NC-AI-consortium-VAETKI/VAETKI

VAETKI 모델 소개

VAETKI는 NC-AI를 중심으로 총 13개 기관이 참여하는 NC-AI 컨소시엄에서 공동 개발한 대규모 언어 모델입니다. 대규모 협력 체계를 기반으로 구축된 VAETKI는 효율성과 확장성을 핵심 목표로 설계되었으며, 이를 위해 Mixture-of-Experts(MoE) 아키텍처를 채택하였습니다.

VAETKI는 연구 및 실서비스 환경 모두를 고려해 설계된 모델로서, 향후 고난도 추론 중심 태스크, 전문 지식 기반 응용, 에이전트형 활용 시나리오 등 다양한 분야에서 활용 가능성을 확장해 나갈 수 있도록 개발되고 있으며, 아래와 같은 주요 특징을 가지고 있습니다:

• Tool Agent의 경우 non-thinking mode로 작동하며, 그 외의 모든 작업은 thinking mode로 작동합니다.
• 지시 사항을 정확히 따르도록 설계된 인간 선호 정렬 및 보다 자연스러운 대화를 제공합니다.
• 영어, 한국어, 중국어 및 일본어로 구성된 지시 이행과 번역을 지원합니다.

1. VAETKI Highlights

VAETKI is a large language model developed by the NC-AI consortium, a collaborative initiative led by NC-AI with participation from a total of 13 organizations. Designed with scalability and efficiency as primary goals, VAETKI adopts a Mixture-of-Experts (MoE) architecture to effectively balance performance and computational cost.

VAETKI is developed with both research and real-world applications in mind. It is intended to serve as a flexible foundation for a wide range of use cases, including advanced reasoning tasks, domain-specific knowledge applications, and agent-oriented systems, with the following key features:

• Non-thinking mode is applied for Tool Agent tasks.
• Strong human preference alignment for instruction following and delivering a more natural conversation.
• Support of English/Korean/Chinese/Japanese languages for instruction following (and translation).

2. Model Overview

VAETKI-112B-A10B has the following features:

• Type: Causal (Auto-regressive) Language Models
• Architecture: Transformers, MoE (Mixture of Experts)
• Developed by: NC-AI consortium (with ETRI, Korea University)
• Training Stage: Pretraining & Post-training
• Number of Parameters: 112.2B in total and 10.1B activated
• Number of Paramaters (Non-Embedding): 111.3B
• Number of Layers: 48
• Number of Attention Heads: 24
• Number of Experts: 128
• Number of Activated Experts: 8
• Context Length: 128k tokens
• Vocabulary Size: 126k
• Languages: Korean, English, Chinese, and Japanese
• License: MIT
• Related URLs: https://github.com/wbl-ncai/VAETKI/

For more details, please refer to our Technical Report - to be updated

3. How to Use

See the Quickstart for more details.

4. Training Details

Training Data

Dataset	# Tokens
FineWeb-2(kor_Hang)	54.5B
FineWeb2-HQ	338.9B
The Stack v2	1.571T
StackExchange_Mar2023	2.6B
finemath(finemath-3plus)	37.4B
finemath(infiwebmath-3plus)	23.7B
proof-pile-2	28.2B
Nemotron-CC-v2	3.360T
Nemotron-CC-Math-v1	214.3B
Nemotron-Pretraining-Code-v1	191.4B
Nemotron-Pretraining-SFT-v1	367.2B
DCLM-baseline-1.0	3.190T
WanJuan-Korean	68.9B
finemath(finemath-4plus)	10.4B
MegaMath	208.0B
Stack-Edu	86.7B
AceReason-1.1-SFT	31.4B
OpenScience-OS-Q2	18.1B
OpenScience-OS-Q3	0.7B
Nemotron-PrisMath	6.2B
OpenCodeGeneticInstruct-Qwen2.5-32b-instruct	6.8B
OpenCodeGeneticInstruct-mixtral-8x22b-instruct	9.0B
Total	9.8T

