News 📢

• 🔧2025/10/29: Added support for function calling on vLLM with Mi:dm 2.0 parser.
• 📕2025/08/08: Published a technical blog article about Mi:dm 2.0 Model.
• ⚡️2025/07/04: Released Mi:dm 2.0 Model collection on Hugging Face🤗.

• Overview
  • Mi:dm 2.0
  • Quickstart
  • Evaluation
• Usage
  • Run on Friendli.AI
  • Run on Your Local Machine
  • Deployment
  • Tutorials
• More Information
  • Limitation
  • License
  • Contact

Overview

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.

[!Note] Neither the pre-training nor the post-training data includes KT users' data.

Quickstart

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-Base-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 = "KT에 대해 소개해줘"

# message for inference
messages = [
    {"role": "system", 
     "content": "Mi:dm(믿:음)은 KT에서 개발한 AI 기반 어시스턴트이다."},
    {"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]))

[!NOTE] The transformers library should be version 4.45.0 or higher.

Evaluation

Korean

* indicates KT proprietary evaluation resources.

English

Usage

Run on Friendli.AI

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

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

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

Basic Serving

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

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

With Function Calling

For advanced function calling tasks, you can serve Mi:dm 2.0 with our own tool parser:

1. Download and place Mi:dm 2.0 parser file in your working directory.
2. Run the following Docker command to launch the vLLM server with our custom parser file:

   docker run --rm -it --gpus all -p 8000:8000 \
       -e HUGGING_FACE_HUB_TOKEN="<YOUR_HUGGINGFACE_TOKEN>" \
       -v "$(pwd)/midm_parser.py:/custom/midm_parser.py" \
       vllm/vllm-openai:v0.11.0 \
       --model K-intelligence/Midm-2.0-Base-Instruct \
       --enable-auto-tool-choice \
       --tool-parser-plugin /custom/midm_parser.py \
       --tool-call-parser midm-parser \
       --host 0.0.0.0
   

[!Note] This setup is compatible with vllm/vllm-openai:v0.8.0 and later, but we strongly recommend using v0.11.0 for optimal stability and compatibility with our parser.

Tutorials

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

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