72.88</td>
</tr>
<tr>
<td>MT-bench</td>
<td>84.19</td>
<td>85.09</td>
<td>83.56*</td>
<td>84.38</td>
<td>87.31</td>
</tr>
<tr>
<td rowspan="2">IF</td>
<td>Ko-IFEval</td>
<td>75.29</td>
<td>68.67</td>
<td>-</td>
<td>74.4</td>
<td>73.24</td>
</tr>
<tr>
<td>IFEval</td>
<td>87.11</td>
<td>82.67</td>
<td>85.6*</td>
<td>82.45</td>
<td>82.27</td>
</tr>
<tr>
<td rowspan="2">Math<br> </td>
<td>HRM8K</td>
<td>45.53</td>
<td>36.3</td>
<td>-</td>
<td>48</td>
<td>41.29</td>
</tr>
<tr>
<td>MATH</td>
<td>75.40</td>
<td>61.64</td>
<td>57.82*</td>
<td>80.72</td>
<td>73.26</td>
</tr>
<tr>
<td rowspan="3">Code<br> <br> </td>
<td>HumanEval+</td>
<td>75.00</td>
<td>77.44</td>
<td>77.44*</td>
<td>78.66</td>
<td>82.32</td>
</tr>
<tr>
<td>MBPP+</td>
<td>70.90</td>
<td>65.87</td>
<td>69.84*</td>
<td>74.07</td>
<td>73.81</td>
</tr>
<tr>
<td>LiveCodeBench</td>
<td>23.34</td>
<td>17.2</td>
<td>-</td>
<td>30.55</td>
<td>26.9</td>
</tr>
</tbody></table>
### Lightweight Model Performance
<table><thead>
<tr>
<th colspan="2">Benchmarks</th>
<th>A.X 3.1 Light</th>
<th>Kanana-1.5-8B</th>
<th>EXAONE-3.5-7.8B</th>
<th>Qwen2.5-7B</th>
<th>Qwen3-8B<br>(w/o reasoning)</th>
</tr></thead>
<tbody>
<tr>
<td rowspan="6">Knowledge</td>
<td>KMMLU</td>
<td>61.70</td>
<td>48.28</td>
<td>53.76</td>
<td>49.56</td>
<td>63.53</td>
</tr>
<tr>
<td>KMMLU-pro</td>
<td>45.54</td>
<td>37.63</td>
<td>40.11</td>
<td>38.87</td>
<td>50.71</td>
</tr>
<tr>
<td>KMMLU-redux</td>
<td>52.34</td>
<td>35.33</td>
<td>42.21</td>
<td>38.58</td>
<td>55.74</td>
</tr>
<tr>
<td>CLIcK</td>
<td>71.22</td>
<td>61.30</td>
<td>64.11</td>
<td>58.30</td>
<td>63.31</td>
</tr>
<tr>
<td>KoBALT</td>
<td>27.43</td>
<td>23.14</td>
<td>21.71</td>
<td>21.57</td>
<td>26.57</td>
</tr>
<tr>
<td>MMLU</td>
<td>66.95</td>
<td>68.82</td>
<td>72.20</td>
<td>75.40</td>
<td>82.89</td>
</tr>
<tr>
<td rowspan="2">General</td>
<td>Ko-MT-Bench</td>
<td>78.56</td>
<td>76.30</td>
<td>81.06</td>
<td>61.31</td>
<td>64.06</td>
</tr>
<tr>
<td>MT-Bench</td>
<td>74.38</td>
<td>77.60</td>
<td>83.50</td>
<td>79.37</td>
<td>65.69</td>
</tr>
<tr>
<td rowspan="2">Instruction<br>Following</td>
<td>Ko-IFEval</td>
<td>70.04</td>
<td>69.96</td>
<td>65.01</td>
<td>60.73</td>
<td>73.39</td>
</tr>
<tr>
<td>IFEval</td>
<td>79.86</td>
<td>80.11</td>
<td>82.61</td>
<td>76.73</td>
<td>85.38</td>
</tr>
<tr>
<td rowspan="2">Math</td>
<td>HRM8K</td>
<td>41.70</td>
<td>30.87</td>
<td>31.88</td>
<td>35.13</td>
<td>52.50</td>
</tr>
<tr>
<td>MATH</td>
<td>70.14</td>
<td>59.28</td>
<td>63.20</td>
<td>65.58</td>
<td>71.48</td>
</tr>
<tr>
<td rowspan="2">Code<br></td>
<td>HumanEval+</td>
<td>73.78</td>
<td>76.83</td>
<td>76.83</td>
<td>74.39</td>
<td>77.44</td>
</tr>
<tr>
<td>MBPP+</td>
<td>61.64</td>
<td>67.99</td>
<td>64.29</td>
<td>68.50</td>
<td>62.17</td>
</tr>
</tbody></table>
## 🚀 Quickstart
### with HuggingFace Transformers
- `transformers>=4.46.0` or the latest version is required to use `skt/A.X-3.1`
```bash