Training Procedure

• Hardware
  • Platform: Naver Cloud MLX Platform
  • GPUs: NVIDIA H100 80GB HBM3 × 1,016
  • Interconnect: InfiniBand 400 Gb/s, 6 lanes (4 lanes were used for RDMA-based inter-node communication)
• Software: The model architecture configuration, training loop, checkpointing, and distributed optimization logic were implemented based on Megatron-Core v0.14, with selective modifications to accommodate experimental requirements. The implementation includes internal modifications to the original frameworks for research and optimization purposes, and this model does not claim full compatibility with original upstream implementations.
• Hyperparameters

  Hyperparameters	Value
  Learning rate	2e-4 → 1e-4 → 8e-5
  Batch size	8.1M Tokens → 33M Tokens → 46M Tokens
  Context Length	4096 → 4096 → 32768

5. Evaluation Results

We evaluate VAETKI 112B-A10B on various benchmarks and compare it with a series of models, as shown in the following.

• Global Common Benchmarks

  Language	Tasks	Benchmark (Metric)	# Shot	gpt-oss-120b	Hunyuan-A13B-Instruct	VAETKI-112B-A10B
  		Architecture	-	MoE	MoE	MoE
  		# Total Params	-	117B	80B	112B
  		# Activated Params	-	5.1B	13B	10B
  Korean	General	NIA benchmark	x-shot	-	-	-
  	General	KMMLU-Pro	x-shot	-	-	-
  	General	CLIcK	x-shot	-	-	-
  	General	KoBALT	x-shot	-	-	-
  	Reasoning	HRM8K	x-shot	-	-	-
  English	General	MMLU-Pro	x-shot	-	-	-
  	Reasoning	GPQA-Diamond	x-shot	-	-	-
  	Reasoning	AIME `25	x-shot	-	-	-
  	Reasoning	HLE (text only)	x-shot	-	-	-
  	Reasoning	IFBench	x-shot	-	-	-
  	Reasoning	IFEval	x-shot	-	-	-
  	Code	LiveCodeBench v6	-	-	-	-
  	Agentic	Tau-Bench Telecom	x-shot	-	-	-
  	Long Context	AA-LCR	x-shot	-	-	-

• Global Additional Benchmarks

  Language	Tasks	Benchmark (Metric)	# Shots	Hunyuan-A13B-Instruct	VAETKI-112B-A10B
  		Architecture	-	MoE	MoE
  		# Total Params	-	80B	112B
  		# Activated Params	-	13B	10B
  English	General	MMLU-Pro	x-shot	-	-
  English	General	BBH	x-shot	-	-
  English	Reasoning	MATH-500	x-shot	-	-
  English	Reasoning	IFEval	x-shot	-	-
  English	Agentic	BFCL v3	x-shot	-	-

6. Limitations

• Limitations: This model may produce inaccurate or incomplete outputs, including hallucinated content, particularly for ambiguous prompts or tasks requiring high factual accuracy. It may have limitations in complex multi-step reasoning, precise mathematical computation, and strict correctness in code generation. The model does not have the ability to independently verify information.
• (Potential) Biases: The training data may contain social or cultural biases, which can be reflected in the model’s outputs. Despite mitigation efforts, biases related to gender, ethnicity, nationality, or religion may still occur.
• Out-of-Scope Use: This model is not designed for use in safety-critical or regulated domains, such as medical, legal, financial, or military applications. It should not be relied upon for decisions where errors could lead to harm.

7. License

This model repository is licensed under the MIT License. The use of VAETKI models is subject to the Model License.

8. Citation

@misc{ncai2025vaetkitechnicalreport,
      title={VAETKI Technical Report}, 
      author={NC-AI Consortium},
      year={2025},
      eprint={xxxx.xxxxx},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/xxxx.xxxxx}, 
}

9. Contact

If you are interested to leave a message or have any questions, please contact us at wbl.ncai.hf@gmail.com.