Midm-2.0-Mini-Instruct-gguf Open-source AI Model - Accurately processes Korean and has a deep understanding of South Korean social and cultural values

Midm 2.0 Mini Instruct Gguf

Developed by mykor

Mi:dm 2.0 is an AI model centered around South Korea, developed by KT using its proprietary technology. This model has deeply internalized the unique values, cognitive frameworks, and common-sense reasoning of South Korean society. It can not only process and generate Korean content but also reflect a profound understanding of South Korean social and cultural norms and values.

Large Language Model

Transformers

Supports Multiple LanguagesOpen Source License:MIT #Understanding of Korean culture #Korean AI #Lightweight deployment

Downloads 470

Release Time : 7/4/2025

Model Overview

Mi:dm 2.0 is an AI model focusing on Korean culture and language, offering two versions, Base and Mini, suitable for different scenarios. It is particularly adept at handling Korean-related tasks.

Model Features

Designed with a focus on South Korea

It has a deep understanding of South Korean social culture and can better handle Korean-related tasks.

Released in multiple versions

It offers two versions, Mi:dm 2.0 Base and Mi:dm 2.0 Mini, suitable for different scenarios respectively.

Supports multiple platforms

It can run on various platforms such as Friendli.AI and local machines.

Model Capabilities

Korean content generation

Understanding of Korean culture

Common-sense reasoning

Instruction following

English content generation

Use Cases

Cultural understanding

Analysis of South Korean social culture

Understand and generate content that reflects South Korean social and cultural norms

It performs excellently in South Korean social and cultural evaluations

Education

Korean learning assistance

Help non-Korean native speakers learn Korean and its culture

🚀 Mi:dm 2.0

Mi:dm 2.0 is a "Korea-centric AI" model developed with KT's proprietary technology, aiming to deeply understand and reflect the unique values and cognitive frameworks of Korean society.

Mi:dm 2.0 Models | Mi:dm 2.0 Technical Report | Mi:dm 2.0 Technical Blog*

_{*To be released soon}

🚀 Quick Start

News

🚀 (Coming Soon!) GGUF format model files will be available soon for easier local deployment.
📢 2025/07/04: Released Mi:dm 2.0 Model collection on Hugging Face.

Overview
Usage
More Information

Mi:dm 2.0

Mi:dm 2.0 is a "Korea-centric AI" model developed using KT's proprietary technology. The term "Korea-centric AI" refers to a model that deeply internalizes the unique values, cognitive frameworks, and commonsense reasoning inherent to Korean society. It goes beyond simply processing or generating Korean text—it reflects a deeper understanding of the socio-cultural norms and values that define Korean society.

Mi:dm 2.0 is released in two versions:

Mi:dm 2.0 Base
An 11.5B parameter dense model designed to balance model size and performance.
It extends an 8B-scale model by applying the Depth-up Scaling (DuS) method, making it suitable for real-world applications that require both performance and versatility.
Mi:dm 2.0 Mini
A lightweight 2.3B parameter dense model optimized for on-device environments and systems with limited GPU resources.
It was derived from the Base model through pruning and distillation to enable compact deployment.

⚠️ Important Note

Neither the pre-training nor the post-training data includes KT users' data.

Quickstart Code Example

Here is the code snippet to run conversational inference with the model:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig

model_name = "K-intelligence/Midm-2.0-Mini-Instruct"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
generation_config = GenerationConfig.from_pretrained(model_name)

prompt = "KTÏóê ÎåÄÌï¥ ÏÜåÍ∞úÌï¥Ï§ò"

# message for inference
messages = [
    {"role": "system", 
     "content": "Mi:dm(ÎØø:Ïùå)ÏùÄ KTÏóêÏÑú Í∞úÎ∞úÌïú AI Í∏∞Î∞ò Ïñ¥ÏãúÏä§ÌÑ¥Ìä∏Ïù¥Îã§."},
    {"role": "user", "content": prompt}
]

input_ids = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt"
)

output = model.generate(
    input_ids.to("cuda"),
    generation_config=generation_config,
    eos_token_id=tokenizer.eos_token_id,
    max_new_tokens=128,
    do_sample=False,
)
print(tokenizer.decode(output[0]))

⚠️ Important Note

The transformers library should be version 4.45.0 or higher.