pip install transformers>=4.46.0
```
#### Example Usage
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "skt/A.X-3.1"
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:
# 우주에서 인간이 처음으로 지구 궤도를 돈 날은 1961년 4월 12일입니다.
```
### with vLLM
- `vllm>=v0.6.4.post1` or the latest version is required to use tool-use feature
```bash
pip install vllm>=v0.6.4.post1
# if you don't want to activate tool-use feature, just commenting out below vLLM option
VLLM_OPTION="--enable-auto-tool-choice --tool-call-parser hermes"
vllm serve skt/A.X-3.1 $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-3.1"
messages = [{"role": "user", "content": "에어컨 여름철 적정 온도는? 한줄로 답변해줘"}]
call(messages, model)
# Output:
# 여름철 에어컨 적정 온도는 24~26도입니다.
messages = [{"role": "user", "content": "What is the appropriate temperature for air conditioning in summer? Respond in a single sentence."}]
call(messages, model)
# Output:
# The appropriate temperature for air conditioning in summer is around 78°F (26°C).
```
#### 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-3.1"
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"
}
},
"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 원가가 57600원인데 직원할인 받으면 얼마야?"}]
call(messages, model)
# Output:
# ChatCompletionMessage(content='직원 할인율이 몇 퍼센트인지 알려주신다면 할인된 가격을 계산할 수 있습니다. 할인율이 몇 퍼센트인지 알려주실 수 있나요?', role='assistant', tool_calls=[])
### Function calling ###
messages = [
{"role": "user", "content": "우리가 뭘 사야되는데 원가가 57600원인데 직원할인 받으면 얼마야?"},
{"role": "assistant", "content": "직원 할인율이 몇 퍼센트인지 알려주신다면 할인된 가격을 계산할 수 있습니다. 할인율이 몇 퍼센트인지 알려주실 수 있나요?"},
{"role": "user", "content": "15% 할인 받을 수 있어."},
]
call(messages, model)
# Output:
# ChatCompletionMessage(content=None, role='assistant', tool_calls=[ChatCompletionMessageToolCall(id='chatcmpl-tool-cb9e827f752d4725abc94377223b2b0f', function=Function(arguments='{"original_price": 57600, "discount_percentage": 15}', name='calculate_discount'), type='function')])
### Completion ###
messages = [
{"role": "user", "content": "우리가 뭘 사야되는데 원가가 57600원인데 직원할인 받으면 얼마야?"},
{"role": "assistant", "content": "직원 할인율이 몇 퍼센트인지 알려주신다면 할인된 가격을 계산할 수 있습니다. 할인율이 몇 퍼센트인지 알려주실 수 있나요?"},
{"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='직원 할인을 받으면 57600원의 상품은 15% 할인을 받아 48960원이 됩니다.', role='assistant', tool_calls=[])
```
### Extend supported token length
The `config.json` file of A.X 3.1 uploaded to HuggingFace is configured for maximum token lengths of 32,768. You can simply handle up to 131,072 tokens by modifying `rope_scaling` field in `config.json` file into the following parameters:
```
"rope_scaling": {
"type": "yarn",
"factor": 4.0,
"original_max_position_embeddings": 32768,
},
```
## License
The `A.X 3.1` model is licensed under `Apache License 2.0`.
## Citation
```
@article{SKTAdotX3.1,
title={A.X 3.1},
author={SKT AI Model Lab},
year={2025},
url={https://huggingface.co/skt/A.X-3.1}
}
```
## Contact
- Business & Partnership Contact: [a.x@sk.com](a.x@sk.com)

3
assets/A.X_from_scratch_logo_ko_4x3.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e41e606567955055a7085c604d922728c926412eafe970faf1d1ec6a62f78b4
size 163775

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.1,
"bos_token_id": 0,
"eos_token_id": 0,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 21824,
"max_position_embeddings": 32768,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 48,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": false,
"vocab_size": 102400
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"bos_token_id": 0,
"eos_token_id": 27,
"max_new_tokens": 28000,
"pad_token_id": 1,
"transformers_version": "4.51.3"
}

102104
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5af27f1de3587cf2f7f6adb1a57ec8d195945c34d9b4a65d54b6f17370a0638a
size 4729145992

3
model-00002-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ccfca12db8238a145e00162c90a3cc2828d48c10f426a68aedd822eaadff3674
size 4839279920

3
model-00003-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8840073b04df6688afb127dcf8c11e52cb01eea30e17ccfdfffd397ef8efdd6c
size 4783738744

3
model-00004-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e916002f5ddb6427605c7e61bff22e01d79ef84175c8e469f0041b8f46311fdb
size 4839279944

3
model-00005-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:736d142f43c2f4d32b7bcf5445264d1e6103fe81b5dd17b73a3c36efab0214f7
size 4783738776

3
model-00006-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:07baf531c43e17f6eb107636d73047ff7a2989bc11456ffe0d54232c93526c69
size 4839279944

3
model-00007-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:259e3d600b1f9f25bbbfbb1721707814a1be2b4dde0e9b4d4bea29363bdee7eb
size 4783738776

3
model-00008-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:afe8f2779fa30814a4cbb7534117b447338ae15bf48a2cfdeda8d172952f9656
size 4839279944

3
model-00009-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6ee8f88de5b09e752a5b4d64eb4bfb09bf5dcbc3d911a3cdae0177c19bcc70ea
size 4783738776

3
model-00010-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f62701a5e81ffd23534df25bffbdb78ca3bc33970dd40e6b51ca5b7ad4c40f1
size 4839279944

3
model-00011-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b9ad98dcf1bb9656267deaba2781aba85f7b804511dd45d87b0c4f560324637
size 4783738776

3
model-00012-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eab76a1631f34db3c7c1ce6e3c1ca0f6cb3139b646054d456547462ccf171260
size 4839279944

3
model-00013-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c837805765a9d070695869106cbde43aefa7ce00972ec082a0e93d2c8b60a53e
size 4783738776

3
model-00014-of-00015.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5dac245c497ec34841d1665a6500bfce7e44c74f0bbc89c4b69a7e0f24ec7406
size 4839279944

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:60c1c4c035eff40ceaa44e759eaa296ed63139b321103c5a7e08b0a3252841fe
size 2035335736

442
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,442 @@
{
"metadata": {
"total_size": 69341822976
},
"weight_map": {
"lm_head.weight": "model-00015-of-00015.safetensors",
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.10.input_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.11.input_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.12.input_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.13.input_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.14.input_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.15.input_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.16.input_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
"model.layers.17.input_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.18.input_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.19.input_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
"model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
"model.layers.20.input_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.21.input_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.22.input_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.23.input_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
"model.layers.24.input_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.25.input_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.26.input_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
"model.layers.27.input_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.28.input_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.29.input_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.30.input_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
"model.layers.31.input_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.32.input_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.33.input_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
"model.layers.34.input_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.35.input_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.36.input_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.37.input_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
"model.layers.38.input_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.39.input_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.40.input_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.40.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.40.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.40.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.40.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.40.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.40.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.40.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.40.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
"model.layers.41.input_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.41.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.41.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.41.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.41.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.41.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.41.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.41.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.41.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.42.input_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.42.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.42.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.42.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.42.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.42.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.42.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.42.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.42.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.43.input_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.43.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.43.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.43.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.43.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
"model.layers.43.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.43.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.43.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.43.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.44.input_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.44.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.44.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.44.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.44.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.44.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.44.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.44.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.44.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
"model.layers.45.input_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.45.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.45.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.45.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.45.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.45.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.45.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.45.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.45.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.46.input_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.46.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.46.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.46.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.46.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
"model.layers.46.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.46.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.46.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.46.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.47.input_layernorm.weight": "model-00015-of-00015.safetensors",
"model.layers.47.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
"model.layers.47.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.47.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.47.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
"model.layers.47.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.47.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.47.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.47.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
"model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
"model.layers.6.input_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.input_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
"model.norm.weight": "model-00015-of-00015.safetensors"
}
}

76
special_tokens_map.json Normal file
View File

@@ -0,0 +1,76 @@
{
"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": "<|im_end|>",
"mask_token": {
"content": "<|mask|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<|pad|>",
"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
}
}

511231
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

387
tokenizer_config.json Normal file
View File

@@ -0,0 +1,387 @@
{
"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",
"extra_special_tokens": {},
"mask_token": "<|mask|>",
"max_length": 7680,
"model_max_length": 32768,
"pad_token": "<|pad|>",
"sep_token": "<|sep|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|unk|>",
"vocab_size": 102400
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long