A.X 3.1 Light

🚀 A.X 3.1 Light

A.X 3.1 Light is a lightweight large language model (LLM) optimized for Korean - language understanding and enterprise deployment. It offers high - efficiency and cost - effective compute usage, with strong performance in multiple benchmarks.

✨ Features

• Authentic Korean Sovereign AI: Trained on a high - quality multilingual dataset curated in - house using SKT’s proprietary GPU infrastructure.
• Highly Efficient Multilingual LLM: Demonstrates superior performance among open - source Korean LLMs, despite a relatively compact training size of 1.65 trillion tokens.
• Superior Korean Proficiency: Achieved a score of 61.7 on the [KMMLU](https://huggingface.co/datasets/HAERAE - HUB/KMMLU), outperforming other Korean - specified models.
• Deep Korean Understanding: Obtained 27.43 on the [KoBALT - 700](https://huggingface.co/datasets/snunlp/KoBALT - 700), outperforming other Korean - specialized models.
• Efficient Token Usage: Requires approximately 33% fewer tokens than GPT - 4o to process equivalent Korean inputs.
• Long - Context Handling: Supports up to 32,768 tokens.

🔧 Technical Details

Model Architecture Specs

High - Quality Data Pipeline & Strategic Mixture

• A training dataset of 20 trillion tokens from diverse domains was collected and curated.
• The entire dataset was processed through SKT’s proprietary data pipeline, including synthetic data generation and comprehensive quality filtering.
• A total of 1.65 trillion tokens from a Korean - focused multilingual corpus were used for training A.X 3.1 Light.

Pareto - Optimal Compute Efficiency

A.X 3.1 Light has 5 to 6 times lower computational cost compared to models with similar performance levels. Rigorous data curation and two - stage training with STEM - focused data enabled competitive performance at reduced FLOPs.

📚 Documentation

Benchmark Results

📦 Installation

with HuggingFace Transformers

• transformers>=4.46.0 or the latest version is required to use skt/A.X - 3.1 - Light

pip install transformers>=4.46.0

with vLLM

• vllm>=v0.6.4.post1 or the latest version is required to use tool - use feature

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-Light $VLLM_OPTION

💻 Usage Examples

Basic Usage

with HuggingFace Transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "skt/A.X-3.1-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 우주에 나가 지구를 궤도를 돌았습니다.

with vLLM

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-Light"
messages = [{"role": "user", "content": "에어컨 여름철 적정 온도는? 한줄로 답변해줘"}]
call(messages, model)
# Output:
# 에어컨 여름철 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 generally set between 24 to 26°C for optimal comfort and energy efficiency.

Advanced Usage (Examples for tool - use)

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-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"
                }
            },
            "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 할인을 적용하기 위해서는 할인율을 알 수 있어야 합니다. 할인율을 알려주실 수 있나요?', role='assistant', function_call=None, tool_calls=[], reasoning_content=None)


### Function calling ###
messages = [
    {"role": "user", "content": "우리가 뭘 사야되는데 원가가 57600원인데 직원할인 받으면 얼마야?"},
    {"role": "assistant", "content": "직원 할인을 적용하기 위해서는 할인율을 알 수 있어야 합니다. 할인율을 알려주실 수 있나요?"},
    {"role": "user", "content": "15% 할인 받을 수 있어."},
]
call(messages, model)
# Output: 
# ChatCompletionMessage(content=None, role='assistant', function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='chatcmpl-tool-3ebf11847364450daf363039db80cc50', 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 원가가 57600원인데 직원할인 받으면 얼마야?"},
    {"role": "assistant", "content": ""},
    {"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='57,600원의 상품에 15% 할인을 적용하면, 할인된 가격은 48,960원입니다.', role='assistant', function_call=None, tool_calls=[], reasoning_content=None)

📄 License

The A.X 3.1 Light model is licensed under Apache License 2.0.

Citation

@article{SKTAdotX3.1Light,
  title={A.X 3.1 Light},
  author={SKT AI Model Lab},
  year={2025},
  url={https://huggingface.co/skt/A.X-3.1-Light}
}

Contact

• Business & Partnership Contact: a.x@sk.com