🔍 Evaluation

Korean Evaluation Results

Model	Society & Culture					General Knowledge			Instruction Following
Model	K-Refer^*	K-Refer-Hard^*	Ko-Sovereign^*	HAERAE	Avg.	KMMLU	Ko-Sovereign^*	Avg.	Ko-IFEval	Ko-MTBench	Avg.
Qwen3-4B	53.6	42.9	35.8	50.6	45.7	50.6	42.5	46.5	75.9	63.0	69.4
Exaone-3.5-2.4B-inst	64.0	67.1	44.4	61.3	59.2	43.5	42.4	43.0	65.4	74.0	68.9
Mi:dm 2.0-Mini-inst	66.4	61.4	36.7	70.8	58.8	45.1	42.4	43.8	73.3	74.0	73.6

Qwen3-14B	72.4	65.7	49.8	68.4	64.1	55.4	54.7	55.1	83.6	71	77.3
Llama-3.1-8B-inst	43.2	36.4	33.8	49.5	40.7	33.0	36.7	34.8	60.1	57	58.5
Exaone-3.5-7.8B-inst	71.6	69.3	46.9	72.9	65.2	52.6	45.6	49.1	69.1	79.6	74.4
Mi:dm 2.0-Base-inst	89.6	86.4	56.3	81.5	78.4	57.3	58.0	57.7	82	89.7	85.9

Model	Comprehension					Reasoning
Model	K-Prag^*	K-Refer-Hard^*	Ko-Best	Ko-Sovereign^*	Avg.	Ko-Winogrande	Ko-Best	LogicKor	HRM8K	Avg.
Qwen3-4B	73.9	56.7	91.5	43.5	66.6	67.5	69.2	5.6	56.7	43.8
Exaone-3.5-2.4B-inst	68.7	58.5	87.2	38.0	62.5	60.3	64.1	7.4	38.5	36.7
Mi:dm 2.0-Mini-inst	69.5	55.4	80.5	42.5	61.9	61.7	64.5	7.7	39.9	37.4

Qwen3-14B	86.7	74.0	93.9	52.0	76.8	77.2	75.4	6.4	64.5	48.8
Llama-3.1-8B-inst	59.9	48.6	77.4	31.5	51.5	40.1	26.0	2.4	30.9	19.8
Exaone-3.5-7.8B-inst	73.5	61.9	92.0	44.0	67.2	64.6	60.3	8.6	49.7	39.5
Mi:dm 2.0-Base-inst	86.5	70.8	95.2	53.0	76.1	75.1	73.0	8.6	52.9	44.8

* indicates KT proprietary evaluation resources.

English Evaluation Results

Model	Instruction	Reasoning				Math	Coding	General Knowledge
Model	IFEval	BBH	GPQA	MuSR	Avg.	GSM8K	MBPP+	MMLU-pro	MMLU	Avg.
Qwen3-4B	79.7	79.0	39.8	58.5	59.1	90.4	62.4	-	73.3	73.3
Exaone-3.5-2.4B-inst	81.1	46.4	28.1	49.7	41.4	82.5	59.8	-	59.5	59.5
Mi:dm 2.0-Mini-inst	73.6	44.5	26.6	51.7	40.9	83.1	60.9	-	56.5	56.5

Qwen3-14B	83.9	83.4	49.8	57.7	63.6	88.0	73.4	70.5	82.7	76.6
Llama-3.1-8B-inst	79.9	60.3	21.6	50.3	44.1	81.2	81.8	47.6	70.7	59.2
Exaone-3.5-7.8B-inst	83.6	50.1	33.1	51.2	44.8	81.1	79.4	40.7	69.0	54.8
Mi:dm 2.0-Base-inst	84.0	77.7	33.5	51.9	54.4	91.6	77.5	53.3	73.7	63.5

💻 Usage

Run on Friendli.AI

You can try our model immediately via Friendli.AI. Simply click Deploy and then Friendli Endpoints.

⚠️ Important Note

Please note that a login to Friendli.AI is required after your fifth chat interaction.

Left Image Right Image

Run on Your Local Machine

We provide a detailed description about running Mi:dm 2.0 on your local machine using llama.cpp, LM Studio, and Ollama. Please check our github for more information

Deployment

To serve Mi:dm 2.0 using vLLM(>=0.8.0) with an OpenAI-compatible API:

vllm serve K-intelligence/Midm-2.0-Mini-Instruct

Tutorials

To help our end-users easily use Mi:dm 2.0, we have provided comprehensive tutorials on github.

ℹ️ More Information

Limitation

The training data for both Mi:dm 2.0 models consists primarily of English and Korean. Understanding and generation in other languages are not guaranteed.
The model is not guaranteed to provide reliable advice in fields that require professional expertise, such as law, medicine, or finance.
Researchers have made efforts to exclude unethical content from the training data — such as profanity, slurs, bias, and discriminatory language. However, despite these efforts, the model may still produce inappropriate expressions or factual inaccuracies.

License

Mi:dm 2.0 is licensed under the MIT License.

Contact

Mi:dm 2.0 Technical Inquiries: midm-llm@kt.com

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご